Author name cluster

A. Rupam Mahmood

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.

37 papers

2 author rows

RLC Conference 2025 Conference Paper

AVG-DICE: Stationary Distribution Correction by Regression

Fengdi Che
Bryan Chan
Chen Ma
A. Rupam Mahmood

Off-policy policy evaluation (OPE), an essential component of reinforcement learning, has long suffered from stationary state distribution mismatch, undermining both stability and accuracy of OPE estimates. While existing methods correct distribution shifts by estimating density ratios, they often rely on expensive optimization or backward Bellman-based updates and struggle to outperform simpler baselines. We introduce AVG-DICE, a computationally simple Monte Carlo estimator for the density ratio that averages discounted importance sampling ratios, providing an unbiased and consistent correction. AVG-DICE extends naturally to nonlinear function approximation using regression, which we roughly tune and test on OPE tasks based on Mujoco Gym environments and compare with state-of-the-art density-ratio estimators using their reported hyperparameters. In our experiments, AVG-DICE is at least as accurate as state-of-the-art estimators and sometimes offers orders-of-magnitude improvements. However, a sensitivity analysis shows that best-performing hyperparameters may vary substantially across different discount factors, so a re-tuning is suggested.

RLJ Journal 2025 Journal Article

AVG-DICE: Stationary Distribution Correction by Regression

Fengdi Che
Bryan Chan
Chen Ma
A. Rupam Mahmood

Off-policy policy evaluation (OPE), an essential component of reinforcement learning, has long suffered from stationary state distribution mismatch, undermining both stability and accuracy of OPE estimates. While existing methods correct distribution shifts by estimating density ratios, they often rely on expensive optimization or backward Bellman-based updates and struggle to outperform simpler baselines. We introduce AVG-DICE, a computationally simple Monte Carlo estimator for the density ratio that averages discounted importance sampling ratios, providing an unbiased and consistent correction. AVG-DICE extends naturally to nonlinear function approximation using regression, which we roughly tune and test on OPE tasks based on Mujoco Gym environments and compare with state-of-the-art density-ratio estimators using their reported hyperparameters. In our experiments, AVG-DICE is at least as accurate as state-of-the-art estimators and sometimes offers orders-of-magnitude improvements. However, a sensitivity analysis shows that best-performing hyperparameters may vary substantially across different discount factors, so a re-tuning is suggested.

EWRL Workshop 2025 Workshop Paper

MaDi: Learning to Mask Distractions for Generalization in Visual Deep Reinforcement Learning

Bram Grooten
Tristan Tomilin
Gautham Vasan
Matthew E. Taylor
A. Rupam Mahmood
Meng Fang
Mykola Pechenizkiy
Decebal Constantin Mocanu

The visual world provides an abundance of information, but many input pixels received by agents often contain distracting stimuli. Autonomous agents need the ability to distinguish useful information from task-irrelevant perceptions, enabling them to generalize to unseen environments with new distractions. Existing works approach this problem using data augmentation or large auxiliary networks with additional loss functions. We introduce MaDi, a novel algorithm that learns to mask distractions by the reward signal only. In MaDi, the conventional actor-critic structure of deep reinforcement learning agents is complemented by a small third sibling, the Masker. This lightweight neural network generates a mask to determine what the actor and critic receive, such that they can focus on learning the task. We run experiments on the DeepMind Control Generalization Benchmark, the Distracting Control Suite, and a real UR5 Robotic Arm. Our algorithm improves the agent’s focus with useful masks, while its efficient Masker network only adds 0. 2% more parameters to the original structure, in contrast to previous work. MaDi consistently achieves generalization results better than or competitive to state-of-the-art methods.

ICLR Conference 2024 Conference Paper

Addressing Loss of Plasticity and Catastrophic Forgetting in Continual Learning

Mohamed Elsayed 0003
A. Rupam Mahmood

Deep representation learning methods struggle with continual learning, suffering from both catastrophic forgetting of useful units and loss of plasticity, often due to rigid and unuseful units. While many methods address these two issues separately, only a few currently deal with both simultaneously. In this paper, we introduce Utility-based Perturbed Gradient Descent (UPGD) as a novel approach for the continual learning of representations. UPGD combines gradient updates with perturbations, where it applies smaller modifications to more useful units, protecting them from forgetting, and larger modifications to less useful units, rejuvenating their plasticity. We use a challenging streaming learning setup where continual learning problems have hundreds of non-stationarities and unknown task boundaries. We show that many existing methods suffer from at least one of the issues, predominantly manifested by their decreasing accuracy over tasks. On the other hand, UPGD continues to improve performance and surpasses or is competitive with all methods in all problems. Finally, in extended reinforcement learning experiments with PPO, we show that while Adam exhibits a performance drop after initial learning, UPGD avoids it by addressing both continual learning issues.

RLC Conference 2024 Conference Paper

Learning to Optimize for Reinforcement Learning

Qingfeng Lan
A. Rupam Mahmood
Shuicheng Yan
Zhongwen Xu

In recent years, by leveraging more data, computation, and diverse tasks, learned optimizers have achieved remarkable success in supervised learning, outperforming classical hand-designed optimizers. Reinforcement learning (RL) is essentially different from supervised learning, and in practice, these learned optimizers do not work well even in simple RL tasks. We investigate this phenomenon and identify two issues. First, the agent-gradient distribution is non-independent and identically distributed, leading to inefficient meta-training. Moreover, due to highly stochastic agent-environment interactions, the agent-gradients have high bias and variance, which increases the difficulty of learning an optimizer for RL. We propose pipeline training and a novel optimizer structure with a good inductive bias to address these issues, making it possible to learn an optimizer for reinforcement learning from scratch. We show that, although only trained in toy tasks, our learned optimizer can generalize to unseen complex tasks in Brax.

