Author name cluster

Georg Martius

Possible papers associated with this exact author name in Arrow. This page groups case-insensitive exact name matches and is not a full identity disambiguation profile.

72 papers

2 author rows

IROS Conference 2025 Conference Paper

A Smooth Analytical Formulation of Collision Detection and Rigid Body Dynamics With Contact

Onur Beker
Nico Gürtler
Ji Shi
Andreas René Geist
Amirreza Razmjoo
Georg Martius
Sylvain Calinon

Generating intelligent robot behavior in contact-rich settings is a research problem where zeroth-order methods currently prevail. A major contributor to the success of such methods is their robustness in the face of non-smooth and discontinuous optimization landscapes that are characteristic of contact interactions, yet zeroth-order methods remain computationally inefficient. It is therefore desirable to develop methods for perception, planning and control in contact-rich settings that can achieve further efficiency by making use of first and second order information (i. e. , gradients and Hessians). To facilitate this, we present a joint formulation of collision detection and contact modelling which, compared to existing differentiable simulation approaches, provides the following benefits: i) it results in forward and inverse dynamics that are entirely analytical (i. e. do not require solving optimization or root-finding problems with iterative methods) and smooth (i. e. twice differentiable), ii) it supports arbitrary collision geometries without needing a convex decomposition, and iii) its runtime is independent of the number of contacts. Through simulation experiments, we demonstrate the validity of the proposed formulation as a "physics for inference" that can facilitate future development of efficient methods to generate intelligent contact-rich behavior.

ICML Conference 2025 Conference Paper

Active Fine-Tuning of Multi-Task Policies

Marco Bagatella
Jonas Hübotter
Georg Martius
Andreas Krause 0001

Pre-trained generalist policies are rapidly gaining relevance in robot learning due to their promise of fast adaptation to novel, in-domain tasks. This adaptation often relies on collecting new demonstrations for a specific task of interest and applying imitation learning algorithms, such as behavioral cloning. However, as soon as several tasks need to be learned, we must decide which tasks should be demonstrated and how often? We study this multi-task problem and explore an interactive framework in which the agent adaptively selects the tasks to be demonstrated. We propose AMF (Active Multi-task Fine-tuning), an algorithm to maximize multi-task policy performance under a limited demonstration budget by collecting demonstrations yielding the largest information gain on the expert policy. We derive performance guarantees for AMF under regularity assumptions and demonstrate its empirical effectiveness to efficiently fine-tune neural policies in complex and high-dimensional environments.

ICLR Conference 2025 Conference Paper

Advancing Out-of-Distribution Detection via Local Neuroplasticity

Alessandro Canevaro
Julian Schmidt
Mohammad Sajad Marvi
Hang Yu
Georg Martius
Julian Jordan

In the domain of machine learning, the assumption that training and test data share the same distribution is often violated in real-world scenarios, requiring effective out-of-distribution (OOD) detection. This paper presents a novel OOD detection method that leverages the unique local neuroplasticity property of Kolmogorov-Arnold Networks (KANs). Unlike traditional multilayer perceptrons, KANs exhibit local plasticity, allowing them to preserve learned information while adapting to new tasks. Our method compares the activation patterns of a trained KAN against its untrained counterpart to detect OOD samples. We validate our approach on benchmarks from image and medical domains, demonstrating superior performance and robustness compared to state-of-the-art techniques. These results underscore the potential of KANs in enhancing the reliability of machine learning systems in diverse environments.

IROS Conference 2025 Conference Paper

DB-MPO: Demonstration Boosted Reactive Grasping For Two-Finger Gripper

Boya Zhang
Andreas Zell
Georg Martius

Prior knowledge vastly exists in the automation industry, especially for tasks like pick-and-place, where simple programmatic demonstrations with online generation ability can be acquired easily. How to learn a policy faster with higher flexibility and generalization ability based on these demonstrations is a question to be answered. End-to-end target learning and imitation learning are widely discussed in previous works. Here, we focus on the online generation ability of the demonstration and propose a demo injection method based on actor-critic off-policy reinforcement learning (RL) for the interaction and policy optimization phase. We conduct experiments and an ablation study based on four research questions around a two-finger reactive grasping task with a Panda robot. The result shows our proposed injection method increases the training stability, strongly reduces the time to convergence and benefits sim-2-real transfer with smooth motion.

TMLR Journal 2025 Journal Article

Directed Exploration in Reinforcement Learning from Linear Temporal Logic

Marco Bagatella
Andreas Krause
Georg Martius

Linear temporal logic (LTL) is a powerful language for task specification in reinforcement learning, as it allows describing objectives beyond the expressivity of conventional discounted return formulations. Nonetheless, recent works have shown that LTL formulas can be translated into a variable rewarding and discounting scheme, whose optimization produces a policy maximizing a lower bound on the probability of formula satisfaction. However, the synthesized reward signal remains fundamentally sparse, making exploration challenging. We aim to overcome this limitation, which can prevent current algorithms from scaling beyond low-dimensional, short-horizon problems. We show how better exploration can be achieved by further leveraging the LTL specification and casting its corresponding Limit Deterministic Büchi Automaton (LDBA) as a Markov reward process, thus enabling a form of high-level value estimation. By taking a Bayesian perspective over LDBA dynamics and proposing a suitable prior distribution, we show that the values estimated through this procedure can be treated as a shaping potential and mapped to informative intrinsic rewards. Empirically, we demonstrate applications of our method from tabular settings to high-dimensional continuous systems, which have so far represented a significant challenge for LTL-based reinforcement learning algorithms.

RLJ Journal 2025 Journal Article

Epistemically-guided forward-backward exploration

Núria Armengol Urpí
Marin Vlastelica
Georg Martius
Stelian Coros

Zero-shot reinforcement learning is necessary for extracting optimal policies in absence of concrete rewards for fast adaptation to future problem settings. Forward-backward representations ($FB$) have emerged as a promising method for learning optimal policies in absence of rewards via a factorization of the policy occupancy measure. However, up until now, $FB$ and many similar zero-shot reinforcement learning algorithms have been decoupled from the exploration problem, generally relying on other exploration algorithms for data collection. We argue that $FB$ representations should fundamentally be used for exploration in order to learn more efficiently. With this goal in mind, we design exploration policies that arise naturally from the $FB$ representation that minimize the posterior variance of the $FB$ representation, hence minimizing its epistemic uncertainty. We empirically demonstrate that such principled exploration strategies improve sample complexity of the $FB$ algorithm considerably in comparison to other exploration methods.

RLC Conference 2025 Conference Paper

Epistemically-guided forward-backward exploration

Núria Armengol Urpí
Marin Vlastelica
Georg Martius
Stelian Coros

Zero-shot reinforcement learning is necessary for extracting optimal policies in absence of concrete rewards for fast adaptation to future problem settings. Forward-backward representations ($FB$) have emerged as a promising method for learning optimal policies in absence of rewards via a factorization of the policy occupancy measure. However, up until now, $FB$ and many similar zero-shot reinforcement learning algorithms have been decoupled from the exploration problem, generally relying on other exploration algorithms for data collection. We argue that $FB$ representations should fundamentally be used for exploration in order to learn more efficiently. With this goal in mind, we design exploration policies that arise naturally from the $FB$ representation that minimize the posterior variance of the $FB$ representation, hence minimizing its epistemic uncertainty. We empirically demonstrate that such principled exploration strategies improve sample complexity of the $FB$ algorithm considerably in comparison to other exploration methods.

EWRL Workshop 2025 Workshop Paper

Epistemically-guided forward-backward exploration

Núria Armengol Urpí
Marin Vlastelica
Georg Martius
Stelian Coros

Zero-shot reinforcement learning is necessary for extracting optimal policies in absence of concrete rewards for fast adaptation to future problem settings. Forward-backward representations (FB) have emerged as a promising method for learning optimal policies in absence of rewards via a factorization of the policy occupancy measure. However, up until now, FB and many similar zero-shot reinforcement learning algorithms have been decoupled from the exploration problem, generally relying on other exploration algorithms for data collection. We argue that FB representations should fundamentally be used for exploration in order to learn more efficiently. With this goal in mind, we design exploration policies that arise naturally from the FB representation that minimize the posterior variance of the FB representation, hence minimizing its epistemic uncertainty. We empirically demonstrate that such principled exploration strategies improve sample complexity of the FB algorithm considerably in comparison to other exploration methods.

NeurIPS Conference 2025 Conference Paper

Forecasting in Offline Reinforcement Learning for Non-stationary Environments

Suzan Ece Ada
Georg Martius
Emre Ugur
Erhan Oztop

Offline Reinforcement Learning (RL) provides a promising avenue for training policies from pre-collected datasets when gathering additional interaction data is infeasible. However, existing offline RL methods often assume stationarity or only consider synthetic perturbations at test time, assumptions that often fail in real-world scenarios characterized by abrupt, time-varying offsets. These offsets can lead to partial observability, causing agents to misperceive their true state and degrade performance. To overcome this challenge, we introduce Forecasting in Non-stationary Offline RL (FORL), a framework that unifies (i) conditional diffusion-based candidate state generation, trained without presupposing any specific pattern of future non-stationarity, and (ii) zero-shot time-series foundation models. FORL targets environments prone to unexpected, potentially non-Markovian offsets, requiring robust agent performance from the onset of each episode. Empirical evaluations on offline RL benchmarks, augmented with real-world time-series data to simulate realistic non-stationarity, demonstrate that FORL consistently improves performance compared to competitive baselines. By integrating zero-shot forecasting with the agent's experience, we aim to bridge the gap between offline RL and the complexities of real-world, non-stationary environments.

