Arrow Research search

Author name cluster

Bilal Piot

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.

30 papers
2 author rows

Possible papers

30

ICLR Conference 2025 Conference Paper

Building Math Agents with Multi-Turn Iterative Preference Learning

  • Wei Xiong 0015
  • Chengshuai Shi
  • Jiaming Shen
  • Aviv Rosenberg 0002
  • Zhen Qin 0001
  • Daniele Calandriello
  • Misha Khalman
  • Rishabh Joshi

Recent studies have shown that large language models' (LLMs) mathematical problem-solving capabilities can be enhanced by integrating external tools, such as code interpreters, and employing multi-turn Chain-of-Thought (CoT) reasoning. While current methods focus on synthetic data generation and Supervised Fine-Tuning (SFT), this paper studies the complementary direct preference learning approach to further improve model performance. However, existing direct preference learning algorithms are originally designed for the single-turn chat task, and do not fully address the complexities of multi-turn reasoning and external tool integration required for tool-integrated mathematical reasoning tasks. To fill in this gap, we introduce a multi-turn direct preference learning framework, tailored for this context, that leverages feedback from code interpreters and optimizes trajectory-level preferences. This framework includes multi-turn DPO and multi-turn KTO as specific implementations. The effectiveness of our framework is validated through training of various language models using an augmented prompt set from the GSM8K and MATH datasets. Our results demonstrate substantial improvements: a supervised fine-tuned Gemma-1.1-it-7B model's performance increased from 77.5% to 83.9% on GSM8K and from 46.1% to 51.2% on MATH. Similarly, a Gemma-2-it-9B model improved from 84.1% to 86.3% on GSM8K and from 51.0% to 54.5% on MATH.

Details

ICLR Conference 2025 Conference Paper

Learning from negative feedback, or positive feedback or both

  • Abbas Abdolmaleki
  • Bilal Piot
  • Bobak Shahriari
  • Jost Tobias Springenberg
  • Tim Hertweck
  • Michael Bloesch
  • Rishabh Joshi
  • Thomas Lampe

Existing preference optimization methods often assume scenarios where paired preference feedback (preferred/positive vs. dis-preferred/negative examples) is available. This requirement limits their applicability in scenarios where only unpaired feedback—for example, either positive or negative— is available. To address this, we introduce a novel approach that decouples learning from positive and negative feedback. This decoupling enables control over the influence of each feedback type and, importantly, allows learning even when only one feedback type is present. A key contribution is demonstrating stable learning from negative feedback alone, a capability not well-addressed by current methods. Our approach builds upon the probabilistic framework introduced in (Dayan and Hinton, 1997), which uses expectation-maximization (EM) to directly optimize the probability of positive outcomes (as opposed to classic expected reward maximization). We address a key limitation in current EM-based methods: they solely maximize the likelihood of positive examples, while neglecting negative ones. We show how to extend EM algorithms to explicitly incorporate negative examples, leading to a theoretically grounded algorithm that offers an intuitive and versatile way to learn from both positive and negative feedback. We evaluate our approach for training language models based on human feedback as well as training policies for sequential decision-making problems, where learned value functions are available.

Details

ICLR Conference 2025 Conference Paper

RRM: Robust Reward Model Training Mitigates Reward Hacking

  • Tianqi Liu 0002
  • Wei Xiong 0015
  • Jie Ren 0006
  • Lichang Chen
  • Junru Wu
  • Rishabh Joshi
  • Yang Gao
  • Jiaming Shen

Reward models (RMs) play a pivotal role in aligning large language models (LLMs) with human preferences. However, traditional RM training, which relies on response pairs tied to specific prompts, struggles to disentangle prompt-driven preferences from prompt-independent artifacts, such as response length and format. In this work, we expose a fundamental limitation of current RM training methods, where RMs fail to effectively distinguish between contextual signals and irrelevant artifacts when determining preferences. To address this, we introduce a causal framework that learns preferences independent of these artifacts and propose a novel data augmentation technique designed to eliminate them. Extensive experiments show that our approach successfully filters out undesirable artifacts, yielding a more robust reward model (RRM). Our RRM improves the performance of a pairwise reward model trained on Gemma-2-9b-it, on Reward-Bench, increasing accuracy from 80.61% to 84.15%. Additionally, we train two DPO policies using both the RM and RRM, demonstrating that the RRM significantly enhances DPO-aligned policies, improving MT-Bench scores from 7.27 to 8.31 and length-controlled win-rates in AlpacaEval-2 from 33.46% to 52.49%.

