skip to main content


This content will become publicly available on May 1, 2025

Title: Single-Trajectory Distributionally Robust Reinforcement Learning
To mitigate the limitation that the classical reinforcement learning (RL) framework heavily relies on identical training and test environments, Distributionally Robust RL (DRRL) has been proposed to enhance performance across a range of environments, possibly including unknown test environments. As a price for robustness gain, DRRL involves optimizing over a set of distributions, which is inherently more challenging than optimizing over a fixed distribution in the non-robust case. Existing DRRL algorithms are either model-based or fail to learn from a single sample trajectory. In this paper, we design a first fully model-free DRRL algorithm, called distributionally robust Q-learning with single trajectory (DRQ). We delicately design a multi-timescale framework to fully utilize each incrementally arriving sample and directly learn the optimal distributionally robust policy without modeling the environment, thus the algorithm can be trained along a single trajectory in a model-free fashion. Despite the algorithm's complexity, we provide asymptotic convergence guarantees by generalizing classical stochastic approximation tools. Comprehensive experimental results demonstrate the superior robustness and sample complexity of our proposed algorithm, compared to non-robust methods and other robust RL algorithms.  more » « less
Award ID(s):
2312204
PAR ID:
10529077
Author(s) / Creator(s):
; ; ; ; ;
Corporate Creator(s):
Editor(s):
Salakhutdinov, Ruslan; Kolter, Zico; Heller, Katherine; Weller, Adrian; Oliver, Nuria; Scarlett, Jonathan; Berkenkamp, Felix
Publisher / Repository:
Proceedings of the 41 International Conference on Machine Learning
Date Published:
Volume:
235
Page Range / eLocation ID:
29644-29666
Subject(s) / Keyword(s):
Proceedings of the 41st International Conference on Machine Learning, PMLR 235:29644-29666, 2024.
Format(s):
Medium: X
Location:
https://raw.githubusercontent.com/mlresearch/v235/main/assets/liang24d/liang24d.pdf
Sponsoring Org:
National Science Foundation
More Like this
  1. Salakhutdinov, Ruslan ; Kolter, Zico ; Heller, Katherine ; Weller, Adrian ; Oliver, Nuria ; Scarlett, Jonathan ; Berkenkamp, Felix (Ed.)
    To mitigate the limitation that the classical reinforcement learning (RL) framework heavily relies on identical training and test environments, Distributionally Robust RL (DRRL) has been proposed to enhance performance across a range of environments, possibly including unknown test environments. As a price for robustness gain, DRRL involves optimizing over a set of distributions, which is inherently more challenging than optimizing over a fixed distribution in the non-robust case. Existing DRRL algorithms are either model-based or fail to learn from a single sample trajectory. In this paper, we design a first fully model-free DRRL algorithm, called distributionally robust Q-learning with single trajectory (DRQ). We delicately design a multi-timescale framework to fully utilize each incrementally arriving sample and directly learn the optimal distributionally robust policy without modeling the environment, thus the algorithm can be trained along a single trajectory in a model-free fashion. Despite the algorithm’s complexity, we provide asymptotic convergence guarantees by generalizing classical stochastic approximation tools. Comprehensive experimental results demonstrate the superior robustness and sample complexity of our proposed algorithm, compared to non-robust methods and other robust RL algorithms. 