RLJ Journal 2025 Journal Article

Long-Horizon Planning with Predictable Skills

Nico Gürtler
Georg Martius

Model-based reinforcement learning (RL) leverages learned world models to plan ahead or train in imagination. Recently, this approach has significantly improved sample efficiency and performance across various challenging domains ranging from playing games to controlling robots. However, there are fundamental limits to how accurate the long-term predictions of a world model can be, for example due to unstable environment dynamics or partial observability. These issues are further exacerbated by the compounding error problem. Model-based RL is therefore currently limited to short rollouts with the world model, and consequently struggles with long-horizon problems. We argue that this limitation can be addressed by modeling the outcome of temporally extended skills instead of the effect of primitive actions. To this end, we propose a mutual-information-based skill learning objective that ensures predictable, diverse, and task-related behavior. The resulting skills compensate for perturbations and drifts, enabling stable long-horizon planning. We design a sample-efficient hierarchical agent consisting of model predictive control with an abstract skill world model on the higher level, and skill execution on the lower level. We demonstrate that our approach, Stable Planning with Temporally Extended Skills (SPlaTES), solves a range of challenging long-horizon continuous control problems, outperforming competitive model-based and skill-based methods.

EWRL Workshop 2025 Workshop Paper

Long-Horizon Planning with Predictable Skills

Nico Gürtler
Georg Martius

Model-based reinforcement learning (RL) leverages learned world models to plan ahead or train in imagination. Recently, this approach has significantly improved sample efficiency and performance across various challenging domains ranging from playing games to controlling robots. However, there are fundamental limits to how accurate the long-term predictions of a world model can be, for example due to unstable environment dynamics or partial observability. These issues are further exacerbated by the compounding error problem. Model-based RL is therefore currently limited to short rollouts with the world model, and consequently struggles with long-horizon problems. We argue that this limitation can be addressed by modeling the outcome of temporally extended skills instead of the effect of primitive actions. To this end, we propose a mutual-information-based skill learning objective that ensures predictable, diverse, and task-related behavior. The resulting skills compensate for perturbations and drifts, enabling stable long-horizon planning. We design a sample-efficient hierarchical agent consisting of model predictive control with an abstract skill world model on the higher level, and skill execution on the lower level. We demonstrate that our approach, Stable Planning with Temporally Extended Skills (SPlaTES), solves a range of challenging long-horizon continuous control problems, outperforming competitive model-based and skill-based methods.

RLC Conference 2025 Conference Paper

Long-Horizon Planning with Predictable Skills

Nico Gürtler
Georg Martius

Model-based reinforcement learning (RL) leverages learned world models to plan ahead or train in imagination. Recently, this approach has significantly improved sample efficiency and performance across various challenging domains ranging from playing games to controlling robots. However, there are fundamental limits to how accurate the long-term predictions of a world model can be, for example due to unstable environment dynamics or partial observability. These issues are further exacerbated by the compounding error problem. Model-based RL is therefore currently limited to short rollouts with the world model, and consequently struggles with long-horizon problems. We argue that this limitation can be addressed by modeling the outcome of temporally extended skills instead of the effect of primitive actions. To this end, we propose a mutual-information-based skill learning objective that ensures predictable, diverse, and task-related behavior. The resulting skills compensate for perturbations and drifts, enabling stable long-horizon planning. We design a sample-efficient hierarchical agent consisting of model predictive control with an abstract skill world model on the higher level, and skill execution on the lower level. We demonstrate that our approach, Stable Planning with Temporally Extended Skills (SPlaTES), solves a range of challenging long-horizon continuous control problems, outperforming competitive model-based and skill-based methods.

RLJ Journal 2025 Journal Article

Offline vs. Online Learning in Model-based RL: Lessons for Data Collection Strategies

Jiaqi Chen
Ji Shi
Cansu Sancaktar
Jonas Frey
Georg Martius

Data collection is crucial for learning robust world models in model-based reinforcement learning. The most prevalent strategies are to actively collect trajectories by interacting with the environment during online training or training on offline datasets. At first glance, the nature of learning task-agnostic environment dynamics makes world models a good candidate for effective offline training. However, the effects of online vs. offline data on world models and thus on the resulting task performance have not been thoroughly studied in the literature. In this work, we investigate both paradigms in model-based settings, conducting experiments on 31 different environments. First, we showcase that online agents outperform their offline counterparts. We identify a key challenge behind performance degradation of offline agents: encountering Out-Of-Distribution states at test time. This issue arises because, without the self-correction mechanism in online agents, offline datasets with limited state space coverage induce a mismatch between the agent's imagination and real rollouts, compromising policy training. We demonstrate that this issue can be mitigated by allowing for additional online interactions in a fixed or adaptive schedule, restoring the performance of online training with limited interaction data. We also showcase that incorporating exploration data helps mitigate the performance degradation of offline agents. Based on our insights, we recommend adding exploration data when collecting large datasets, as current efforts predominantly focus on expert data alone.

RLC Conference 2025 Conference Paper

Offline vs. Online Learning in Model-based RL: Lessons for Data Collection Strategies

Jiaqi Chen
Ji Shi
Cansu Sancaktar
Jonas Frey
Georg Martius

Data collection is crucial for learning robust world models in model-based reinforcement learning. The most prevalent strategies are to actively collect trajectories by interacting with the environment during online training or training on offline datasets. At first glance, the nature of learning task-agnostic environment dynamics makes world models a good candidate for effective offline training. However, the effects of online vs. offline data on world models and thus on the resulting task performance have not been thoroughly studied in the literature. In this work, we investigate both paradigms in model-based settings, conducting experiments on 31 different environments. First, we showcase that online agents outperform their offline counterparts. We identify a key challenge behind performance degradation of offline agents: encountering Out-Of-Distribution states at test time. This issue arises because, without the self-correction mechanism in online agents, offline datasets with limited state space coverage induce a mismatch between the agent's imagination and real rollouts, compromising policy training. We demonstrate that this issue can be mitigated by allowing for additional online interactions in a fixed or adaptive schedule, restoring the performance of online training with limited interaction data. We also showcase that incorporating exploration data helps mitigate the performance degradation of offline agents. Based on our insights, we recommend adding exploration data when collecting large datasets, as current efforts predominantly focus on expert data alone.

ICLR Conference 2025 Conference Paper

On the Transfer of Object-Centric Representation Learning

Aniket Rajiv Didolkar
Andrii Zadaianchuk
Anirudh Goyal
Michael Mozer
Yoshua Bengio
Georg Martius
Maximilian Seitzer

The goal of object-centric representation learning is to decompose visual scenes into a structured representation that isolates the entities into individual vectors. Recent successes have shown that object-centric representation learning can be scaled to real-world scenes by utilizing features from pre-trained foundation models like DINO. However, so far, these object-centric methods have mostly been applied in-distribution, with models trained and evaluated on the same dataset. This is in contrast to the underlying foundation models, which have been shown to be applicable to a wide range of data and tasks. Thus, in this work, we answer the question of whether current real-world capable object-centric methods exhibit similar levels of transferability by introducing a benchmark comprising seven different synthetic and real-world datasets. We analyze the factors influencing performance under transfer and find that training on diverse real-world images improves generalization to unseen scenarios. Furthermore, inspired by the success of task-specific fine-tuning in foundation models, we introduce a novel fine-tuning strategy to adapt pre-trained vision encoders for the task of object discovery. We find that the proposed approach results in state-of-the-art performance for unsupervised object discovery, exhibiting strong zero-shot transfer to unseen datasets.

EWRL Workshop 2025 Workshop Paper

SENSEI: Semantic Exploration Guided by Foundation Models to Learn Versatile World Models

Cansu Sancaktar
Christian Gumbsch
Andrii Zadaianchuk
Pavel Kolev
Georg Martius

Exploration is a cornerstone of reinforcement learning (RL). Intrinsic motivation attempts to decouple exploration from external, task-based rewards. However, established approaches to intrinsic motivation that follow general principles such as information gain, often only uncover low-level interactions. In contrast, children’s play suggests that they engage in meaningful high-level behavior by imitating or interacting with their caregivers. Recent work has focused on using foundation models to inject these semantic biases into exploration. However, these methods often rely on unrealistic assumptions, such as language-embedded environments or access to high-level actions. We propose SEmaNtically Sensible ExploratIon (SENSEI), a framework to equip model-based RL agents with an intrinsic mo- tivation for semantically meaningful behavior. SENSEI distills a reward signal of interestingness from Vision Language Model (VLM) annotations, enabling an agent to predict these rewards through a world model. Using model-based RL, SENSEI trains an exploration policy that jointly maximizes semantic rewards and uncertainty. We show that in both robotic and video game-like simulations SENSEI discovers a variety of meaningful behaviors from image observations and low-level actions. SENSEI provides a general tool for learning from foundation model feedback, a crucial research direction, as VLMs become more powerful.