Details

ICML Conference 2024 Conference Paper

Generalized Preference Optimization: A Unified Approach to Offline Alignment

  • Yunhao Tang
  • Daniel Guo 0001
  • Zeyu Zheng
  • Daniele Calandriello
  • Rémi Munos
  • Mark Rowland 0001
  • Pierre Harvey Richemond
  • Michal Valko

Offline preference optimization allows fine-tuning large models directly from offline data, and has proved effective in recent alignment practices. We propose generalized preference optimization (GPO), a family of offline losses parameterized by a general class of convex functions. GPO enables a unified view over preference optimization, encompassing existing algorithms such as DPO, IPO and SLiC as special cases, while naturally introducing new variants. The GPO framework also sheds light on how offline algorithms enforce regularization, through the design of the convex function that defines the loss. Our analysis and experiments reveal the connections and subtle differences between the offline regularization and the KL divergence regularization intended by the canonical RLHF formulation. In a controlled setting akin to Gao et al 2023, we also show that different GPO variants achieve similar trade-offs between regularization and performance, though the optimal values of hyper-parameter might differ as predicted by theory. In all, our results present new algorithmic toolkits and empirical insights to alignment practitioners.

Details

ICML Conference 2024 Conference Paper

Human Alignment of Large Language Models through Online Preference Optimisation

  • Daniele Calandriello
  • Daniel Guo 0001
  • Rémi Munos
  • Mark Rowland 0001
  • Yunhao Tang
  • Bernardo Ávila Pires
  • Pierre Harvey Richemond
  • Charline Le Lan

Ensuring alignment of language model’s outputs with human preferences is critical to guarantee a useful, safe, and pleasant user experience. Thus, human alignment has been extensively studied recently and several methods such as Reinforcement Learning from Human Feedback (RLHF), Direct Policy Optimisation (DPO) and Sequence Likelihood Calibration (SLiC) have emerged. In this paper, our contribution is two-fold. First, we show the equivalence between two recent alignment methods, namely Identity Policy Optimisation (IPO) and Nash Mirror Descent (Nash-MD). Second, we introduce a generalisation of IPO, named IPO-MD, that leverages the regularised sampling approach proposed by Nash-MD. This equivalence may seem surprising at first sight, since IPO is an offline method whereas Nash-MD is an online method using a preference model. However, this equivalence can be proven when we consider the online version of IPO, that is when both generations are sampled by the online policy and annotated by a trained preference model. Optimising the IPO loss with such a stream of data becomes then equivalent to finding the Nash equilibrium of the preference model through self-play. Building on this equivalence, we introduce the IPO-MD algorithm that generates data with a mixture policy (between the online and reference policy) similarly as the general Nash-MD algorithm. We compare online-IPO and IPO-MD to different online versions of existing losses on preference data such as DPO and SLiC on a summarisation task.

Details

NeurIPS Conference 2024 Conference Paper

Multi-turn Reinforcement Learning with Preference Human Feedback

  • Lior Shani
  • Aviv Rosenberg
  • Asaf Cassel
  • Oran Lang
  • Daniele Calandriello
  • Avital Zipori
  • Hila Noga
  • Orgad Keller

Reinforcement Learning from Human Feedback (RLHF) has become the standard approach for aligning Large Language Models (LLMs) with human preferences, allowing LLMs to demonstrate remarkable abilities in various tasks. Existing methods work by emulating the human preference at the single decision (turn) level, limiting their capabilities in settings that require planning or multi-turn interactions to achieve a long-term goal. In this paper, we address this issue by developing novel methods for Reinforcement Learning (RL) from preference feedback between two full multi-turn conversations. In the tabular setting, we present a novel mirror-descent-based policy optimization algorithm for the general multi-turn preference-based RL problem, and prove its convergence to Nash equilibrium. To evaluate performance, we create a new environment, Education Dialogue, where a teacher agent guides a student in learning a random topic, and show that a deep RL variant of our algorithm outperforms RLHF baselines. Finally, we show that in an environment with explicit rewards, our algorithm recovers the same performance as a reward-based RL baseline, despite relying solely on a weaker preference signal.