RLJ Journal 2024 Journal Article

Learning to Optimize for Reinforcement Learning

Qingfeng Lan
A. Rupam Mahmood
Shuicheng Yan
Zhongwen Xu

In recent years, by leveraging more data, computation, and diverse tasks, learned optimizers have achieved remarkable success in supervised learning, outperforming classical hand-designed optimizers. Reinforcement learning (RL) is essentially different from supervised learning, and in practice, these learned optimizers do not work well even in simple RL tasks. We investigate this phenomenon and identify two issues. First, the agent-gradient distribution is non-independent and identically distributed, leading to inefficient meta-training. Moreover, due to highly stochastic agent-environment interactions, the agent-gradients have high bias and variance, which increases the difficulty of learning an optimizer for RL. We propose pipeline training and a novel optimizer structure with a good inductive bias to address these issues, making it possible to learn an optimizer for reinforcement learning from scratch. We show that, although only trained in toy tasks, our learned optimizer can generalize to unseen complex tasks in Brax.

AAMAS Conference 2024 Conference Paper

MaDi: Learning to Mask Distractions for Generalization in Visual Deep Reinforcement Learning

Bram Grooten
Tristan Tomilin
Gautham Vasan
Matthew E. Taylor
A. Rupam Mahmood
Meng Fang
Mykola Pechenizkiy
Decebal Constantin Mocanu

The visual world provides an abundance of information, but many input pixels received by agents often contain distracting stimuli. Autonomous agents need the ability to distinguish useful information from task-irrelevant perceptions, enabling them to generalize to unseen environments with new distractions. Existing works approach this problem using data augmentation or large auxiliary networks with additional loss functions. We introduce MaDi, a novel algorithm that learns to mask distractions by the reward signal only. In MaDi, the conventional actor-critic structure of deep reinforcement learning agents is complemented by a small third sibling, the Masker. This lightweight neural network generates a mask to determine what the actor and critic receive, such that they can focus on learning the task. We run experiments on the DeepMind Control Generalization Benchmark, the Distracting Control Suite, and a real UR5 Robotic Arm. Our algorithm improves the agent’s focus with useful masks, while its efficient Masker network only adds 0. 2% more parameters to the original structure, in contrast to previous work. MaDi consistently achieves generalization results better than or competitive to state-of-the-art methods. 1

RLJ Journal 2024 Journal Article

More Efficient Randomized Exploration for Reinforcement Learning via Approximate Sampling

Haque Ishfaq
Yixin Tan
Yu Yang
Qingfeng Lan
Jianfeng Lu
A. Rupam Mahmood
Doina Precup
Pan Xu

Thompson sampling (TS) is one of the most popular exploration techniques in reinforcement learning (RL). However, most TS algorithms with theoretical guarantees are difficult to implement and not generalizable to Deep RL. While approximate sampling-based exploration schemes are promising, most existing algorithms are specific to linear Markov Decision Processes (MDP) with suboptimal regret bounds, or only use the most basic samplers such as Langevin Monte Carlo. In this work, we propose an algorithmic framework that incorporates different approximate sampling methods with the recently proposed Feel-Good Thompson Sampling (FGTS) approach (Zhang, 2022; Dann et al., 2021), which was previously known to be intractable. When applied to linear MDPs, our regret analysis yields the best known dependency of regret on dimensionality, surpassing existing randomized algorithms. Additionally, we provide explicit sampling complexity for each employed sampler. Empirically, we show that in tasks where deep exploration is necessary, our proposed algorithms that combine FGTS and approximate sampling perform significantly better compared to other strong baselines. On several challenging games from the Atari 57 suite, our algorithms achieve performance that is either better than or on par with other strong baselines from the deep RL literature.

RLC Conference 2024 Conference Paper

More Efficient Randomized Exploration for Reinforcement Learning via Approximate Sampling

Haque Ishfaq
Yixin Tan
Yu Yang
Qingfeng Lan
Jianfeng Lu
A. Rupam Mahmood
Doina Precup
Pan Xu

Thompson sampling (TS) is one of the most popular exploration techniques in reinforcement learning (RL). However, most TS algorithms with theoretical guarantees are difficult to implement and not generalizable to Deep RL. While approximate sampling-based exploration schemes are promising, most existing algorithms are specific to linear Markov Decision Processes (MDP) with suboptimal regret bounds, or only use the most basic samplers such as Langevin Monte Carlo. In this work, we propose an algorithmic framework that incorporates different approximate sampling methods with the recently proposed Feel-Good Thompson Sampling (FGTS) approach (Zhang, 2022; Dann et al. , 2021), which was previously known to be intractable. When applied to linear MDPs, our regret analysis yields the best known dependency of regret on dimensionality, surpassing existing randomized algorithms. Additionally, we provide explicit sampling complexity for each employed sampler. Empirically, we show that in tasks where deep exploration is necessary, our proposed algorithms that combine FGTS and approximate sampling perform significantly better compared to other strong baselines. On several challenging games from the Atari 57 suite, our algorithms achieve performance that is either better than or on par with other strong baselines from the deep RL literature.