ICML Conference 2025 Conference Paper

SENSEI: Semantic Exploration Guided by Foundation Models to Learn Versatile World Models

Cansu Sancaktar
Christian Gumbsch
Andrii Zadaianchuk
Pavel Kolev
Georg Martius

Exploration is a cornerstone of reinforcement learning (RL). Intrinsic motivation attempts to decouple exploration from external, task-based rewards. However, established approaches to intrinsic motivation that follow general principles such as information gain, often only uncover low-level interactions. In contrast, children’s play suggests that they engage in meaningful high-level behavior by imitating or interacting with their caregivers. Recent work has focused on using foundation models to inject these semantic biases into exploration. However, these methods often rely on unrealistic assumptions, such as language-embedded environments or access to high-level actions. We propose SEmaNtically Sensible ExploratIon (SENSEI), a framework to equip model-based RL agents with an intrinsic motivation for semantically meaningful behavior. SENSEI distills a reward signal of interestingness from Vision Language Model (VLM) annotations, enabling an agent to predict these rewards through a world model. Using model-based RL, SENSEI trains an exploration policy that jointly maximizes semantic rewards and uncertainty. We show that in both robotic and video game-like simulations SENSEI discovers a variety of meaningful behaviors from image observations and low-level actions. SENSEI provides a general tool for learning from foundation model feedback, a crucial research direction, as VLMs become more powerful.

EWRL Workshop 2025 Workshop Paper

Test-time Offline Reinforcement Learning on Goal-related Experience

Marco Bagatella
Mert Albaba
Jonas Hübotter
Georg Martius
Andreas Krause

Foundation models compress a large amount of information in a single, large neural network, which can then be queried for individual tasks. There are strong parallels between this widespread framework and offline goal-conditioned reinforcement learning algorithms: a universal value function is trained on a large number of goals, and the policy is evaluated on a single goal in each test episode. Extensive research in foundation models has shown that performance can be substantially improved through test-time training, specializing the model to the current goal. We find similarly that test-time offline reinforcement learning on experience related to the test goal can lead to substantially better policies at minimal compute costs. We propose a novel self-supervised data selection criterion, which selects transitions from an offline dataset according to their relevance to the current state and quality with respect to the evaluation goal. We demonstrate across a wide range of high-dimensional loco-navigation and manipulation tasks that fine-tuning a policy on the selected data for a few gradient steps leads to significant performance gains over standard offline pre-training. Our goal-conditioned test-time training (GC-TTT) algorithm applies this routine in a receding-horizon fashion during evaluation, adapting the policy to the current trajectory as it is being rolled out. Finally, we study compute allocation at inference, demonstrating that, at comparable costs, GC-TTT induces performance gains that are not achievable by scaling model size.

ICRA Conference 2025 Conference Paper

The Role of Tactile Sensing for Learning Reach and Grasp

Boya Zhang
Iris Andrussow
Andreas Zell
Georg Martius

Stable and robust robotic grasping is essential for current and future robot applications. In recent works, the use of large datasets and supervised learning has enhanced speed and precision in antipodal grasping. However, these methods struggle with perception and calibration errors due to large planning horizons. To obtain more robust and reactive grasping motions, leveraging reinforcement learning combined with tactile sensing is a promising direction. Yet, there is no systematic evaluation of how the complexity of force-based tactile sensing affects the learning behavior for grasping tasks. This paper compares various tactile and environmental setups using two model-free reinforcement learning approaches for antipodal grasping. Our findings suggest that under imperfect visual perception, various tactile features improve learning outcomes, while complex tactile inputs complicate training.

ICML Conference 2025 Conference Paper

Zero-Shot Offline Imitation Learning via Optimal Transport

Thomas Rupf
Marco Bagatella
Nico Gürtler
Jonas Frey
Georg Martius

Zero-shot imitation learning algorithms hold the promise of reproducing unseen behavior from as little as a single demonstration at test time. Existing practical approaches view the expert demonstration as a sequence of goals, enabling imitation with a high-level goal selector, and a low-level goal-conditioned policy. However, this framework can suffer from myopic behavior: the agent’s immediate actions towards achieving individual goals may undermine long-term objectives. We introduce a novel method that mitigates this issue by directly optimizing the occupancy matching objective that is intrinsic to imitation learning. We propose to lift a goal-conditioned value function to a distance between occupancies, which are in turn approximated via a learned world model. The resulting method can learn from offline, suboptimal data, and is capable of non-myopic, zero-shot imitation, as we demonstrate in complex, continuous benchmarks. The code is available at https: //github. com/martius-lab/zilot.

ICML Conference 2024 Conference Paper

Causal Action Influence Aware Counterfactual Data Augmentation

Núria Armengol Urpí
Marco Bagatella
Marin Vlastelica
Georg Martius

Offline data are both valuable and practical resources for teaching robots complex behaviors. Ideally, learning agents should not be constrained by the scarcity of available demonstrations, but rather generalize beyond the training distribution. However, the complexity of real-world scenarios typically requires huge amounts of data to prevent neural network policies from picking up on spurious correlations and learning non-causal relationships. We propose CAIAC, a data augmentation method that can create feasible synthetic transitions from a fixed dataset without having access to online environment interactions. By utilizing principled methods for quantifying causal influence, we are able to perform counterfactual reasoning by swapping $\textit{action}$-unaffected parts of the state-space between independent trajectories in the dataset. We empirically show that this leads to a substantial increase in robustness of offline learning algorithms against distributional shift.

AAAI Conference 2024 Conference Paper

Colored Noise in PPO: Improved Exploration and Performance through Correlated Action Sampling

Jakob Hollenstein
Georg Martius
Justus Piater

Proximal Policy Optimization (PPO), a popular on-policy deep reinforcement learning method, employs a stochastic policy for exploration. In this paper, we propose a colored noise-based stochastic policy variant of PPO. Previous research highlighted the importance of temporal correlation in action noise for effective exploration in off-policy reinforcement learning. Building on this, we investigate whether correlated noise can also enhance exploration in on-policy methods like PPO. We discovered that correlated noise for action selection improves learning performance and outperforms the currently popular uncorrelated white noise approach in on-policy methods. Unlike off-policy learning, where pink noise was found to be highly effective, we found that a colored noise, intermediate between white and pink, performed best for on-policy learning in PPO. We examined the impact of varying the amount of data collected for each update by modifying the number of parallel simulation environments for data collection and observed that with a larger number of parallel environments, more strongly correlated noise is beneficial. Due to the significant impact and ease of implementation, we recommend switching to correlated noise as the default noise source in PPO.

PDF Details DOI

EWRL Workshop 2024 Workshop Paper

Directed Exploration in Reinforcement Learning from Linear Temporal Logic

Marco Bagatella
Andreas Krause
Georg Martius

Linear temporal logic (LTL) is a powerful language for task specification in reinforcement learning, as it allows describing objectives beyond the expressivity of conventional discounted return formulations. Nonetheless, recent works have shown that LTL formulas can be translated into a variable rewarding and discounting scheme, whose optimization produces a policy maximizing a lower bound on the probability of formula satisfaction. However, the synthesized reward signal remains fundamentally sparse, making exploration challenging. We aim to overcome this limitation, which can prevent current algorithms from scaling beyond low-dimensional, short-horizon problems. We show how better exploration can be achieved by further leveraging the LTL specification and casting its corresponding Limit Deterministic Büchi Automaton (LDBA) as a Markov reward process, thus enabling a form of high-level value estimation. By taking a Bayesian perspective over LDBA dynamics and proposing a suitable prior distribution, we show that the values estimated through this procedure can be treated as a shaping potential and mapped to informative intrinsic rewards. Empirically, we demonstrate applications of our method from tabular settings to high-dimensional continuous systems, which have so far represented a significant challenge for LTL-based reinforcement learning algorithms.

EWRL Workshop 2024 Workshop Paper

Dual-Force: Enhanced Offline Diversity Maximization under Imitation Constraints

Pavel Kolev
Marin Vlastelica
Georg Martius

While many algorithms for diversity maximization under imitation constraints are online in nature, many applications require offline algorithms without environment interactions. Tackling this problem in the offline setting, however, presents significant challenges that require non-trivial, multi-stage optimization processes with non-stationary rewards. In this work, we present a novel offline algorithm that enhances diversity using an objective based on Van der Waals (VdW) force and successor features, and eliminates the need to learn a previously used skill discriminator. Moreover, by conditioning the value function and policy on a pre-trained Functional Reward Encoding (FRE), our method allows for better handling of non-stationary rewards and provides zero-shot recall of all skills encountered during training, significantly expanding the set of skills learned in prior work. Consequently, our algorithm benefits from receiving a consistently strong diversity signal (VdW), and enjoys more stable and efficient training. We demonstrate the effectiveness of our method in generating diverse skills for two robotic tasks in simulation: locomotion of a quadruped and local navigation with obstacle traversal.

ICLR Conference 2024 Conference Paper

Emergent mechanisms for long timescales depend on training curriculum and affect performance in memory tasks

Sina Khajehabdollahi
Roxana Zeraati
Emmanouil Giannakakis
Tim Jakob Schäfer
Georg Martius
Anna Levina

Recurrent neural networks (RNNs) in the brain and \emph{in silico} excel at solving tasks with intricate temporal dependencies. Long timescales required for solving such tasks can arise from properties of individual neurons (single-neuron timescale, $\tau$, e.g., membrane time constant in biological neurons) or recurrent interactions among them (network-mediated timescale, $\tau_\textrm{\small{net}}$). However, the contribution of each mechanism for optimally solving memory-dependent tasks remains poorly understood. Here, we train RNNs to solve $N$-parity and $N$-delayed match-to-sample tasks with increasing memory requirements controlled by $N$, by simultaneously optimizing recurrent weights and $\tau$s. We find that RNNs develop longer timescales with increasing $N$, but depending on the learning objective, they use different mechanisms. Two distinct curricula define learning objectives: sequential learning of a single-$N$ (single-head) or simultaneous learning of multiple $N$s (multi-head). Single-head networks increase their $\tau$ with $N$ and can solve large-$N$ tasks, but suffer from catastrophic forgetting. However, multi-head networks, which are explicitly required to hold multiple concurrent memories, keep $\tau$ constant and develop longer timescales through recurrent connectivity. We show that the multi-head curriculum increases training speed and stability to perturbations, and allows generalization to tasks beyond the training set. This curriculum also significantly improves training GRUs and LSTMs for large-$N$ tasks. Our results suggest that adapting timescales to task requirements via recurrent interactions allows learning more complex objectives and improves the RNN's performance.