PDF Details DOI

ICML Conference 2024 Conference Paper

Nash Learning from Human Feedback

  • Rémi Munos
  • Michal Valko
  • Daniele Calandriello
  • Mohammad Gheshlaghi Azar
  • Mark Rowland 0001
  • Daniel Guo 0001
  • Yunhao Tang
  • Matthieu Geist

Reinforcement learning from human feedback (RLHF) has emerged as the main paradigm for aligning large language models (LLMs) with human preferences. Traditionally, RLHF involves the initial step of learning a reward model from pairwise human feedback, i. e. , expressed as preferences between pairs of text generations. Subsequently, the LLM’s policy is fine-tuned to maximize the reward through a reinforcement learning algorithm. In this study, we introduce an alternative pipeline for the fine-tuning of LLMs using pairwise human feedback. Our approach entails the initial learning of a pairwise preference model, which is conditioned on two inputs (instead of a single input in the case of a reward model) given a prompt, followed by the pursuit of a policy that consistently generates responses preferred over those generated by any competing policy, thus defining the Nash equilibrium of this preference model. We term this approach Nash learning from human feedback (NLHF). In the context of a tabular policy representation, we present a novel algorithmic solution, Nash-MD, founded on the principles of mirror descent. This algorithm produces a sequence of policies, with the last iteration converging to the regularized Nash equilibrium. Additionally, we explore parametric representations of policies and introduce gradient descent algorithms for deep-learning architectures. We illustrate the effectiveness of our approach by presenting experimental results on a text summarization task. We believe NLHF offers a compelling avenue for fine-tuning LLMs and enhancing the alignment of LLMs with human preferences.

Details

ICLR Conference 2024 Conference Paper

Unlocking the Power of Representations in Long-term Novelty-based Exploration

  • Alaa Saade
  • Steven Kapturowski
  • Daniele Calandriello
  • Charles Blundell
  • Pablo Sprechmann
  • Leopoldo Sarra
  • Oliver Groth
  • Michal Valko

We introduce Robust Exploration via Clustering-based Online Density Estimation (RECODE), a non-parametric method for novelty-based exploration that estimates visitation counts for clusters of states based on their similarity in a chosen embedding space. By adapting classical clustering to the nonstationary setting of Deep RL, RECODE can efficiently track state visitation counts over thousands of episodes. We further propose a novel generalization of the inverse dynamics loss, which leverages masked transformer architectures for multi-step prediction; which in conjunction with \DETOCS achieves a new state-of-the-art in a suite of challenging 3D-exploration tasks in DM-Hard-8. RECODE also sets new state-of-the-art in hard exploration Atari games, and is the first agent to reach the end screen in "Pitfall!"

Details

ICML Conference 2023 Conference Paper

The Edge of Orthogonality: A Simple View of What Makes BYOL Tick

  • Pierre Harvey Richemond
  • Allison C. Tam
  • Yunhao Tang
  • Florian Strub
  • Bilal Piot
  • Felix Hill

Self-predictive unsupervised learning methods such as BYOL or SimSIAM have shown impressive results, and counter-intuitively, do not collapse to trivial representations. In this work, we aim at exploring the simplest possible mathematical arguments towards explaining the underlying mechanisms behind self-predictive unsupervised learning. We start with the observation that those methods crucially rely on the presence of a predictor network (and stop-gradient). With simple linear algebra, we show that when using a linear predictor, the optimal predictor is close to an orthogonal projection, and propose a general framework based on orthonormalization that enables to interpret and give intuition on why BYOL works. In addition, this framework demonstrates the crucial role of the exponential moving average and stop-gradient operator in BYOL as an efficient orthonormalization mechanism. We use these insights to propose four new closed-form predictor variants of BYOL to support our analysis. Our closed-form predictors outperform standard linear trainable predictor BYOL at 100 and 300 epochs (top-1 linear accuracy on ImageNet).

Details

ICML Conference 2023 Conference Paper

Understanding Self-Predictive Learning for Reinforcement Learning

  • Yunhao Tang
  • Daniel Guo 0001
  • Pierre Harvey Richemond
  • Bernardo Ávila Pires
  • Yash Chandak
  • Rémi Munos
  • Mark Rowland 0001
  • Mohammad Gheshlaghi Azar

We study the learning dynamics of self-predictive learning for reinforcement learning, a family of algorithms that learn representations by minimizing the prediction error of their own future latent representations. Despite its recent empirical success, such algorithms have an apparent defect: trivial representations (such as constants) minimize the prediction error, yet it is obviously undesirable to converge to such solutions. Our central insight is that careful designs of the optimization dynamics are critical to learning meaningful representations. We identify that a faster paced optimization of the predictor and semi-gradient updates on the representation, are crucial to preventing the representation collapse. Then in an idealized setup, we show self-predictive learning dynamics carries out spectral decomposition on the state transition matrix, effectively capturing information of the transition dynamics. Building on the theoretical insights, we propose bidirectional self-predictive learning, a novel self-predictive algorithm that learns two representations simultaneously. We examine the robustness of our theoretical insights with a number of small-scale experiments and showcase the promise of the novel representation learning algorithm with large-scale experiments.