ICLR Conference 2024 Conference Paper

Provable and Practical: Efficient Exploration in Reinforcement Learning via Langevin Monte Carlo

Haque Ishfaq
Qingfeng Lan
Pan Xu 0002
A. Rupam Mahmood
Doina Precup
Anima Anandkumar
Kamyar Azizzadenesheli

We present a scalable and effective exploration strategy based on Thompson sampling for reinforcement learning (RL). One of the key shortcomings of existing Thompson sampling algorithms is the need to perform a Gaussian approximation of the posterior distribution, which is not a good surrogate in most practical settings. We instead directly sample the Q function from its posterior distribution, by using Langevin Monte Carlo, an efficient type of Markov Chain Monte Carlo (MCMC) method. Our method only needs to perform noisy gradient descent updates to learn the exact posterior distribution of the Q function, which makes our approach easy to deploy in deep RL. We provide a rigorous theoretical analysis for the proposed method and demonstrate that, in the linear Markov decision process (linear MDP) setting, it has a regret bound of $\tilde{O}(d^{3/2}H^{3/2}\sqrt{T})$, where $d$ is the dimension of the feature mapping, $H$ is the planning horizon, and $T$ is the total number of steps. We apply this approach to deep RL, by using Adam optimizer to perform gradient updates. Our approach achieves better or similar results compared with state-of-the-art deep RL algorithms on several challenging exploration tasks from the Atari57 suite.

ICML Conference 2024 Conference Paper

Revisiting Scalable Hessian Diagonal Approximations for Applications in Reinforcement Learning

Mohamed Elsayed 0003
Homayoon Farrahi
Felix Dangel
A. Rupam Mahmood

Second-order information is valuable for many applications but challenging to compute. Several works focus on computing or approximating Hessian diagonals, but even this simplification introduces significant additional costs compared to computing a gradient. In the absence of efficient exact computation schemes for Hessian diagonals, we revisit an early approximation scheme proposed by Becker and LeCun (1989, BL89), which has a cost similar to gradients and appears to have been overlooked by the community. We introduce HesScale, an improvement over BL89, which adds negligible extra computation. On small networks, we find that this improvement is of higher quality than all alternatives, even those with theoretical guarantees, such as unbiasedness, while being much cheaper to compute. We use this insight in reinforcement learning problems where small networks are used and demonstrate HesScale in second-order optimization and scaling the step-size parameter. In our experiments, HesScale optimizes faster than existing methods and improves stability through step-size scaling. These findings are promising for scaling second-order methods in larger models in the future.

RLJ Journal 2024 Journal Article

Revisiting Sparse Rewards for Goal-Reaching Reinforcement Learning

Gautham Vasan
Yan Wang
Fahim Shahriar
James Bergstra
Martin Jägersand
A. Rupam Mahmood

Many real-world robot learning problems, such as pick-and-place or arriving at a destination, can be seen as a problem of reaching a goal state as soon as possible. These problems, when formulated as episodic reinforcement learning tasks, can easily be specified to align well with our intended goal: -1 reward every time step with termination upon reaching the goal state (termed $\textit{minimum-time}$ tasks). Despite this simplicity, such formulations are often overlooked in favor of dense rewards due to their perceived difficulty and lack of informativeness. Our studies contrast the two reward paradigms, revealing that the minimum-time task specification not only facilitates learning higher-quality policies but can also surpass dense-reward-based policies on their own performance metrics. Crucially, we also identify the goal-hit rate of the initial policy as a robust early indicator for learning success in such sparse feedback settings. Finally, using four distinct real-robotic platforms, we show that it is possible to learn pixel-based policies from scratch within two to three hours using constant negative rewards. Our video demo can be found here: https://youtu.be/a6zlVUuKzBc

RLC Conference 2024 Conference Paper

Revisiting Sparse Rewards for Goal-Reaching Reinforcement Learning

Gautham Vasan
Yan Wang
Fahim Shahriar
James Bergstra
Martin Jägers
A. Rupam Mahmood

Many real-world robot learning problems, such as pick-and-place or arriving at a destination, can be seen as a problem of reaching a goal state as soon as possible. These problems, when formulated as episodic reinforcement learning tasks, can easily be specified to align well with our intended goal: -1 reward every time step with termination upon reaching the goal state (termed $\textit{minimum-time}$ tasks). Despite this simplicity, such formulations are often overlooked in favor of dense rewards due to their perceived difficulty and lack of informativeness. Our studies contrast the two reward paradigms, revealing that the minimum-time task specification not only facilitates learning higher-quality policies but can also surpass dense-reward-based policies on their own performance metrics. Crucially, we also identify the goal-hit rate of the initial policy as a robust early indicator for learning success in such sparse feedback settings. Finally, using four distinct real-robotic platforms, we show that it is possible to learn pixel-based policies from scratch within two to three hours using constant negative rewards. Our video demo can be found here: https: //youtu. be/a6zlVUuKzBc

ICML Conference 2024 Conference Paper

Target Networks and Over-parameterization Stabilize Off-policy Bootstrapping with Function Approximation

Fengdi Che
Chenjun Xiao
Jincheng Mei
Bo Dai 0001
Ramki Gummadi
Oscar Ramirez
Christopher K. Harris
A. Rupam Mahmood

We prove that the combination of a target network and over-parameterized linear function approximation establishes a weaker convergence condition for bootstrapped value estimation in certain cases, even with off-policy data. Our condition is naturally satisfied for expected updates over the entire state-action space or learning with a batch of complete trajectories from episodic Markov decision processes. Notably, using only a target network or an over-parameterized model does not provide such a convergence guarantee. Additionally, we extend our results to learning with truncated trajectories, showing that convergence is achievable for all tasks with minor modifications, akin to value truncation for the final states in trajectories. Our primary result focuses on temporal difference estimation for prediction, providing high-probability value estimation error bounds and empirical analysis on Baird’s counterexample and a Four-room task. Furthermore, we explore the control setting, demonstrating that similar convergence conditions apply to Q-learning.