ICRA Conference 2024 Conference Paper

Learning Diverse Skills for Local Navigation under Multi-constraint Optimality

Jin Cheng 0002
Marin Vlastelica
Pavel Kolev
Chenhao Li
Georg Martius

Despite many successful applications of data-driven control in robotics, extracting meaningful diverse behaviors remains a challenge. Typically, task performance needs to be compromised in order to achieve diversity. In many scenarios, task requirements are specified as a multitude of reward terms, each requiring a different trade-off. In this work, we take a constrained optimization viewpoint on the quality-diversity trade-off and show that we can obtain diverse policies while imposing constraints on their value functions which are defined through distinct rewards. In line with previous work, further control of the diversity level can be achieved through an attract-repel reward term motivated by the Van der Waals force. We demonstrate the effectiveness of our method on a local navigation task where a quadruped robot needs to reach the target within a finite horizon. Finally, our trained policies transfer well to the real 12-DoF quadruped robot, Solo12, and exhibit diverse agile behaviors with successful obstacle traversal.

ICLR Conference 2024 Conference Paper

Learning Hierarchical World Models with Adaptive Temporal Abstractions from Discrete Latent Dynamics

Christian Gumbsch
Noor Sajid
Georg Martius
Martin V. Butz

Hierarchical world models can significantly improve model-based reinforcement learning (MBRL) and planning by enabling reasoning across multiple time scales. Nonetheless, the majority of state-of-the-art MBRL methods employ flat, non-hierarchical models. We propose Temporal Hierarchies from Invariant Context Kernels (THICK), an algorithm that learns a world model hierarchy via discrete latent dynamics. The lower level of THICK updates parts of its latent state sparsely in time, forming invariant contexts. The higher level exclusively predicts situations involving context changes. Our experiments demonstrate that THICK learns categorical, interpretable, temporal abstractions on the high level, while maintaining precise low-level predictions. Furthermore, we show that the emergent hierarchical predictive model seamlessly enhances the abilities of MBRL or planning methods. We believe that THICK contributes to the further development of hierarchical agents capable of more sophisticated planning and reasoning abilities.

ICML Conference 2024 Conference Paper

Learning with 3D rotations, a hitchhiker's guide to SO(3)

Andreas René Geist
Jonas Frey
Mikel Zhobro
Anna Levina
Georg Martius

Many settings in machine learning require the selection of a rotation representation. However, choosing a suitable representation from the many available options is challenging. This paper acts as a survey and guide through rotation representations. We walk through their properties that harm or benefit deep learning with gradient-based optimization. By consolidating insights from rotation-based learning, we provide a comprehensive overview of learning functions with rotation representations. We provide guidance on selecting representations based on whether rotations are in the model’s input or output and whether the data primarily comprises small angles.

ICML Conference 2024 Conference Paper

LPGD: A General Framework for Backpropagation through Embedded Optimization Layers

Anselm Paulus
Georg Martius
Vít Musil

Embedding parameterized optimization problems as layers into machine learning architectures serves as a powerful inductive bias. Training such architectures with stochastic gradient descent requires care, as degenerate derivatives of the embedded optimization problem often render the gradients uninformative. We propose Lagrangian Proximal Gradient Descent (LPGD), a flexible framework for training architectures with embedded optimization layers that seamlessly integrates into automatic differentiation libraries. LPGD efficiently computes meaningful replacements of the degenerate optimization layer derivatives by re-running the forward solver oracle on a perturbed input. LPGD captures various previously proposed methods as special cases, while fostering deep links to traditional optimization methods. We theoretically analyze our method and demonstrate on historical and synthetic data that LPGD converges faster than gradient descent even in a differentiable setup.

ICML Conference 2024 Conference Paper

Modelling Microbial Communities with Graph Neural Networks

Albane Ruaud
Cansu Sancaktar
Marco Bagatella
Christoph Ratzke
Georg Martius

Understanding the interactions and interplay of microorganisms is a great challenge with many applications in medical and environmental settings. In this work, we model bacterial communities directly from their genomes using graph neural networks (GNNs). GNNs leverage the inductive bias induced by the set nature of bacteria, enforcing permutation invariance and granting combinatorial generalization. We propose to learn the dynamics implicitly by directly predicting community relative abundance profiles at steady state, thus escaping the need for growth curves. On two real-world datasets, we show for the first time generalization to unseen bacteria and different community structures. To investigate the prediction results more deeply, we create a simulation for flexible data generation and analyze effects of bacteria interaction strength, community size, and training data amount.

ICLR Conference 2024 Conference Paper

Multi-View Causal Representation Learning with Partial Observability

Dingling Yao
Danru Xu
Sébastien Lachapelle
Sara Magliacane
Perouz Taslakian
Georg Martius
Julius von Kügelgen
Francesco Locatello

We present a unified framework for studying the identifiability of representations learned from simultaneously observed views, such as different data modalities. We allow a partially observed setting in which each view constitutes a nonlinear mixture of a subset of underlying latent variables, which can be causally related. We prove that the information shared across all subsets of any number of views can be learned up to a smooth bijection using contrastive learning and a single encoder per view. We also provide graphical criteria indicating which latent variables can be identified through a simple set of rules, which we refer to as identifiability algebra. Our general framework and theoretical results unify and extend several previous work on multi-view nonlinear ICA, disentanglement, and causal representation learning. We experimentally validate our claims on numerical, image, and multi-modal data sets. Further, we demonstrate that the performance of prior methods is recovered in different special cases of our setup. Overall, we find that access to multiple partial views offers unique opportunities for identifiable representation learning, enabling the discovery of latent structures from purely observational data.

RLC Conference 2024 Conference Paper

Offline Diversity Maximization under Imitation Constraints

Marin Vlastelica
Jin Cheng
Georg Martius
Pavel Kolev

There has been significant recent progress in the area of unsupervised skill discovery, utilizing various information-theoretic objectives as measures of diversity. Despite these advances, challenges remain: current methods require significant online interaction, fail to leverage vast amounts of available task-agnostic data and typically lack a quantitative measure of skill utility. We address these challenges by proposing a principled offline algorithm for unsupervised skill discovery that, in addition to maximizing diversity, ensures that each learned skill imitates state-only expert demonstrations to a certain degree. Our main analytical contribution is to connect Fenchel duality, reinforcement learning, and unsupervised skill discovery to maximize a mutual information objective subject to KL-divergence state occupancy constraints. Furthermore, we demonstrate the effectiveness of our method on the standard offline benchmark D4RL and on a custom offline dataset collected from a 12-DoF quadruped robot for which the policies trained in simulation transfer well to the real robotic system.

RLJ Journal 2024 Journal Article

Offline Diversity Maximization under Imitation Constraints

Marin Vlastelica
Jin Cheng
Georg Martius
Pavel Kolev

There has been significant recent progress in the area of unsupervised skill discovery, utilizing various information-theoretic objectives as measures of diversity. Despite these advances, challenges remain: current methods require significant online interaction, fail to leverage vast amounts of available task-agnostic data and typically lack a quantitative measure of skill utility. We address these challenges by proposing a principled offline algorithm for unsupervised skill discovery that, in addition to maximizing diversity, ensures that each learned skill imitates state-only expert demonstrations to a certain degree. Our main analytical contribution is to connect Fenchel duality, reinforcement learning, and unsupervised skill discovery to maximize a mutual information objective subject to KL-divergence state occupancy constraints. Furthermore, we demonstrate the effectiveness of our method on the standard offline benchmark D4RL and on a custom offline dataset collected from a 12-DoF quadruped robot for which the policies trained in simulation transfer well to the real robotic system.

ICLR Conference 2024 Conference Paper

The Expressive Leaky Memory Neuron: an Efficient and Expressive Phenomenological Neuron Model Can Solve Long-Horizon Tasks

Aaron Spieler
Nasim Rahaman
Georg Martius
Bernhard Schölkopf
Anna Levina

Biological cortical neurons are remarkably sophisticated computational devices, temporally integrating their vast synaptic input over an intricate dendritic tree, subject to complex, nonlinearly interacting internal biological processes. A recent study proposed to characterize this complexity by fitting accurate surrogate models to replicate the input-output relationship of a detailed biophysical cortical pyramidal neuron model and discovered it needed temporal convolutional networks (TCN) with millions of parameters. Requiring these many parameters, however, could stem from a misalignment between the inductive biases of the TCN and cortical neuron's computations. In light of this, and to explore the computational implications of leaky memory units and nonlinear dendritic processing, we introduce the Expressive Leaky Memory (ELM) neuron model, a biologically inspired phenomenological model of a cortical neuron. Remarkably, by exploiting such slowly decaying memory-like hidden states and two-layered nonlinear integration of synaptic input, our ELM neuron can accurately match the aforementioned input-output relationship with under ten thousand trainable parameters. To further assess the computational ramifications of our neuron design, we evaluate it on various tasks with demanding temporal structures, including the Long Range Arena (LRA) datasets, as well as a novel neuromorphic dataset based on the Spiking Heidelberg Digits dataset (SHD-Adding). Leveraging a larger number of memory units with sufficiently long timescales, and correspondingly sophisticated synaptic integration, the ELM neuron displays substantial long-range processing capabilities, reliably outperforming the classic Transformer or Chrono-LSTM architectures on LRA, and even solving the Pathfinder-X task with over 70\% accuracy (16k context length). These findings raise further questions about the computational sophistication of individual cortical neurons and their role in extracting complex long-range temporal dependencies.