Details

NeurIPS Conference 2022 Conference Paper

BYOL-Explore: Exploration by Bootstrapped Prediction

  • Zhaohan Guo
  • Shantanu Thakoor
  • Miruna Pislar
  • Bernardo Avila Pires
  • Florent Altché
  • Corentin Tallec
  • Alaa Saade
  • Daniele Calandriello

We present BYOL-Explore, a conceptually simple yet general approach for curiosity-driven exploration in visually complex environments. BYOL-Explore learns the world representation, the world dynamics and the exploration policy all-together by optimizing a single prediction loss in the latent space with no additional auxiliary objective. We show that BYOL-Explore is effective in DM-HARD-8, a challenging partially-observable continuous-action hard-exploration benchmark with visually rich 3-D environment. On this benchmark, we solve the majority of the tasks purely through augmenting the extrinsic reward with BYOL-Explore intrinsic reward, whereas prior work could only get off the ground with human demonstrations. As further evidence of the generality of BYOL-Explore, we show that it achieves superhuman performance on the ten hardest exploration games in Atari while having a much simpler design than other competitive agents.

PDF Details

ICLR Conference 2022 Conference Paper

Emergent Communication at Scale

  • Rahma Chaabouni 0001
  • Florian Strub
  • Florent Altché
  • Eugene Tarassov
  • Corentin Tallec
  • Elnaz Davoodi
  • Kory Wallace Mathewson
  • Olivier Tieleman

Emergent communication aims for a better understanding of human language evolution and building more efficient representations. We posit that reaching these goals will require scaling up, in contrast to a significant amount of literature that focuses on setting up small-scale problems to tease out desired properties of the emergent languages. We focus on three independent aspects to scale up, namely the dataset, task complexity, and population size. We provide a first set of results for large populations solving complex tasks on realistic large-scale datasets, as well as an easy-to-use codebase to enable further experimentation. In more complex tasks and datasets, we find that RL training can become unstable, but responds well to established stabilization techniques. We also identify the need for a different metric than topographic similarity, which does not correlate with the generalization performances when working with natural images. In this context, we probe ease-of-learnability and transfer methods to assess emergent languages. Finally, we observe that larger populations do not induce robust emergent protocols with high generalization performance, leading us to explore different ways to leverage population, through voting and imitation learning.

Details

ICML Conference 2020 Conference Paper

Agent57: Outperforming the Atari Human Benchmark

  • Adrià Puigdomènech Badia
  • Bilal Piot
  • Steven Kapturowski
  • Pablo Sprechmann
  • Alex Vitvitskyi
  • Daniel Guo 0001
  • Charles Blundell

Atari games have been a long-standing benchmark in the reinforcement learning (RL) community for the past decade. This benchmark was proposed to test general competency of RL algorithms. Previous work has achieved good average performance by doing outstandingly well on many games of the set, but very poorly in several of the most challenging games. We propose Agent57, the first deep RL agent that outperforms the standard human benchmark on all 57 Atari games. To achieve this result, we train a neural network which parameterizes a family of policies ranging from very exploratory to purely exploitative. We propose an adaptive mechanism to choose which policy to prioritize throughout the training process. Additionally, we utilize a novel parameterization of the architecture that allows for more consistent and stable learning.

Details

ICML Conference 2020 Conference Paper

Bootstrap Latent-Predictive Representations for Multitask Reinforcement Learning

  • Daniel Guo 0001
  • Bernardo Ávila Pires
  • Bilal Piot
  • Jean-Bastien Grill
  • Florent Altché
  • Rémi Munos
  • Mohammad Gheshlaghi Azar

Learning a good representation is an essential component for deep reinforcement learning (RL). Representation learning is especially important in multitask and partially observable settings where building a representation of the unknown environment is crucial to solve the tasks. Here we introduce Predictions of Bootstrapped Latents (PBL), a simple and flexible self-supervised representation learning algorithm for multitask deep RL. PBL builds on multistep predictive representations of future observations, and focuses on capturing structured information about environment dynamics. Specifically, PBL trains its representation by predicting latent embeddings of future observations. These latent embeddings are themselves trained to be predictive of the aforementioned representations. These predictions form a bootstrapping effect, allowing the agent to learn more about the key aspects of the environment dynamics. In addition, by defining prediction tasks completely in latent space, PBL provides the flexibility of using multimodal observations involving pixel images, language instructions, rewards and more. We show in our experiments that PBL delivers across-the-board improved performance over state of the art deep RL agents in the DMLab-30 multitask setting.