RLC Conference 2024 Conference Paper

Weight Clipping for Deep Continual and Reinforcement Learning

Mohamed Elsayed
Qingfeng Lan
Clare Lyle
A. Rupam Mahmood

Many failures in deep continual and reinforcement learning are associated with increasing magnitudes of the weights, making them hard to change and potentially causing overfitting. While many methods address these learning failures, they often change the optimizer or the architecture, a complexity that hinders widespread adoption in various systems. In this paper, we focus on learning failures that are associated with increasing weight norm and we propose a simple technique that can be easily added on top of existing learning systems: clipping neural network weights to limit them to a specific range. We study the effectiveness of weight clipping in a series of supervised and reinforcement learning experiments. Our empirical results highlight the benefits of weight clipping for generalization, addressing loss of plasticity and policy collapse, and facilitating learning with a large replay ratio.

RLJ Journal 2024 Journal Article

Weight Clipping for Deep Continual and Reinforcement Learning

Mohamed Elsayed
Qingfeng Lan
Clare Lyle
A. Rupam Mahmood

Many failures in deep continual and reinforcement learning are associated with increasing magnitudes of the weights, making them hard to change and potentially causing overfitting. While many methods address these learning failures, they often change the optimizer or the architecture, a complexity that hinders widespread adoption in various systems. In this paper, we focus on learning failures that are associated with increasing weight norm and we propose a simple technique that can be easily added on top of existing learning systems: clipping neural network weights to limit them to a specific range. We study the effectiveness of weight clipping in a series of supervised and reinforcement learning experiments. Our empirical results highlight the benefits of weight clipping for generalization, addressing loss of plasticity and policy collapse, and facilitating learning with a large replay ratio.

EWRL Workshop 2023 Workshop Paper

A Gradient Critic for Policy Gradient Estimation

Samuele Tosatto
Andrew Patterson
Martha White
A. Rupam Mahmood

The policy gradient theorem (Sutton et al. , 2000) prescribes the usage of the on-policy state distribution to approximate the gradient. Most algorithms based on this theorem, in practice, break this assumption introducing a distribution shift that can cause the convergence to poor solutions. In this paper, we propose a new approach of reconstructing the policy gradient from the start state without requiring a particular sampling strategy. The policy gradient calculation in this form can be simplified in terms of a \textsl{gradient critic}, which can be recursively estimated due to a new Bellman equation of gradients. By using temporal-difference updates of the gradient critic from an off-policy data stream, we develop the first estimator that side-steps the distribution shift issue in a model-free way. We prove that, under certain realizability conditions, our estimator is unbiased regardless of the sampling strategy. We empirically show that our technique achieves a superior bias-variance trade-off and performance in the presence of off-policy samples. The extended version of this work can be found in Tosatto et al. (2022), and the implementation of the experiment at github. com/SamuelePolimi/temporal-difference-gradient.

ICML Conference 2023 Conference Paper

Correcting discount-factor mismatch in on-policy policy gradient methods

Fengdi Che
Gautham Vasan
A. Rupam Mahmood

The policy gradient theorem gives a convenient form of the policy gradient in terms of three factors: an action value, a gradient of the action likelihood, and a state distribution involving discounting called the discounted stationary distribution. But commonly used on-policy methods based on the policy gradient theorem ignores the discount factor in the state distribution, which is technically incorrect and may even cause degenerate learning behavior in some environments. An existing solution corrects this discrepancy by using $\gamma^t$ as a factor in the gradient estimate. However, this solution is not widely adopted and does not work well in tasks where the later states are similar to earlier states. We introduce a novel distribution correction to account for the discounted stationary distribution that can be plugged into many existing gradient estimators. Our correction circumvents the performance degradation associated with the $\gamma^t$ correction with a lower variance. Importantly, compared to the uncorrected estimators, our algorithm provides improved state emphasis to evade suboptimal policies in certain environments and consistently matches or exceeds the original performance on several OpenAI gym and DeepMind suite benchmarks.

IROS Conference 2023 Conference Paper

Dynamic Decision Frequency with Continuous Options

Amirmohammad Karimi
Jun Jin 0001
Jun Luo 0009
A. Rupam Mahmood
Martin Jägersand
Samuele Tosatto

In classic reinforcement learning algorithms, agents make decisions at discrete and fixed time intervals. The duration between decisions becomes a crucial hyperparameter, as setting it too short may increase the problem's difficulty by requiring the agent to make numerous decisions to achieve its goal while setting it too long can result in the agent losing control over the system. However, physical systems do not necessarily require a constant control frequency, and for learning agents, it is often preferable to operate with a low frequency when possible and a high frequency when necessary. We propose a framework called Continuous-Time Continuous-Options (CTCO), where the agent chooses options as sub-policies of variable durations. These options are time-continuous and can interact with the system at any desired frequency providing a smooth change of actions. We demonstrate the effectiveness of CTCO by comparing its performance to classical RL and temporal-abstraction RL methods on simulated continuous control tasks with various action-cycle times. We show that our algorithm's performance is not affected by the choice of environment interaction frequency. Furthermore, we demonstrate the efficacy of CTCO in facilitating exploration in a real-world visual reaching task for a 7 DOF robotic arm with sparse rewards.