ICLR Conference 2023 Conference Paper

Backpropagation through Combinatorial Algorithms: Identity with Projection Works

Subham Sekhar Sahoo
Anselm Paulus
Marin Vlastelica
Vít Musil
Volodymyr Kuleshov
Georg Martius

Embedding discrete solvers as differentiable layers has given modern deep learning architectures combinatorial expressivity and discrete reasoning capabilities. The derivative of these solvers is zero or undefined, therefore a meaningful replacement is crucial for effective gradient-based learning. Prior works rely on smoothing the solver with input perturbations, relaxing the solver to continuous problems, or interpolating the loss landscape with techniques that typically require additional solver calls, introduce extra hyper-parameters, or compromise performance. We propose a principled approach to exploit the geometry of the discrete solution space to treat the solver as a negative identity on the backward pass and further provide a theoretical justification. Our experiments demonstrate that such a straightforward hyper-parameter-free approach is able to compete with previous more complex methods on numerous experiments such as backpropagation through discrete samplers, deep graph matching, and image retrieval. Furthermore, we substitute the previously proposed problem-specific and label-dependent margin with a generic regularization procedure that prevents cost collapse and increases robustness.

ICLR Conference 2023 Conference Paper

Benchmarking Offline Reinforcement Learning on Real-Robot Hardware

Nico Gürtler
Sebastian Blaes
Pavel Kolev
Felix Widmaier
Manuel Wüthrich
Stefan Bauer
Bernhard Schölkopf
Georg Martius

Learning policies from previously recorded data is a promising direction for real-world robotics tasks, as online learning is often infeasible. Dexterous manipulation in particular remains an open problem in its general form. The combination of offline reinforcement learning with large diverse datasets, however, has the potential to lead to a breakthrough in this challenging domain analogously to the rapid progress made in supervised learning in recent years. To coordinate the efforts of the research community toward tackling this problem, we propose a benchmark including: i) a large collection of data for offline learning from a dexterous manipulation platform on two tasks, obtained with capable RL agents trained in simulation; ii) the option to execute learned policies on a real-world robotic system and a simulation for efficient debugging. We evaluate prominent open-sourced offline reinforcement learning algorithms on the datasets and provide a reproducible experimental setup for offline reinforcement learning on real systems.

EWRL Workshop 2023 Workshop Paper

Colored Noise in PPO: Improved Exploration and Performance Through Correlated Action Sampling

Jakob Hollenstein
Georg Martius
Justus Piater

Proximal Policy Optimization (PPO), a popular on-policy deep reinforcement learning method, employs a stochastic policy for exploration. In this paper, we propose a colored noise-based stochastic policy variant of PPO. Previous research highlighted the importance of temporal correlation in action noise for effective exploration in off-policy reinforcement learning. Building on this, we investigate whether correlated noise can also enhance exploration in on-policy methods like PPO. We discovered that correlated noise for action selection improves learning performance and outperforms the currently popular uncorrelated white noise approach in on-policy methods. Unlike off-policy learning, where pink noise was found to be highly effective, we found that a colored noise, intermediate between white and pink, performed best for on-policy learning in PPO. We examined the impact of varying the amount of data collected for each update by modifying the number of parallel simulation environments for data collection and observed that a larger number of parallel environments benefits from more correlated noise. However, overall, we found four parallel environments to work best. Due to the significant impact and ease of implementation, we recommend switching to correlated noise as the default noise source in PPO.

ICLR Conference 2023 Conference Paper

DEP-RL: Embodied Exploration for Reinforcement Learning in Overactuated and Musculoskeletal Systems

Pierre Schumacher
Daniel F. B. Häufle
Dieter Büchler
Syn Schmitt
Georg Martius

Muscle-actuated organisms are capable of learning an unparalleled diversity of dexterous movements despite their vast amount of muscles. Reinforcement learning (RL) on large musculoskeletal models, however, has not been able to show similar performance. We conjecture that ineffective exploration in large overactuated action spaces is a key problem. This is supported by the finding that common exploration noise strategies are inadequate in synthetic examples of overactuated systems. We identify differential extrinsic plasticity (DEP), a method from the domain of self-organization, as being able to induce state-space covering exploration within seconds of interaction. By integrating DEP into RL, we achieve fast learning of reaching and locomotion in musculoskeletal systems, outperforming current approaches in all considered tasks in sample efficiency and robustness.

EWRL Workshop 2023 Workshop Paper

Diverse Offline Imitation via Fenchel Duality

Marin Vlastelica
Pavel Kolev
Jin Cheng
Georg Martius

There has been significant recent progress in the area of unsupervised skill discovery, with various works proposing mutual information based objectives, as a source of intrinsic motivation. Prior works predominantly focused on designing algorithms that require online access to the environment. In contrast, we develop an offline skill discovery algorithm. Our problem formulation considers the maximization of a mutual information objective constrained by a KL-divergence. More precisely, the constraints ensure that the state occupancy of each skill remains close to the state occupancy of an expert, within the support of an offline dataset with good state-action coverage. Our main contribution is to connect Fenchel-Rockafellar duality, reinforcement learning and unsupervised skill discovery, and to give a simple offline algorithm for learning diverse skills that are aligned with an expert.

ICRA Conference 2023 Conference Paper

Efficient Learning of High Level Plans from Play

Núria Armengol Urpí
Marco Bagatella
Otmar Hilliges
Georg Martius
Stelian Coros

Real-world robotic manipulation tasks remain an elusive challenge, since they involve both fine-grained environment interaction, as well as the ability to plan for long-horizon goals. Although deep reinforcement learning (RL) methods have shown encouraging results when planning end-to-end in high-dimensional environments, they remain fundamentally limited by poor sample efficiency due to inefficient exploration, and by the complexity of credit assignment over long horizons. In this work, we present Efficient Learning of High-Level Plans from Play (ELF-P), a framework for robotic learning that bridges motion planning and deep RL to achieve long-horizon complex manipulation tasks. We leverage task-agnostic play data to learn a discrete behavioral prior over object-centric primitives, modeling their feasibility given the current context. We then design a high-level goal-conditioned policy which (1) uses primitives as building blocks to scaffold complex long-horizon tasks and (2) leverages the behavioral prior to accelerate learning. We demonstrate that ELF-P has significantly better sample efficiency than relevant baselines over multiple realistic manipulation tasks and learns policies that can be easily transferred to physical hardware.

EWRL Workshop 2023 Workshop Paper

Goal-conditioned Offline Planning from Curious Exploration

Marco Bagatella
Georg Martius

Curiosity has established itself as a powerful exploration strategy in deep reinforcement learning. Notably, leveraging expected future novelty as intrinsic motivation has been shown to efficiently generate exploratory trajectories, as well as a robust dynamics model. We consider the challenge of extracting goal-conditioned behavior from the products of such unsupervised exploration techniques, without any additional environment interaction. We find that conventional goal-conditioned reinforcement learning approaches for extracting a value function and policy fall short in this difficult offline setting. By analyzing the geometry of optimal goal-conditioned value functions, we relate this issue to a specific class of estimation artifacts in learned values. In order to mitigate their occurrence, we propose to combine model-based planning over learned value landscapes with a graph-based value aggregation scheme. We show how this combination can correct both local and global artifacts, obtaining significant improvements in zero-shot goal-reaching performance across diverse simulated environments.

NeurIPS Conference 2023 Conference Paper

Goal-conditioned Offline Planning from Curious Exploration

Marco Bagatella
Georg Martius

Curiosity has established itself as a powerful exploration strategy in deep reinforcement learning. Notably, leveraging expected future novelty as intrinsic motivation has been shown to efficiently generate exploratory trajectories, as well as a robust dynamics model. We consider the challenge of extracting goal-conditioned behavior from the products of such unsupervised exploration techniques, without any additional environment interaction. We find that conventional goal-conditioned reinforcement learning approaches for extracting a value function and policy fall short in this difficult offline setting. By analyzing the geometry of optimal goal-conditioned value functions, we relate this issue to a specific class of estimation artifacts in learned values. In order to mitigate their occurrence, we propose to combine model-based planning over learned value landscapes with a graph-based value aggregation scheme. We show how this combination can correct both local and global artifacts, obtaining significant improvements in zero-shot goal-reaching performance across diverse simulated environments.