Details

NeurIPS Conference 2020 Conference Paper

Bootstrap Your Own Latent - A New Approach to Self-Supervised Learning

  • Jean-Bastien Grill
  • Florian Strub
  • Florent Altché
  • Corentin Tallec
  • Pierre Richemond
  • Elena Buchatskaya
  • Carl Doersch
  • Bernardo Avila Pires

We introduce Bootstrap Your Own Latent (BYOL), a new approach to self-supervised image representation learning. BYOL relies on two neural networks, referred to as online and target networks, that interact and learn from each other. From an augmented view of an image, we train the online network to predict the target network representation of the same image under a different augmented view. At the same time, we update the target network with a slow-moving average of the online network. While state-of-the art methods intrinsically rely on negative pairs, BYOL achieves a new state of the art without them. BYOL reaches 74. 3% top-1 classification accuracy on ImageNet using the standard linear evaluation protocol with a standard ResNet-50 architecture and 79. 6% with a larger ResNet. We also show that BYOL performs on par or better than the current state of the art on both transfer and semi-supervised benchmarks.

PDF Details

ICLR Conference 2020 Conference Paper

Never Give Up: Learning Directed Exploration Strategies

  • Adrià Puigdomènech Badia
  • Pablo Sprechmann
  • Alex Vitvitskyi
  • Daniel Guo 0001
  • Bilal Piot
  • Steven Kapturowski
  • Olivier Tieleman
  • Martín Arjovsky

We propose a reinforcement learning agent to solve hard exploration games by learning a range of directed exploratory policies. We construct an episodic memory-based intrinsic reward using k-nearest neighbors over the agent's recent experience to train the directed exploratory policies, thereby encouraging the agent to repeatedly revisit all states in its environment. A self-supervised inverse dynamics model is used to train the embeddings of the nearest neighbour lookup, biasing the novelty signal towards what the agent can control. We employ the framework of Universal Value Function Approximators to simultaneously learn many directed exploration policies with the same neural network, with different trade-offs between exploration and exploitation. By using the same neural network for different degrees of exploration/exploitation, transfer is demonstrated from predominantly exploratory policies yielding effective exploitative policies. The proposed method can be incorporated to run with modern distributed RL agents that collect large amounts of experience from many actors running in parallel on separate environment instances. Our method doubles the performance of the base agent in all hard exploration in the Atari-57 suite while maintaining a very high score across the remaining games, obtaining a median human normalised score of 1344.0%. Notably, the proposed method is the first algorithm to achieve non-zero rewards (with a mean score of 8,400) in the game of Pitfall! without using demonstrations or hand-crafted features.

Details

NeurIPS Conference 2019 Conference Paper

Hindsight Credit Assignment

  • Anna Harutyunyan
  • Will Dabney
  • Thomas Mesnard
  • Mohammad Gheshlaghi Azar
  • Bilal Piot
  • Nicolas Heess
  • Hado van Hasselt
  • Gregory Wayne

We consider the problem of efficient credit assignment in reinforcement learning. In order to efficiently and meaningfully utilize new data, we propose to explicitly assign credit to past decisions based on the likelihood of them having led to the observed outcome. This approach uses new information in hindsight, rather than employing foresight. Somewhat surprisingly, we show that value functions can be rewritten through this lens, yielding a new family of algorithms. We study the properties of these algorithms, and empirically show that they successfully address important credit assignment challenges, through a set of illustrative tasks.