UAI Conference 2023 Conference Paper

Loosely consistent emphatic temporal-difference learning

Jiamin He
Fengdi Che
Yi Wan
A. Rupam Mahmood

There has been significant interest in searching for off-policy Temporal-Difference (TD) algorithms that find the same solution that would have been obtained in the on-policy regime. An important property of such algorithms is that their expected update has the same fixed point as that of On-policy TD($\lambda$), which we call loose consistency. Notably, Full-IS-TD($\lambda$) is the only existing loosely consistent method under general linear function approximation but, unfortunately, has a high variance and is scarcely practical. This notorious high variance issue motivates the introduction of ETD($\lambda$), which tames down the variance but has a biased fixed point. Inspired by these two methods, we propose a new loosely consistent algorithm called Average Emphatic TD (AETD($\lambda$)) with a transient bias, which strikes a balance between bias and variance. Further, we unify AETD($\lambda$) with existing methods and obtain a new family of loosely consistent algorithms called Loosely Consistent Emphatic TD (LC-ETD($\lambda$, $\beta$, $\nu$)), which can control a smooth bias-variance trade-off by varying the speed at which the transient bias fades. Through experiments on illustrative examples, we show the effectiveness and practicality of LC-ETD($\lambda$, $\beta$, $\nu$).

TMLR Journal 2023 Journal Article

Memory-efficient Reinforcement Learning with Value-based Knowledge Consolidation

Qingfeng Lan
Yangchen Pan
Jun Luo
A. Rupam Mahmood

Artificial neural networks are promising for general function approximation but challenging to train on non-independent or non-identically distributed data due to catastrophic forgetting. The experience replay buffer, a standard component in deep reinforcement learning, is often used to reduce forgetting and improve sample efficiency by storing experiences in a large buffer and using them for training later. However, a large replay buffer results in a heavy memory burden, especially for onboard and edge devices with limited memory capacities. We propose memory-efficient reinforcement learning algorithms based on the deep Q-network algorithm to alleviate this problem. Our algorithms reduce forgetting and maintain high sample efficiency by consolidating knowledge from the target Q-network to the current Q-network. Compared to baseline methods, our algorithms achieve comparable or better performance in both feature-based and image-based tasks while easing the burden of large experience replay buffers.

EWRL Workshop 2023 Workshop Paper

Overcoming Policy Collapse in Deep Reinforcement Learning

Shibhansh Dohare
Qingfeng Lan
A. Rupam Mahmood

A long-awaited characteristic of reinforcement learning agents is scalable performance, that is, to continue to learn and improve performance with a never-ending stream of experience. However, current deep reinforcement learning algorithms are known to be brittle and difficult to train, which limits their scalability. For example, the learned policy can dramatically worsen after some initial training as the agent continues to interact with the environment. We call this phenomenon \textit{policy collapse}. We first establish that policy collapse can occur in both policy gradient and value-based methods. Policy collapse happens in these algorithms in typical benchmarks such as Mujoco environments when trained with their commonly used hyper-parameters. In a simple 2-state MDP, we show that the standard use of the Adam optimizer with its default hyper-parameters is a root cause of policy collapse. Specifically, the standard use of Adam can lead to sudden large weight changes even when the gradient is small whenever there is non-stationarity in the data stream. We find that policy collapse can be successfully mitigated by using the same hyper-parameters for the running averages of the first and second moments of the gradient. Additionally, we find that aggressive L2 regularization also mitigates policy collapse in many cases. Our work establishes that a minimal change in the existing usage of deep reinforcement learning can mitigate policy collapse and enable more stable and scalable deep reinforcement learning.

EWRL Workshop 2023 Workshop Paper

Provable and Practical: Efficient Exploration in Reinforcement Learning via Langevin Monte Carlo

Haque Ishfaq
Qingfeng Lan
Pan Xu
A. Rupam Mahmood
Doina Precup
Anima Anandkumar
Kamyar Azizzadenesheli

We present a scalable and effective exploration strategy based on Thompson sampling for reinforcement learning (RL). One of the key shortcomings of existing Thompson sampling algorithms is the need to perform a Gaussian approximation of the posterior distribution, which is not a good surrogate in most practical settings. We instead directly sample the Q function from its posterior distribution, by using Langevin Monte Carlo, an efficient type of Markov Chain Monte Carlo (MCMC) method. Our method only needs to perform noisy gradient descent updates to learn the exact posterior distribution of the Q function, which makes our approach easy to deploy in deep RL. We provide a rigorous theoretical analysis for the proposed method and demonstrate that, in the linear Markov decision process (linear MDP) setting, it has a regret bound of $\tilde{O}(d^{3/2}H^{5/2}\sqrt{T})$, where $d$ is the dimension of the feature mapping, $H$ is the planning horizon, and $T$ is the total number of steps. We apply this approach to deep RL, by using Adam optimizer to perform gradient updates. Our approach achieves better or similar results compared with state-of-the-art deep RL algorithms on several challenging exploration tasks from the Atari57 suite.

ICRA Conference 2023 Conference Paper

Real-Time Reinforcement Learning for Vision-Based Robotics Utilizing Local and Remote Computers

Yan Wang
Gautham Vasan
A. Rupam Mahmood

Real-time learning is crucial for robotic agents adapting to ever-changing, non-stationary environments. A common setup for a robotic agent is to have two different computers simultaneously: a resource-limited local computer tethered to the robot and a powerful remote computer connected wirelessly. Given such a setup, it is unclear to what extent the performance of a learning system can be affected by resource limitations and how to efficiently use the wirelessly connected powerful computer to compensate for any performance loss. In this paper, we implement a real-time learning system called the Remote-Local Distributed (ReLoD) system to distribute computations of two deep reinforcement learning (RL) algorithms, Soft Actor-Critic (SAC) and Proximal Policy Optimization (PPO), between a local and a remote computer. The performance of the system is evaluated on two vision-based control tasks developed using a robotic arm and a mobile robot. Our results show that SAC's performance degrades heavily on a resource-limited local computer. Strikingly, when all computations of the learning system are deployed on a remote workstation, SAC fails to compensate for the performance loss, indicating that, without careful consideration, using a powerful remote computer may not result in performance improvement. However, a carefully chosen distribution of computations of SAC consistently and substantially improves its performance on both tasks. On the other hand, the performance of PPO remains largely unaffected by the distribution of computations. In addition, when all computations happen solely on a powerful tethered computer, the performance of our system remains on par with an existing system that is well-tuned for using a single machine. ReLoD is the only publicly available system for real-time RL that applies to multiple robots for vision-based tasks. The source code can be found at https://github.com/rlai-lab/relod