    more » « less
  2. To mitigate the limitation that the classical reinforcement learning (RL) framework heavily relies on identical training and test environments, Distributionally Robust RL (DRRL) has been proposed to enhance performance across a range of environments, possibly including unknown test environments. As a price for robustness gain, DRRL involves optimizing over a set of distributions, which is inherently more challenging than optimizing over a fixed distribution in the non-robust case. Existing DRRL algorithms are either model-based or fail to learn from a single sample trajectory. In this paper, we design a first fully model-free DRRL algorithm, called distributionally robust Q-learning with single trajectory (DRQ). We delicately design a multi-timescale framework to fully utilize each incrementally arriving sample and directly learn the optimal distributionally robust policy without modeling the environment, thus the algorithm can be trained along a single trajectory in a model-free fashion. Despite the algorithm's complexity, we provide asymptotic convergence guarantees by generalizing classical stochastic approximation tools.Comprehensive experimental results demonstrate the superior robustness and sample complexity of our proposed algorithm, compared to non-robust methods and other robust RL algorithms. @inproceedings{ liang2024singletrajectory, title={Single-Trajectory Distributionally Robust Reinforcement Learning}, author={Zhipeng Liang and Xiaoteng Ma and Jose Blanchet and Jun Yang and Jiheng Zhang and Zhengyuan Zhou}, booktitle={Forty-first International Conference on Machine Learning}, year={2024}, url={https://openreview.net/forum?id=3B6vmW2L80} } 
    more » « less
  3. Banerjee, Arindam and (Ed.)
    While reinforcement learning has witnessed tremendous success recently in a wide range of domains, robustness–or the lack thereof–remains an important issue that remains inadequately addressed. In this paper, we provide a distributionally robust formulation of offline learning policy in tabular RL that aims to learn a policy from historical data (collected by some other behavior policy) that is robust to the future environment arising as a perturbation of the training environment. We first develop a novel policy evaluation scheme that accurately estimates the robust value (i.e. how robust it is in a perturbed environment) of any given policy and establish its finite-sample estimation error. Building on this, we then develop a novel and minimax-optimal distributionally robust learning algorithm that achieves $O_P\left(1/\sqrt{n}\right)$ regret, meaning that with high probability, the policy learned from using $n$ training data points will be $O\left(1/\sqrt{n}\right)$ close to the optimal distributionally robust policy. Finally, our simulation results demonstrate the superiority of our distributionally robust approach compared to non-robust RL algorithms. 
    more » « less
  4. Chaudhuri, Kamalika ; Jegelka, Stefanie ; Song, Le ; Szepesvari, Csaba ; Niu, Gang ; Sabato, Sivan (Ed.)
    Reinforcement learning (RL) has demonstrated remarkable achievements in simulated environments. However, carrying this success to real environments requires the important attribute of robustness, which the existing RL algorithms often lack as they assume that the future deployment environment is the same as the training environment (i.e. simulator) in which the policy is learned. This assumption often does not hold due to the discrepancy between the simulator and the real environment and, as a result, and hence renders the learned policy fragile when deployed. In this paper, we propose a novel distributionally robust Q-learning algorithm that learns the best policy in the worst distributional perturbation of the environment. Our algorithm first transforms the infinite-dimensional learning problem (since the environment MDP perturbation lies in an infinite-dimensional space) into a finite-dimensional dual problem and subsequently uses a multi-level Monte-Carlo scheme to approximate the dual value using samples from the simulator. Despite the complexity, we show that the resulting distributionally robust Q-learning algorithm asymptotically converges to optimal worst-case policy, thus making it robust to future environment changes. Simulation results further demonstrate its strong empirical robustness. 
    more » « less
  5. Offline or batch reinforcement learning seeks to learn a near-optimal policy using history data without active exploration of the environment. To counter the insufficient coverage and sample scarcity of many offline datasets, the principle of pessimism has been recently introduced to mitigate high bias of the estimated values. While pessimistic variants of model-based algorithms (e.g., value iteration with lower confidence bounds) have been theoretically investigated, their model-free counterparts — which do not require explicit model estimation — have not been adequately studied, especially in terms of sample efficiency. To address this inadequacy, we study a pessimistic variant of Q-learning in the context of finite-horizon Markov decision processes, and characterize its sample complexity under the single-policy concentrability assumption which does not require the full coverage of the state-action space. In addition, a variance-reduced pessimistic Q-learning algorithm is proposed to achieve near-optimal sample complexity. Altogether, this work highlights the efficiency of model-free algorithms in offline RL when used in conjunction with pessimism and variance reduction. 
    more » « less