PDF Details

AAMAS Conference 2019 Conference Paper

Observational Learning by Reinforcement Learning

  • Diana Borsa
  • Nicolas Heess
  • Bilal Piot
  • Siqi Liu
  • Leonard Hasenclever
  • Remi Munos
  • Olivier Pietquin

Observational learning is a type of learning that occurs as a function of observing, retaining and possibly imitating the behaviour of another agent. It is a core mechanism appearing in various instances of social learning and has been found to be employed in several intelligent species, including humans. In this paper, we investigate to what extent the explicit modelling of other agents is necessary to achieve observational learning through machine learning. Especially, we argue that observational learning can emerge from pure Reinforcement Learning (RL), potentially coupled with memory. Through simple scenarios, we demonstrate that an RL agent can leverage the information provided by the observations of an other agent performing a task in a shared environment. The other agent is only observed through the e�ect of its actions on the environment and never explicitly modeled. Two key aspects are borrowed from observational learning: i) the observer behaviour needs to change as a result of viewing a ’teacher’ (another agent) and ii) the observer needs to be motivated somehow to engage in making use of the other agent’s behaviour. The later is naturally modeled by RL, by correlating the learning agent’s reward with the teacher agent’s behaviour.

PDF

AAAI Conference 2018 Conference Paper

Deep Q-learning From Demonstrations

  • Todd Hester
  • Matej Vecerik
  • Olivier Pietquin
  • Marc Lanctot
  • Tom Schaul
  • Bilal Piot
  • Dan Horgan
  • John Quan

Deep reinforcement learning (RL) has achieved several high profile successes in difficult decision-making problems. However, these algorithms typically require a huge amount of data before they reach reasonable performance. In fact, their performance during learning can be extremely poor. This may be acceptable for a simulator, but it severely limits the applicability of deep RL to many real-world tasks, where the agent must learn in the real environment. In this paper we study a setting where the agent may access data from previous control of the system. We present an algorithm, Deep Q-learning from Demonstrations (DQfD), that leverages small sets of demonstration data to massively accelerate the learning process even from relatively small amounts of demonstration data and is able to automatically assess the necessary ratio of demonstration data while learning thanks to a prioritized replay mechanism. DQfD works by combining temporal difference updates with supervised classification of the demonstrator’s actions. We show that DQfD has better initial performance than Prioritized Dueling Double Deep Q-Networks (PDD DQN) as it starts with better scores on the first million steps on 41 of 42 games and on average it takes PDD DQN 83 million steps to catch up to DQfD’s performance. DQfD learns to out-perform the best demonstration given in 14 of 42 games. In addition, DQfD leverages human demonstrations to achieve state-of-the-art results for 11 games. Finally, we show that DQfD performs better than three related algorithms for incorporating demonstration data into DQN.

PDF Details

AAAI Conference 2018 Conference Paper

Rainbow: Combining Improvements in Deep Reinforcement Learning

  • Matteo Hessel
  • Joseph Modayil
  • Hado van Hasselt
  • Tom Schaul
  • Georg Ostrovski
  • Will Dabney
  • Dan Horgan
  • Bilal Piot

The deep reinforcement learning community has made several independent improvements to the DQN algorithm. However, it is unclear which of these extensions are complementary and can be fruitfully combined. This paper examines six extensions to the DQN algorithm and empirically studies their combination. Our experiments show that the combination provides state-of-the-art performance on the Atari 2600 benchmark, both in terms of data efficiency and final performance. We also provide results from a detailed ablation study that shows the contribution of each component to overall performance.

PDF Details

IJCAI Conference 2017 Conference Paper

End-to-end optimization of goal-driven and visually grounded dialogue systems

  • Florian Strub
  • Harm de Vries
  • Jérémie Mary
  • Bilal Piot
  • Aaron Courville
  • Olivier Pietquin

End-to-end design of dialogue systems has recently become a popular research topic thanks to powerful tools such as encoder-decoder architectures for sequence-to-sequence learning. Yet, most current approaches cast human-machine dialogue management as a supervised learning problem, aiming at predicting the next utterance of a participant given the full history of the dialogue. This vision may fail to correctly render the planning problem inherent to dialogue as well as its contextual and grounded nature. In this paper, we introduce a Deep Reinforcement Learning method to optimize visually grounded task-oriented dialogues, based on the policy gradient algorithm. This approach is tested on the question generation task from the dataset GuessWhat? ! containing 120k dialogues and provides encouraging results at solving both the problem of generating natural dialogues and the task of discovering a specific object in a complex picture.

PDF Details

NeurIPS Conference 2017 Conference Paper

Is the Bellman residual a bad proxy?