ICML Conference 2022 Conference Paper

A Temporal-Difference Approach to Policy Gradient Estimation

Samuele Tosatto
Andrew Patterson
Martha White
A. Rupam Mahmood

The policy gradient theorem (Sutton et al. , 2000) prescribes the usage of a cumulative discounted state distribution under the target policy to approximate the gradient. Most algorithms based on this theorem, in practice, break this assumption, introducing a distribution shift that can cause the convergence to poor solutions. In this paper, we propose a new approach of reconstructing the policy gradient from the start state without requiring a particular sampling strategy. The policy gradient calculation in this form can be simplified in terms of a gradient critic, which can be recursively estimated due to a new Bellman equation of gradients. By using temporal-difference updates of the gradient critic from an off-policy data stream, we develop the first estimator that side-steps the distribution shift issue in a model-free way. We prove that, under certain realizability conditions, our estimator is unbiased regardless of the sampling strategy. We empirically show that our technique achieves a superior bias-variance trade-off and performance in presence of off-policy samples.

ICRA Conference 2022 Conference Paper

Asynchronous Reinforcement Learning for Real-Time Control of Physical Robots

Yufeng Yuan
A. Rupam Mahmood

An oft-ignored challenge of real-world reinforcement learning is that the real world does not pause when agents make learning updates. As standard simulated environments do not address this real-time aspect of learning, most available implementations of RL algorithms process environment interactions and learning updates sequentially. As a consequence, when such implementations are deployed in the real world, they may make decisions based on significantly delayed observations and not act responsively. Asynchronous learning has been proposed to solve this issue, but no systematic comparison between sequential and asynchronous reinforcement learning was conducted using real-world environments. In this work, we set up two vision-based tasks with a robotic arm, implement an asynchronous learning system that extends a previous architecture, and compare sequential and asynchronous reinforcement learning across different action cycle times, sensory data dimensions, and mini-batch sizes. Our experiments show that when the time cost of learning updates increases, the action cycle time in sequential implementation could grow excessively long, while the asynchronous implementation can always maintain an appropriate action cycle time. Consequently, when learning updates are expensive, the performance of sequential learning diminishes and is outperformed by asynchronous learning by a substantial margin. Our system learns in real-time to reach and track visual targets from pixels within two hours of experience and does so directly using real robots, learning completely from scratch. Our code is available at: https://github.com/YufengYuan/ur5_async_r1.

JMLR Journal 2022 Journal Article

Greedification Operators for Policy Optimization: Investigating Forward and Reverse KL Divergences

Alan Chan
Hugo Silva
Sungsu Lim
Tadashi Kozuno
A. Rupam Mahmood
Martha White

Approximate Policy Iteration (API) algorithms alternate between (approximate) policy evaluation and (approximate) greedification. Many different approaches have been explored for approximate policy evaluation, but less is understood about approximate greedification and what choices guarantee policy improvement. In this work, we investigate approximate greedification when reducing the KL divergence between the parameterized policy and the Boltzmann distribution over action values. In particular, we investigate the difference between the forward and reverse KL divergences, with varying degrees of entropy regularization; these are chosen because they underlie many existing policy optimization approaches, as we highlight in this work. We show that the reverse KL has stronger policy improvement guarantees, and that reducing the forward KL can result in a worse policy. We also demonstrate, however, that a large enough reduction of the forward KL can induce improvement under additional assumptions. Empirically, we show on simple continuous-action environments that the forward KL can induce more exploration, but at the cost of a more suboptimal policy. No significant differences were observed in the discrete-action setting or on a suite of benchmark problems. This work provides novel theoretical and empirical insights about the forward KL and reverse KL for greedification, and clear next steps for understanding and improving our policy optimization algorithms. [abs] [ pdf ][ bib ] &copy JMLR 2022. ( edit, beta )

ICRA Conference 2021 Conference Paper

Analyzing Neural Jacobian Methods in Applications of Visual Servoing and Kinematic Control

Michael Przystupa
Masood Dehghan
Martin Jägersand
A. Rupam Mahmood

Designing adaptable control laws that can transfer between different robots is a challenge because of kinematic and dynamic differences, as well as in scenarios where external sensors are used. In this work, we empirically investigate a neural networks ability to approximate the Jacobian matrix for an application in Cartesian control schemes. Specifically, we are interested in approximating the kinematic Jacobian, which arises from kinematic equations mapping a manipulator’s joint angles to the end-effector’s location. We propose two different approaches to learn the kinematic Jacobian. The first method arises from visual servoing where we learn the kinematic Jacobian as an approximate linear system of equations from the k-nearest neighbors for a desired joint configuration. The second, motivated by forward models in machine learning, learns the kinematic behavior directly and calculates the Jacobian by differentiating the learned neural kinematics model. Simulation experimental results show that both methods achieve better performance than alternative data-driven methods for control, provide closer approximations to the proper kinematics Jacobian matrix, and on average produce better-conditioned Jacobian matrices. Real-world experiments were conducted on a Kinova Gen-3 lightweight robotic manipulator, which includes an uncalibrated visual servoing experiment, a practical application of our methods, as well as a 7-DOF point-to-point task highlighting that our methods are applicable on real robotic manipulators.