EWRL Workshop 2023 Workshop Paper

Learning Hierarchical World Models with Adaptive Temporal Abstractions from Discrete Latent Dynamics

Christian Gumbsch
Noor Sajid
Georg Martius
Martin V. Butz

Hierarchical world models have the potential to significantly improve model-based reinforcement learning (MBRL) and planning by enabling reasoning across multiple time scales. Nonetheless, the majority of state-of-the-art MBRL methods still employ flat, non-hierarchical models. The challenge lies in learning suitable hierarchical abstractions. We propose Temporal Hierarchies from Invariant Context Kernels (THICK), an algorithm that learns a world model hierarchy based on discrete latent dynamics. The lower level of the THICK world model selectively updates parts of its latent state sparsely in time, forming invariant contexts. The higher level is trained exclusively to predict situations involving these sparse context state changes. Our experiments demonstrate that THICK learns categorical, interpretable, temporal abstractions on the high level while maintaining precise low-level predictions. Furthermore, we show that the developing hierarchical predictive model can seamlessly enhance the abilities of MBRL or planning methods. We believe that THICK-like, hierarchical world models will be key for developing more sophisticated agents capable of exploring, planning, and reasoning about the future across multiple time scales.

PRL Workshop 2023 Workshop Paper

Mind the Uncertainty: Risk-Aware and Actively Exploring Model-Based Reinforcement Learning

Marin Vlastelica
Sebastian Blaes
Cristina Pinneri
Georg Martius

We introduce a simple but effective method for managing risk in model-based reinforcement learning with trajectory sampling that involves probabilistic safety constraints and balancing of optimism in the face of epistemic uncertainty and pessimism in the face of aleatoric uncertainty of an ensemble of stochastic neural networks. Various experiments indicate that the separation of uncertainties is essential to performing well with data-driven MPC approaches in uncertain and safety-critical control environments.

EWRL Workshop 2023 Workshop Paper

Mind the Uncertainty: Risk-Aware and Actively Exploring Model-Based Reinforcement Learning

Marin Vlastelica
Sebastian Blaes
Cristina Pinneri
Georg Martius

We introduce a simple but effective method for managing risk in model-based reinforcement learning with trajectory sampling that involves probabilistic safety constraints and balancing of optimism in the face of epistemic uncertainty and pessimism in the face of aleatoric uncertainty of an ensemble of stochastic neural networks. Various experiments indicate that the separation of uncertainties is essential to performing well with data-driven MPC approaches in uncertain and safety-critical control environments.

NeurIPS Conference 2023 Conference Paper

Object-Centric Learning for Real-World Videos by Predicting Temporal Feature Similarities

Andrii Zadaianchuk
Maximilian Seitzer
Georg Martius

Unsupervised video-based object-centric learning is a promising avenue to learn structured representations from large, unlabeled video collections, but previous approaches have only managed to scale to real-world datasets in restricted domains. Recently, it was shown that the reconstruction of pre-trained self-supervised features leads to object-centric representations on unconstrained real-world image datasets. Building on this approach, we propose a novel way to use such pre-trained features in the form of a temporal feature similarity loss. This loss encodes semantic and temporal correlations between image patches and is a natural way to introduce a motion bias for object discovery. We demonstrate that this loss leads to state-of-the-art performance on the challenging synthetic MOVi datasets. When used in combination with the feature reconstruction loss, our model is the first object-centric video model that scales to unconstrained video datasets such as YouTube-VIS. https: //martius-lab. github. io/videosaur/

NeurIPS Conference 2023 Conference Paper

Online Learning under Adversarial Nonlinear Constraints

Pavel Kolev
Georg Martius
Michael Muehlebach

In many applications, learning systems are required to process continuous non-stationary data streams. We study this problem in an online learning framework and propose an algorithm that can deal with adversarial time-varying and nonlinear constraints. As we show in our work, the algorithm called Constraint Violation Velocity Projection (CVV-Pro) achieves $\sqrt{T}$ regret and converges to the feasible set at a rate of $1/\sqrt{T}$, despite the fact that the feasible set is slowly time-varying and a priori unknown to the learner. CVV-Pro only relies on local sparse linear approximations of the feasible set and therefore avoids optimizing over the entire set at each iteration, which is in sharp contrast to projected gradients or Frank-Wolfe methods. We also empirically evaluate our algorithm on two-player games, where the players are subjected to a shared constraint.

EWRL Workshop 2023 Workshop Paper

Online Learning under Adversarial Nonlinear Constraints

Pavel Kolev
Georg Martius
Michael Muehlebach

In many applications, learning systems are required to process continuous non-stationary data streams. We study this problem in an online learning framework and propose an algorithm that can deal with adversarial time-varying and nonlinear constraints. As we show in our work, the algorithm called Constraint Violation Velocity Projection (CVV-Pro) achieves $\sqrt{T}$ regret and converges to the feasible set at a rate of $1/\sqrt{T}$, despite the fact that the feasible set is slowly time-varying and a priori unknown to the learner. CVV-Pro only relies on local sparse linear approximations of the feasible set and therefore avoids optimizing over the entire set at each iteration, which is in sharp contrast to projected gradients or Frank-Wolfe methods. We also empirically evaluate our algorithm on two-player games, where the players are subjected to a shared constraint.

ICLR Conference 2023 Conference Paper

Pink Noise Is All You Need: Colored Noise Exploration in Deep Reinforcement Learning

Onno Eberhard
Jakob J. Hollenstein
Cristina Pinneri
Georg Martius

In off-policy deep reinforcement learning with continuous action spaces, exploration is often implemented by injecting action noise into the action selection process. Popular algorithms based on stochastic policies, such as SAC or MPO, inject white noise by sampling actions from uncorrelated Gaussian distributions. In many tasks, however, white noise does not provide sufficient exploration, and temporally correlated noise is used instead. A common choice is Ornstein-Uhlenbeck (OU) noise, which is closely related to Brownian motion (red noise). Both red noise and white noise belong to the broad family of colored noise. In this work, we perform a comprehensive experimental evaluation on MPO and SAC to explore the effectiveness of other colors of noise as action noise. We find that pink noise, which is halfway between white and red noise, significantly outperforms white noise, OU noise, and other alternatives on a wide range of environments. Thus, we recommend it as the default choice for action noise in continuous control.

NeurIPS Conference 2023 Conference Paper

Regularity as Intrinsic Reward for Free Play

Cansu Sancaktar
Justus Piater
Georg Martius

We propose regularity as a novel reward signal for intrinsically-motivated reinforcement learning. Taking inspiration from child development, we postulate that striving for structure and order helps guide exploration towards a subspace of tasks that are not favored by naive uncertainty-based intrinsic rewards. Our generalized formulation of Regularity as Intrinsic Reward (RaIR) allows us to operationalize it within model-based reinforcement learning. In a synthetic environment, we showcase the plethora of structured patterns that can emerge from pursuing this regularity objective. We also demonstrate the strength of our method in a multi-object robotic manipulation environment. We incorporate RaIR into free play and use it to complement the model’s epistemic uncertainty as an intrinsic reward. Doing so, we witness the autonomous construction of towers and other regular structures during free play, which leads to a substantial improvement in zero-shot downstream task performance on assembly tasks.

EWRL Workshop 2023 Workshop Paper

Regularity as Intrinsic Reward for Free Play

Cansu Sancaktar
Justus Piater
Georg Martius

We propose regularity as a novel reward signal for intrinsically-motivated reinforcement learning. Taking inspiration from child development, we postulate that striving for structure and order helps guide exploration towards a subspace of tasks that are not favored by naive uncertainty-based intrinsic rewards. Our generalized formulation of Regularity as Intrinsic Reward (RaIR) allows us to operationalize it within model-based reinforcement learning. In a synthetic environment, we showcase the plethora of structured patterns that can emerge from pursuing this regularity objective. We also demonstrate the strength of our method in a multi-object robotic manipulation environment. We incorporate RaIR into free play and use it to complement the model’s epistemic uncertainty as an intrinsic reward. Doing so, we witness the autonomous construction of towers and other regular structures during free play, which leads to a substantial improvement in zero-shot downstream task performance on assembly tasks.

ICRA Conference 2023 Conference Paper

Versatile Skill Control via Self-supervised Adversarial Imitation of Unlabeled Mixed Motions

Chenhao Li
Sebastian Blaes
Pavel Kolev
Marin Vlastelica
Jonas Frey
Georg Martius

Learning diverse skills is one of the main challenges in robotics. To this end, imitation learning approaches have achieved impressive results. These methods require explicitly labeled datasets or assume consistent skill execution to enable learning and active control of individual behaviors, which limits their applicability. In this work, we propose a cooperative adversarial method for obtaining single versatile policies with controllable skill sets from unlabeled datasets containing diverse state transition patterns by maximizing their discriminability. Moreover, we show that by utilizing unsupervised skill discovery in the generative adversarial imitation learning framework, novel and useful skills emerge with successful task fulfillment. Finally, the obtained versatile policies are tested on an agile quadruped robot called Solo 8 and present faithful replications of diverse skills encoded in the demonstrations.