  • Matthieu Geist
  • Bilal Piot
  • Olivier Pietquin

This paper aims at theoretically and empirically comparing two standard optimization criteria for Reinforcement Learning: i) maximization of the mean value and ii) minimization of the Bellman residual. For that purpose, we place ourselves in the framework of policy search algorithms, that are usually designed to maximize the mean value, and derive a method that minimizes the residual $\|T_* v_\pi - v_\pi\|_{1, \nu}$ over policies. A theoretical analysis shows how good this proxy is to policy optimization, and notably that it is better than its value-based counterpart. We also propose experiments on randomly generated generic Markov decision processes, specifically designed for studying the influence of the involved concentrability coefficient. They show that the Bellman residual is generally a bad proxy to policy optimization and that directly maximizing the mean value is much better, despite the current lack of deep theoretical analysis. This might seem obvious, as directly addressing the problem of interest is usually better, but given the prevalence of (projected) Bellman residual minimization in value-based reinforcement learning, we believe that this question is worth to be considered.

PDF Details

EWRL Workshop 2016 Workshop Paper

Batch policy iteration algorithms for continuous domains

  • Bilal Piot
  • Matthieu Geist
  • Olivier Pietquin

This paper establishes the link between an adaptation of the policy iteration method for Markov decision processes with continuous state and action spaces and the policy gradient method when the differentiation of the mean value is directly done over the policy without parameterization. This approach allows deriving sound and practical batch Reinforcement Learning algorithms for continuous state and action spaces.

PDF Details

AAMAS Conference 2016 Conference Paper

Score-based Inverse Reinforcement Learning

  • Layla El Asri
  • Bilal Piot
  • Matthieu Geist
  • Romain Laroche
  • Olivier Pietquin

This paper reports theoretical and empirical results obtained for the score-based Inverse Reinforcement Learning (IRL) algorithm. It relies on a non-standard setting for IRL consisting of learning a reward from a set of globally scored trajectories. This allows using any type of policy (optimal or not) to generate trajectories without prior knowledge during data collection. This way, any existing database (like logs of systems in use) can be scored a posteriori by an expert and used to learn a reward function. Thanks to this reward function, it is shown that a near-optimal policy can be computed. Being related to least-square regression, the algorithm (called SBIRL) comes with theoretical guarantees that are proven in this paper. SBIRL is compared to standard IRL algorithms on synthetic data showing that annotations do help under conditions on the quality of the trajectories. It is also shown to be suitable for real-world applications such as the optimisation of a spoken dialogue system.

PDF

ICML Conference 2016 Conference Paper

Softened Approximate Policy Iteration for Markov Games

  • Julien Pérolat
  • Bilal Piot
  • Matthieu Geist
  • Bruno Scherrer
  • Olivier Pietquin

This paper reports theoretical and empirical investigations on the use of quasi-Newton methods to minimize the Optimal Bellman Residual (OBR) of zero-sum two-player Markov Games. First, it reveals that state-of-the-art algorithms can be derived by the direct application of Newton’s method to different norms of the OBR. More precisely, when applied to the norm of the OBR, Newton’s method results in the Bellman Residual Minimization Policy Iteration (BRMPI) and, when applied to the norm of the Projected OBR (POBR), it results into the standard Least Squares Policy Iteration (LSPI) algorithm. Consequently, new algorithms are proposed, making use of quasi-Newton methods to minimize the OBR and the POBR so as to take benefit of enhanced empirical performances at low cost. Indeed, using a quasi-Newton method approach introduces slight modifications in term of coding of LSPI and BRMPI but improves significantly both the stability and the performance of those algorithms. These phenomena are illustrated on an experiment conducted on artificially constructed games called Garnets.

Details

ICML Conference 2015 Conference Paper

Approximate Dynamic Programming for Two-Player Zero-Sum Markov Games

  • Julien Pérolat
  • Bruno Scherrer
  • Bilal Piot
  • Olivier Pietquin

This paper provides an analysis of error propagation in Approximate Dynamic Programming applied to zero-sum two-player Stochastic Games. We provide a novel and unified error propagation analysis in L_p-norm of three well-known algorithms adapted to Stochastic Games (namely Approximate Value Iteration, Approximate Policy Iteration and Approximate Generalized Policy Iteration). We show that we can achieve a stationary policy which is \frac2γ(1 - γ)^2 ε+ \frac1(1 - γ)^2ε’-optimal, where εis the value function approximation error and ε’ is the approximate greedy operator error. In addition, we provide a practical algorithm (AGPI-Q) to solve infinite horizon γ-discounted two-player zero-sum stochastic games in a batch setting. It is an extension of the Fitted-Q algorithm (which solves Markov Decisions Processes in a batch setting) and can be non-parametric. Finally, we demonstrate experimentally the performance of AGPI-Q on a simultaneous two-player game, namely Alesia.