IJCAI Conference 2019 Conference Paper

Autoregressive Policies for Continuous Control Deep Reinforcement Learning

Dmytro Korenkevych
A. Rupam Mahmood
Gautham Vasan
James Bergstra

Reinforcement learning algorithms rely on exploration to discover new behaviors, which is typically achieved by following a stochastic policy. In continuous control tasks, policies with a Gaussian distribution have been widely adopted. Gaussian exploration however does not result in smooth trajectories that generally correspond to safe and rewarding behaviors in practical tasks. In addition, Gaussian policies do not result in an effective exploration of an environment and become increasingly inefficient as the action rate increases. This contributes to a low sample efficiency often observed in learning continuous control tasks. We introduce a family of stationary autoregressive (AR) stochastic processes to facilitate exploration in continuous control domains. We show that proposed processes possess two desirable features: subsequent process observations are temporally coherent with continuously adjustable degree of coherence, and the process stationary distribution is standard normal. We derive an autoregressive policy (ARP) that implements such processes maintaining the standard agent-environment interface. We show how ARPs can be easily used with the existing off-the-shelf learning algorithms. Empirically we demonstrate that using ARPs results in improved exploration and sample efficiency in both simulated and real world domains, and, furthermore, provides smooth exploration trajectories that enable safe operation of robotic hardware.

JMLR Journal 2018 Journal Article

On Generalized Bellman Equations and Temporal-Difference Learning

Huizhen Yu
A. Rupam Mahmood
Richard S. Sutton

We consider off-policy temporal-difference (TD) learning in discounted Markov decision processes, where the goal is to evaluate a policy in a model-free way by using observations of a state process generated without executing the policy. To curb the high variance issue in off-policy TD learning, we propose a new scheme of setting the $\lambda$-parameters of TD, based on generalized Bellman equations. Our scheme is to set $\lambda$ according to the eligibility trace iterates calculated in TD, thereby easily keeping these traces in a desired bounded range. Compared with prior work, this scheme is more direct and flexible, and allows much larger $\lambda$ values for off-policy TD learning with bounded traces. As to its soundness, using Markov chain theory, we prove the ergodicity of the joint state-trace process under nonrestrictive conditions, and we show that associated with our scheme is a generalized Bellman equation (for the policy to be evaluated) that depends on both the evolution of $\lambda$ and the unique invariant probability measure of the state-trace process. These results not only lead immediately to a characterization of the convergence behavior of least-squares based implementation of our scheme, but also prepare the ground for further analysis of gradient-based implementations. [abs] [ pdf ][ bib ] &copy JMLR 2018. ( edit, beta )

IROS Conference 2018 Conference Paper

Setting up a Reinforcement Learning Task with a Real-World Robot

A. Rupam Mahmood
Dmytro Korenkevych
Brent J. Komer
James Bergstra

Reinforcement learning is a promising approach to developing hard-to-engineer adaptive solutions for complex and diverse robotic tasks. However, learning with real-world robots is often unreliable and difficult, which resulted in their low adoption in reinforcement learning research. This difficulty is worsened by the lack of guidelines for setting up learning tasks with robots. In this work, we develop a learning task with a UR5 robotic arm to bring to light some key elements of a task setup and study their contributions to the challenges with robots 1 1 Source code of the task and the computational model behind the setup available at https://github.com/kindredresearch/SenseAct.We find that learning performance can be highly sensitive to the setup, and thus oversights and omissions in setup details can make effective learning, reproducibility, and fair comparison hard. Our study suggests some mitigating steps to help future experimenters avoid difficulties and pitfalls. We show that highly reliable and repeatable experiments can be performed in our setup, indicating the possibility of reinforcement learning research extensively based on real-world robots.

JMLR Journal 2016 Journal Article

An Emphatic Approach to the Problem of Off-policy Temporal-Difference Learning

Richard S. Sutton
A. Rupam Mahmood
Martha White

In this paper we introduce the idea of improving the performance of parametric temporal-difference (TD) learning algorithms by selectively emphasizing or de-emphasizing their updates on different time steps. In particular, we show that varying the emphasis of linear TD($\lambda$)'s updates in a particular way causes its expected update to become stable under off-policy training. The only prior model-free TD methods to achieve this with per- step computation linear in the number of function approximation parameters are the gradient-TD family of methods including TDC, GTD($\lambda$), and GQ$\lambda$). Compared to these methods, our emphatic TD($\lambda$) is simpler and easier to use; it has only one learned parameter vector and one step-size parameter. Our treatment includes general state- dependent discounting and bootstrapping functions, and a way of specifying varying degrees of interest in accurately valuing different states. [abs] [ pdf ][ bib ] &copy JMLR 2016. ( edit, beta )

JMLR Journal 2016 Journal Article

True Online Temporal-Difference Learning

Harm van Seijen
A. Rupam Mahmood
Patrick M. Pilarski
Marlos C. Machado
Richard S. Sutton