EWRL Workshop 2022 Workshop Paper

Curious Exploration via Structured World Models Yields Zero-Shot Object Manipulation

Cansu Sancaktar
Sebastian Blaes
Georg Martius

It has been a long-standing dream to design artificial agents that explore their environment efficiently via intrinsic motivation, similar to how children perform curious free play. Despite recent advances in intrinsically motivated reinforcement learning (RL), sample-efficient exploration in object manipulation scenarios remains a significant challenge as most of the relevant information lies in the sparse agent-object and object-object interactions. In this paper, we propose to use structured world models to incorporate relational inductive biases in the control loop to achieve sample-efficient and interaction-rich exploration in compositional multi-object environments. By planning for future novelty inside structured world models, our method generates free-play behavior that starts to interact with objects early on and develops more complex behavior over time. Instead of using models only to compute intrinsic rewards, as commonly done, our method showcases that the self-reinforcing cycle between good models and good exploration also opens up another avenue: zero-shot generalization to downstream tasks via model-based planning. After the entirely intrinsic task-agnostic exploration phase, our method solves challenging downstream tasks such as stacking, flipping, pick & place, and throwing that generalizes to unseen numbers and arrangements of objects without any additional training.1

NeurIPS Conference 2022 Conference Paper

Curious Exploration via Structured World Models Yields Zero-Shot Object Manipulation

Cansu Sancaktar
Sebastian Blaes
Georg Martius

It has been a long-standing dream to design artificial agents that explore their environment efficiently via intrinsic motivation, similar to how children perform curious free play. Despite recent advances in intrinsically motivated reinforcement learning (RL), sample-efficient exploration in object manipulation scenarios remains a significant challenge as most of the relevant information lies in the sparse agent-object and object-object interactions. In this paper, we propose to use structured world models to incorporate relational inductive biases in the control loop to achieve sample-efficient and interaction-rich exploration in compositional multi-object environments. By planning for future novelty inside structured world models, our method generates free-play behavior that starts to interact with objects early on and develops more complex behavior over time. Instead of using models only to compute intrinsic rewards, as commonly done, our method showcases that the self-reinforcing cycle between good models and good exploration also opens up another avenue: zero-shot generalization to downstream tasks via model-based planning. After the entirely intrinsic task-agnostic exploration phase, our method solves challenging downstream tasks such as stacking, flipping, pick & place, and throwing that generalizes to unseen numbers and arrangements of objects without any additional training.

NeurIPS Conference 2022 Conference Paper

Embrace the Gap: VAEs Perform Independent Mechanism Analysis

Patrik Reizinger
Luigi Gresele
Jack Brady
Julius von Kügelgen
Dominik Zietlow
Bernhard Schölkopf
Georg Martius
Wieland Brendel

Variational autoencoders (VAEs) are a popular framework for modeling complex data distributions; they can be efficiently trained via variational inference by maximizing the evidence lower bound (ELBO), at the expense of a gap to the exact (log-)marginal likelihood. While VAEs are commonly used for representation learning, it is unclear why ELBO maximization would yield useful representations, since unregularized maximum likelihood estimation cannot invert the data-generating process. Yet, VAEs often succeed at this task. We seek to elucidate this apparent paradox by studying nonlinear VAEs in the limit of near-deterministic decoders. We first prove that, in this regime, the optimal encoder approximately inverts the decoder---a commonly used but unproven conjecture---which we refer to as self-consistency. Leveraging self-consistency, we show that the ELBO converges to a regularized log-likelihood. This allows VAEs to perform what has recently been termed independent mechanism analysis (IMA): it adds an inductive bias towards decoders with column-orthogonal Jacobians, which helps recovering the true latent factors. The gap between ELBO and log-likelihood is therefore welcome, since it bears unanticipated benefits for nonlinear representation learning. In experiments on synthetic and image data, we show that VAEs uncover the true latent factors when the data generating process satisfies the IMA assumption.

ICLR Conference 2022 Conference Paper

On the Pitfalls of Heteroscedastic Uncertainty Estimation with Probabilistic Neural Networks

Maximilian Seitzer
Arash Tavakoli
Dimitrije Antic
Georg Martius

Capturing aleatoric uncertainty is a critical part of many machine learning systems. In deep learning, a common approach to this end is to train a neural network to estimate the parameters of a heteroscedastic Gaussian distribution by maximizing the logarithm of the likelihood function under the observed data. In this work, we examine this approach and identify potential hazards associated with the use of log-likelihood in conjunction with gradient-based optimizers. First, we present a synthetic example illustrating how this approach can lead to very poor but stable parameter estimates. Second, we identify the culprit to be the log-likelihood loss, along with certain conditions that exacerbate the issue. Third, we present an alternative formulation, termed $\beta$-NLL, in which each data point's contribution to the loss is weighted by the $\beta$-exponentiated variance estimate. We show that using an appropriate $\beta$ largely mitigates the issue in our illustrative example. Fourth, we evaluate this approach on a range of domains and tasks and show that it achieves considerable improvements and performs more robustly concerning hyperparameters, both in predictive RMSE and log-likelihood criteria.

NeurIPS Conference 2021 Conference Paper

Causal Influence Detection for Improving Efficiency in Reinforcement Learning

Maximilian Seitzer
Bernhard Schölkopf
Georg Martius

Many reinforcement learning (RL) environments consist of independent entities that interact sparsely. In such environments, RL agents have only limited influence over other entities in any particular situation. Our idea in this work is that learning can be efficiently guided by knowing when and what the agent can influence with its actions. To achieve this, we introduce a measure of situation-dependent causal influence based on conditional mutual information and show that it can reliably detect states of influence. We then propose several ways to integrate this measure into RL algorithms to improve exploration and off-policy learning. All modified algorithms show strong increases in data efficiency on robotic manipulation tasks.

ICML Conference 2021 Conference Paper

CombOptNet: Fit the Right NP-Hard Problem by Learning Integer Programming Constraints

Anselm Paulus
Michal Rolínek
Vít Musil
Brandon Amos
Georg Martius

Bridging logical and algorithmic reasoning with modern machine learning techniques is a fundamental challenge with potentially transformative impact. On the algorithmic side, many NP-hard problems can be expressed as integer programs, in which the constraints play the role of their ’combinatorial specification’. In this work, we aim to integrate integer programming solvers into neural network architectures as layers capable of learning both the cost terms and the constraints. The resulting end-to-end trainable architectures jointly extract features from raw data and solve a suitable (learned) combinatorial problem with state-of-the-art integer programming solvers. We demonstrate the potential of such layers with an extensive performance analysis on synthetic data and with a demonstration on a competitive computer vision keypoint matching benchmark.

ICML Conference 2021 Conference Paper

Demystifying Inductive Biases for (Beta-)VAE Based Architectures

Dominik Zietlow
Michal Rolínek
Georg Martius

The performance of Beta-Variational-Autoencoders and their variants on learning semantically meaningful, disentangled representations is unparalleled. On the other hand, there are theoretical arguments suggesting the impossibility of unsupervised disentanglement. In this work, we shed light on the inductive bias responsible for the success of VAE-based architectures. We show that in classical datasets the structure of variance, induced by the generating factors, is conveniently aligned with the latent directions fostered by the VAE objective. This builds the pivotal bias on which the disentangling abilities of VAEs rely. By small, elaborate perturbations of existing datasets, we hide the convenient correlation structure that is easily exploited by a variety of architectures. To demonstrate this, we construct modified versions of standard datasets in which (i) the generative factors are perfectly preserved; (ii) each image undergoes a mild transformation causing a small change of variance; (iii) the leading VAE-based disentanglement architectures fail to produce disentangled representations whilst the performance of a non-variational method remains unchanged.

ICLR Conference 2021 Conference Paper

Extracting Strong Policies for Robotics Tasks from Zero-Order Trajectory Optimizers

Cristina Pinneri
Shambhuraj Sawant
Sebastian Blaes
Georg Martius

Solving high-dimensional, continuous robotic tasks is a challenging optimization problem. Model-based methods that rely on zero-order optimizers like the cross-entropy method (CEM) have so far shown strong performance and are considered state-of-the-art in the model-based reinforcement learning community. However, this success comes at the cost of high computational complexity, being therefore not suitable for real-time control. In this paper, we propose a technique to jointly optimize the trajectory and distill a policy, which is essential for fast execution in real robotic systems. Our method builds upon standard approaches, like guidance cost and dataset aggregation, and introduces a novel adaptive factor which prevents the optimizer from collapsing to the learner's behavior at the beginning of the training. The extracted policies reach unprecedented performance on challenging tasks as making a humanoid stand up and opening a door without reward shaping

NeurIPS Conference 2021 Conference Paper

Hierarchical Reinforcement Learning with Timed Subgoals

Nico Gürtler
Dieter Büchler
Georg Martius

Hierarchical reinforcement learning (HRL) holds great potential for sample-efficient learning on challenging long-horizon tasks. In particular, letting a higher level assign subgoals to a lower level has been shown to enable fast learning on difficult problems. However, such subgoal-based methods have been designed with static reinforcement learning environments in mind and consequently struggle with dynamic elements beyond the immediate control of the agent even though they are ubiquitous in real-world problems. In this paper, we introduce Hierarchical reinforcement learning with Timed Subgoals (HiTS), an HRL algorithm that enables the agent to adapt its timing to a dynamic environment by not only specifying what goal state is to be reached but also when. We discuss how communicating with a lower level in terms of such timed subgoals results in a more stable learning problem for the higher level. Our experiments on a range of standard benchmarks and three new challenging dynamic reinforcement learning environments show that our method is capable of sample-efficient learning where an existing state-of-the-art subgoal-based HRL method fails to learn stable solutions.

ICML Conference 2021 Conference Paper

Neuro-algorithmic Policies Enable Fast Combinatorial Generalization

Marin Vlastelica
Michal Rolínek
Georg Martius

Although model-based and model-free approaches to learning the control of systems have achieved impressive results on standard benchmarks, generalization to task variations is still lacking. Recent results suggest that generalization for standard architectures improves only after obtaining exhaustive amounts of data. We give evidence that generalization capabilities are in many cases bottlenecked by the inability to generalize on the combinatorial aspects of the problem. We show that, for a certain subclass of the MDP framework, this can be alleviated by a neuro-algorithmic policy architecture that embeds a time-dependent shortest path solver in a deep neural network. Trained end-to-end via blackbox-differentiation, this method leads to considerable improvement in generalization capabilities in the low-data regime.