Details

IJCAI Conference 2015 Conference Paper

Inverse Reinforcement Learning in Relational Domains

  • Thibaut Munzer
  • Bilal Piot
  • Matthieu Geist
  • Olivier Pietquin
  • Manuel Lopes

In this work, we introduce the first approach to the Inverse Reinforcement Learning (IRL) problem in relational domains. IRL has been used to recover a more compact representation of the expert policy leading to better generalization performances among different contexts. On the other hand, relational learning allows representing problems with a varying number of objects (potentially infinite), thus provides more generalizable representations of problems and skills. We show how these different formalisms allow one to create a new IRL algorithm for relational domains that can recover with great efficiency rewards from expert data that have strong generalization and transfer properties. We evaluate our algorithm in representative tasks and study the impact of diverse experimental conditions such as: the number of demonstrations, knowledge about the dynamics, transfer among varying dimensions of a problem, and changing dynamics.

PDF Details

NeurIPS Conference 2014 Conference Paper

Difference of Convex Functions Programming for Reinforcement Learning

  • Bilal Piot
  • Matthieu Geist
  • Olivier Pietquin

Large Markov Decision Processes (MDPs) are usually solved using Approximate Dynamic Programming (ADP) methods such as Approximate Value Iteration (AVI) or Approximate Policy Iteration (API). The main contribution of this paper is to show that, alternatively, the optimal state-action value function can be estimated using Difference of Convex functions (DC) Programming. To do so, we study the minimization of a norm of the Optimal Bellman Residual (OBR) $T^*Q-Q$, where $T^*$ is the so-called optimal Bellman operator. Controlling this residual allows controlling the distance to the optimal action-value function, and we show that minimizing an empirical norm of the OBR is consistant in the Vapnik sense. Finally, we frame this optimization problem as a DC program. That allows envisioning using the large related literature on DC Programming to address the Reinforcement Leaning (RL) problem.

PDF Details

RLDM Conference 2013 Conference Abstract

Around Inverse Reinforcement Learning and Score-based Classification

  • Matthieu Geist
  • Edouard Klein
  • Bilal Piot
  • Yann Guermeur

Inverse reinforcement learning (IRL) aims at estimating an unknown reward function optimized by some expert agent from interactions between this expert and the system to be controlled. One of its major application fields is imitation learning, where the goal is to imitate the expert, possibly in situations not encountered before. A classic and simple way to handle this problem is to see it as a classification problem, mapping states to actions. The potential issue with this approach is that classification does not take naturally into account the temporal structure of sequential decision making. Yet, many classification algorithms consist in learning a score function, mapping state-action couples to values, such that the value of the action chosen by the expert is higher than the others. The decision rule of the classifier maximizes the score over actions for a given state. This is curiously reminiscent of the state-action value function in reinforcement learning, and of the associated greedy policy. Based on this simple statement, we propose two IRL algorithms that incorporate the structure of the se- quential decision making problem into some classifier in different ways. The first one, SCIRL (Structured Classification for IRL), starts from the observation that linearly parameterizing a reward function by some features imposes a linear parametrization of the Q-function by a so-called feature expectation. SCIRL simply uses (an estimate of) the expert feature expectation as the basis function of the score function. The second algorithm, CSI (Cascaded Supervised IRL), applies a reversed Bellman equation (expressing the reward as a function of the Q-function) to the score function outputted by any score-based classifier, which reduces to a simple (and generic) regression step. These two algorithms come with theoretical guarantees and perform competitively on toy problems.

PDF Details

NeurIPS Conference 2012 Conference Paper

Inverse Reinforcement Learning through Structured Classification

  • Edouard Klein
  • Matthieu Geist
  • Bilal Piot
  • Olivier Pietquin

This paper adresses the inverse reinforcement learning (IRL) problem, that is inferring a reward for which a demonstrated expert behavior is optimal. We introduce a new algorithm, SCIRL, whose principle is to use the so-called feature expectation of the expert as the parameterization of the score function of a multi-class classifier. This approach produces a reward function for which the expert policy is provably near-optimal. Contrary to most of existing IRL algorithms, SCIRL does not require solving the direct RL problem. Moreover, with an appropriate heuristic, it can succeed with only trajectories sampled according to the expert behavior. This is illustrated on a car driving simulator.

PDF Details