The temporal-difference methods TD($\lambda$) and Sarsa($\lambda$) form a core part of modern reinforcement learning. Their appeal comes from their good performance, low computational cost, and their simple interpretation, given by their forward view. Recently, new versions of these methods were introduced, called true online TD($\lambda$) and true online Sarsa($\lambda$), respectively (van Seijen & Sutton, 2014). Algorithmically, these true online methods only make two small changes to the update rules of the regular methods, and the extra computational cost is negligible in most cases. However, they follow the ideas underlying the forward view much more closely. In particular, they maintain an exact equivalence with the forward view at all times, whereas the traditional versions only approximate it for small step-sizes. We hypothesize that these true online methods not only have better theoretical properties, but also dominate the regular methods empirically. In this article, we put this hypothesis to the test by performing an extensive empirical comparison. Specifically, we compare the performance of true online TD($\lambda$)/Sarsa($\lambda$) with regular TD($\lambda$)/Sarsa($\lambda$) on random MRPs, a real-world myoelectric prosthetic arm, and a domain from the Arcade Learning Environment. We use linear function approximation with tabular, binary, and non-binary features. Our results suggest that the true online methods indeed dominate the regular methods. Across all domains/representations the learning speed of the true online methods are often better, but never worse than that of the regular methods. An additional advantage is that no choice between traces has to be made for the true online methods. Besides the empirical results, we provide an in-dept analysis of the theory behind true online temporal-difference learning. In addition, we show that new true online temporal- difference methods can be derived by making changes to the online forward view and then rewriting the update equations. [abs] [ pdf ][ bib ] &copy JMLR 2016. ( edit, beta )

UAI Conference 2015 Conference Paper

Off-policy learning based on weighted importance sampling with linear computational complexity

A. Rupam Mahmood
Richard S. Sutton

Importance sampling is an essential component of model-free off-policy learning algorithms. Weighted importance sampling (WIS) is generally considered superior to ordinary importance sampling but, when combined with function approximation, it has hitherto required computational complexity that is O(n2 ) or more in the number of features. In this paper we introduce new off-policy learning algorithms that obtain the benefits of WIS with O(n) computational complexity. Our algorithms maintain for each component of the parameter vector a measure of the extent to which that component has been used in previous examples. This measure is used to determine component-wise step sizes, merging the ideas of stochastic gradient descent and sample averages. We present our main WIS-based algorithm first in an intuitive acausal form (the forward view) and then derive a causal algorithm using eligibility traces that is equivalent but more efficient (the backward view). In three small experiments, our algorithms performed significantly better than prior O(n) algorithms for offpolicy policy evaluation. We also show that our adaptive step-size technique can also improve the performance of on-policy algorithms such as TD( ) and true online TD( ).

ICML Conference 2014 Conference Paper

A new Q(lambda) with interim forward view and Monte Carlo equivalence

Richard S. Sutton
A. Rupam Mahmood
Doina Precup
Hado van Hasselt

Q-learning, the most popular of reinforcement learning algorithms, has always included an extension to eligibility traces to enable more rapid learning and improved asymptotic performance on non-Markov problems. The lambda parameter smoothly shifts on-policy algorithms such as TD(lambda) and Sarsa(lambda) from a pure bootstrapping form (lambda=0) to a pure Monte Carlo form (lambda=1). In off-policy algorithms, including Q(lambda), GQ(lambda), and off-policy LSTD(lambda), the lambda parameter is intended to play the same role, but does not; on every exploratory action these algorithms bootstrap regardless of the value of lambda, and as a result they fail to approximate Monte Carlo learning when lambda=1. It may seem that this is inevitable for any online off-policy algorithm; if updates are made on each step on which the target policy is followed, then how could just the right updates be ‘un-made’ upon deviation from the target policy? In this paper, we introduce a new version of Q(lambda) that does exactly that, without significantly increased algorithmic complexity. En route to our new Q(lambda), we introduce a new derivation technique based on the forward-view/backward-view analysis familiar from TD(lambda) but extended to apply at every time step rather than only at the end of episodes. We apply this technique to derive first a new off-policy version of TD(lambda), called PTD(lambda), and then our new Q(lambda), called PQ(lambda).

UAI Conference 2014 Conference Paper

Off-policy TD( l) with a true online equivalence

Hado van Hasselt
A. Rupam Mahmood
Richard S. Sutton

Van Seijen and Sutton (2014) recently proposed a new version of the linear TD( ) learning algorithm that is exactly equivalent to an online forward view and that empirically performed better than its classical counterpart in both prediction and control problems. However, their algorithm is restricted to on-policy learning. In the more general case of off-policy learning, in which the policy whose outcome is predicted and the policy used to generate data may be different, their algorithm cannot be applied. One reason for this is that the algorithm bootstraps and thus is subject to instability problems when function approximation is used. A second reason true online TD( ) cannot be used for off-policy learning is that the off-policy case requires sophisticated importance sampling in its eligibility traces. To address these limitations, we generalize their equivalence result and use this generalization to construct the first online algorithm to be exactly equivalent to an off-policy forward view. We show this algorithm, named true online GTD( ), empirically outperforms GTD( ) (Maei, 2011) which was derived from the same objective as our forward view but lacks the exact online equivalence. In the general theorem that allows us to derive this new algorithm, we encounter a new general eligibility-trace update.

NeurIPS Conference 2014 Conference Paper

Weighted importance sampling for off-policy learning with linear function approximation

A. Rupam Mahmood
Hado van Hasselt
Richard Sutton

Importance sampling is an essential component of off-policy model-free reinforcement learning algorithms. However, its most effective variant, \emph{weighted} importance sampling, does not carry over easily to function approximation and, because of this, it is not utilized in existing off-policy learning algorithms. In this paper, we take two steps toward bridging this gap. First, we show that weighted importance sampling can be viewed as a special case of weighting the error of individual training samples, and that this weighting has theoretical and empirical benefits similar to those of weighted importance sampling. Second, we show that these benefits extend to a new weighted-importance-sampling version of off-policy LSTD(lambda). We show empirically that our new WIS-LSTD(lambda) algorithm can result in much more rapid and reliable convergence than conventional off-policy LSTD(lambda) (Yu 2010, Bertsekas & Yu 2009).