NeurIPS Conference 2021 Conference Paper

Planning from Pixels in Environments with Combinatorially Hard Search Spaces

Marco Bagatella
Miroslav Olšák
Michal Rolínek
Georg Martius

The ability to form complex plans based on raw visual input is a litmus test for current capabilities of artificial intelligence, as it requires a seamless combination of visual processing and abstract algorithmic execution, two traditionally separate areas of computer science. A recent surge of interest in this field brought advances that yield good performance in tasks ranging from arcade games to continuous control; these methods however do not come without significant issues, such as limited generalization capabilities and difficulties when dealing with combinatorially hard planning instances. Our contribution is two-fold: (i) we present a method that learns to represent its environment as a latent graph and leverages state reidentification to reduce the complexity of finding a good policy from exponential to linear (ii) we introduce a set of lightweight environments with an underlying discrete combinatorial structure in which planning is challenging even for humans. Moreover, we show that our methods achieves strong empirical generalization to variations in the environment, even across highly disadvantaged regimes, such as “one-shot” planning, or in an offline RL paradigm which only provides low-quality trajectories.

ICLR Conference 2021 Conference Paper

Self-supervised Visual Reinforcement Learning with Object-centric Representations

Andrii Zadaianchuk
Maximilian Seitzer
Georg Martius

Autonomous agents need large repertoires of skills to act reasonably on new tasks that they have not seen before. However, acquiring these skills using only a stream of high-dimensional, unstructured, and unlabeled observations is a tricky challenge for any autonomous agent. Previous methods have used variational autoencoders to encode a scene into a low-dimensional vector that can be used as a goal for an agent to discover new skills. Nevertheless, in compositional/multi-object environments it is difficult to disentangle all the factors of variation into such a fixed-length representation of the whole scene. We propose to use object-centric representations as a modular and structured observation space, which is learned with a compositional generative world model. We show that the structure in the representations in combination with goal-conditioned attention policies helps the autonomous agent to discover and learn useful skills. These skills can be further combined to address compositional tasks like the manipulation of several different objects.

NeurIPS Conference 2021 Conference Paper

Sparsely Changing Latent States for Prediction and Planning in Partially Observable Domains

Christian Gumbsch
Martin V. Butz
Georg Martius

A common approach to prediction and planning in partially observable domains is to use recurrent neural networks (RNNs), which ideally develop and maintain a latent memory about hidden, task-relevant factors. We hypothesize that many of these hidden factors in the physical world are constant over time, changing only sparsely. To study this hypothesis, we propose Gated $L_0$ Regularized Dynamics (GateL0RD), a novel recurrent architecture that incorporates the inductive bias to maintain stable, sparsely changing latent states. The bias is implemented by means of a novel internal gating function and a penalty on the $L_0$ norm of latent state changes. We demonstrate that GateL0RD can compete with or outperform state-of-the-art RNNs in a variety of partially observable prediction and control tasks. GateL0RD tends to encode the underlying generative factors of the environment, ignores spurious temporal dependencies, and generalizes better, improving sampling efficiency and overall performance in model-based planning and reinforcement learning tasks. Moreover, we show that the developing latent states can be easily interpreted, which is a step towards better explainability in RNNs.

ICRA Conference 2020 Conference Paper

A Real-Robot Dataset for Assessing Transferability of Learned Dynamics Models

Diego Agudelo-España
Andrii Zadaianchuk
Philippe Wenk
Aditya Garg
Joel Akpo
Felix Grimminger
Julian Viereck
Maximilien Naveau

In the context of model-based reinforcement learning and control, a large number of methods for learning system dynamics have been proposed in recent years. The purpose of these learned models is to synthesize new control policies. An important open question is how robust current dynamics-learning methods are to shifts in the data distribution due to changes in the control policy. We present a real-robot dataset which allows to systematically investigate this question. This dataset contains trajectories of a 3 degrees-of-freedom (DOF) robot being controlled by a diverse set of policies. For comparison, we also provide a simulated version of the dataset. Finally, we benchmark a few widely-used dynamics-learning methods using the proposed dataset. Our results show that the iid test error of a learned model is not necessarily a good indicator of its accuracy under control policies different from the one which generated the training data. This suggests that it may be important to evaluate dynamics-learning methods in terms of their transfer performance, rather than only their iid error.

ICLR Conference 2020 Conference Paper

Differentiation of Blackbox Combinatorial Solvers

Marin Vlastelica
Anselm Paulus
Vít Musil
Georg Martius
Michal Rolínek

Achieving fusion of deep learning with combinatorial algorithms promises transformative changes to artificial intelligence. One possible approach is to introduce combinatorial building blocks into neural networks. Such end-to-end architectures have the potential to tackle combinatorial problems on raw input data such as ensuring global consistency in multi-object tracking or route planning on maps in robotics. In this work, we present a method that implements an efficient backward pass through blackbox implementations of combinatorial solvers with linear objective functions. We provide both theoretical and experimental backing. In particular, we incorporate the Gurobi MIP solver, Blossom V algorithm, and Dijkstra's algorithm into architectures that extract suitable features from raw inputs for the traveling salesman problem, the min-cost perfect matching problem and the shortest path problem.

NeurIPS Conference 2019 Conference Paper

Control What You Can: Intrinsically Motivated Task-Planning Agent

Sebastian Blaes
Marin Vlastelica Pogančić
Jiajie Zhu
Georg Martius

We present a novel intrinsically motivated agent that learns how to control the environment in a sample efficient manner, that is with as few environment interactions as possible, by optimizing learning progress. It learns what can be controlled, how to allocate time and attention as well as the relations between objects using surprise-based motivation. The effectiveness of our method is demonstrated in a synthetic and robotic manipulation environment yielding considerably improved performance and smaller sample complexity compared to an intrinsically motivated, non-hierarchical and state-of-the-art hierarchical baseline. In a nutshell, our work combines several task-level planning agent structures (backtracking search on task-graph, probabilistic road-maps, allocation of search efforts) with intrinsic motivation to achieve learning from scratch.

NeurIPS Conference 2018 Conference Paper

L4: Practical loss-based stepsize adaptation for deep learning

Michal Rolinek
Georg Martius

We propose a stepsize adaptation scheme for stochastic gradient descent. It operates directly with the loss function and rescales the gradient in order to make fixed predicted progress on the loss. We demonstrate its capabilities by conclusively improving the performance of Adam and Momentum optimizers. The enhanced optimizers with default hyperparameters consistently outperform their constant stepsize counterparts, even the best ones, without a measurable increase in computational cost. The performance is validated on multiple architectures including dense nets, CNNs, ResNets, and the recurrent Differential Neural Computer on classical datasets MNIST, fashion MNIST, CIFAR10 and others.

ICML Conference 2018 Conference Paper

Learning Equations for Extrapolation and Control

Subham Sekhar Sahoo
Christoph H. Lampert
Georg Martius

We present an approach to identify concise equations from data using a shallow neural network approach. In contrast to ordinary black-box regression, this approach allows understanding functional relations and generalizing them from observed data to unseen parts of the parameter space. We show how to extend the class of learnable equations for a recently proposed equation learning network to include divisions, and we improve the learning and model selection strategy to be useful for challenging real-world data. For systems governed by analytical expressions, our method can in many cases identify the true underlying equation and extrapolate to unseen domains. We demonstrate its effectiveness by experiments on a cart-pendulum system, where only 2 random rollouts are required to learn the forward dynamics and successfully achieve the swing-up task.

IROS Conference 2016 Conference Paper

Compliant control for soft robots: Emergent behavior of a tendon driven anthropomorphic arm

Georg Martius
Rafael Hostettler
Alois C. Knoll
Ralf Der

With the accelerated development of robot technologies, optimal control becomes one of the central themes of research. In traditional approaches, the controller, by its internal functionality, finds appropriate actions on the basis of the history of sensor values, guided by the goals, intentions, objectives, learning schemes, and so forth. While very successful with classical robots, these methods run into severe difficulties when applied to soft robots, a new field of robotics with large interest for human-robot interaction. We claim that a novel controller paradigm opens new perspective for this field. This paper applies a recently developed neuro controller with differential extrinsic synaptic plasticity to a muscle-tendon driven arm-shoulder system from the Myorobotics toolkit. In the experiments, we observe a vast variety of self-organized behavior patterns: when left alone, the arm realizes pseudo-random sequences of different poses. By applying physical forces, the system can be entrained into definite motion patterns like wiping a table. Most interestingly, after attaching an object, the controller gets in a functional resonance with the object's internal dynamics, starting to shake spontaneously bottles half-filled with water or sensitively driving an attached pendulum into a circular mode. When attached to the crank of a wheel the neural system independently develops to rotate it. In this way, the robot discovers affordances of objects its body is interacting with.

IROS Conference 2008 Conference Paper

Structure from behavior in autonomous agents

Georg Martius
Katja Fiedler
J. Michael Herrmann

We describe a learning algorithm that generates behaviors by self-organization of sensorimotor loops in an autonomous robot. The behavior of the robot is analyzed by a multi-expert architecture, where a number of controllers compete for the data from the physical robot. Each expert stabilizes the representation of the acquired sensorimotor mapping in dependence of the achieved prediction error and forms eventually a behavioral primitive. The experts provide a discrete representation of the behavioral manifold of the robot and are suited to form building blocks for complex behaviors.