skip to main content

Title: Finite-Sample Regret Bound for Distributionally Robust Offline Tabular Reinforcement Learning
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
Award ID(s):
Author(s) / Creator(s):
Banerjee, Arindam and
Date Published:
Journal Name:
Proceedings of The 24th International Conference on Artificial Intelligence and Statistics
Page Range / eLocation ID:
Medium: X
Sponsoring Org:
National Science Foundation
More Like this
  1. We study the \emph{offline reinforcement learning} (offline RL) problem, where the goal is to learn a reward-maximizing policy in an unknown \emph{Markov Decision Process} (MDP) using the data coming from a policy $\mu$. In particular, we consider the sample complexity problems of offline RL for the finite horizon MDPs. Prior works derive the information-theoretical lower bounds based on different data-coverage assumptions and their upper bounds are expressed by the covering coefficients which lack the explicit characterization of system quantities. In this work, we analyze the \emph{Adaptive Pessimistic Value Iteration} (APVI) algorithm and derive the suboptimality upper bound that nearly matches $ O\left(\sum_{h=1}^H\sum_{s_h,a_h}d^{\pi^\star}_h(s_h,a_h)\sqrt{\frac{\mathrm{Var}_{P_{s_h,a_h}}{(V^\star_{h+1}+r_h)}}{d^\mu_h(s_h,a_h)}}\sqrt{\frac{1}{n}}\right). $ We also prove an information-theoretical lower bound to show this quantity is required under the weak assumption that $d^\mu_h(s_h,a_h)>0$ if $d^{\pi^\star}_h(s_h,a_h)>0$. Here $\pi^\star$ is a optimal policy, $\mu$ is the behavior policy and $d(s_h,a_h)$ is the marginal state-action probability. We call this adaptive bound the \emph{intrinsic offline reinforcement learning bound} since it directly implies all the existing optimal results: minimax rate under uniform data-coverage assumption, horizon-free setting, single policy concentrability, and the tight problem-dependent results. Later, we extend the result to the \emph{assumption-free} regime (where we make no assumption on $ \mu$) and obtain the assumption-free intrinsic bound. Due to its generic form, we believe the intrinsic bound could help illuminate what makes a specific problem hard and reveal the fundamental challenges in offline RL. 
    more » « less
  2. 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
  3. Prompting has shown impressive success in enabling large pre-trained language models (LMs) to perform diverse NLP tasks, especially with only few downstream data. Automatically finding the optimal prompt for each task, however, is challenging. Most existing work resorts to tuning *soft* prompts (e.g., embeddings) which fall short of interpretability, reusability across LMs, and applicability when gradients are not accessible. *Discrete* prompts, on the other hand, are difficult to optimize, and are often created by “enumeration (e.g., paraphrasing)-then-selection” heuristics that do not explore the prompt space systematically. This paper proposes RLPrompt, an efficient discrete prompt optimization approach with reinforcement learning (RL). RLPrompt formulates a parameter-efficient policy network that generates the optimized discrete prompt after training with reward. To harness the complex and stochastic reward signals from the large LM environment, we incorporate effective reward stabilization that substantially enhances training efficiency. RLPrompt is flexibly applicable to different types of LMs, such as masked (e.g., BERT) and left-to-right models (e.g., GPTs), for both classification and generation tasks. Experiments on few-shot classification and unsupervised text style transfer show superior performance over a wide range of existing fine-tuning or prompting methods. Interestingly, the resulting optimized prompts are often ungrammatical gibberish text; and surprisingly, those gibberish prompts are transferrable between different LMs to retain significant performance, indicating that LM prompting may not follow human language patterns. 
    more » « less
  4. We consider the imitation learning problem of learning a policy in a Markov Decision Process (MDP) setting where the reward function is not given, but demonstrations from experts are available. Although the goal of imitation learning is to learn a policy that produces behaviors nearly as good as the experts’ for a desired task, assumptions of consistent optimality for demonstrated behaviors are often violated in practice. Finding a policy that is distributionally robust against noisy demonstrations based on an adversarial construction potentially solves this problem by avoiding optimistic generalizations of the demonstrated data. This paper studies Distributionally Robust Imitation Learning (DRoIL) and establishes a close connection between DRoIL and Maximum Entropy Inverse Reinforcement Learning. We show that DRoIL can be seen as a framework that maximizes a generalized concept of entropy. We develop a novel approach to transform the objective function into a convex optimization problem over a polynomial number of variables for a class of loss functions that are additive over state and action spaces. Our approach lets us optimize both stationary and non-stationary policies and, unlike prevalent previous methods, it does not require repeatedly solving an inner reinforcement learning problem. We experimentally show the significant benefits of DRoIL’s new optimization method on synthetic data and a highway driving environment. 
    more » « less
  5. We study model-free reinforcement learning (RL) algorithms for infinite-horizon average-reward Markov decision process (MDP), which is more appropriate for applications that involve continuing operations not divided into episodes. In contrast to episodic/discounted MDPs, theoretical understanding of model-free RL algorithms is relatively inadequate for the average-reward setting. In this paper, we consider both the online setting and the setting with access to a simulator. We develop computationally efficient model-free algorithms that achieve sharper guarantees on regret/sample complexity compared with existing results. In the online setting, we design an algorithm, UCB-AVG, based on an optimistic variant of variance-reduced Q-learning. We show that UCB-AVG achieves a regret bound $\widetilde{O}(S^5A^2sp(h^*)\sqrt{T})$ after $T$ steps, where $S\times A$ is the size of state-action space, and $sp(h^*)$ the span of the optimal bias function. Our result provides the first computationally efficient model-free algorithm that achieves the optimal dependence in $T$ (up to log factors) for weakly communicating MDPs, which is necessary for low regret. In contrast, prior results either are suboptimal in $T$ or require strong assumptions of ergodicity or uniformly mixing of MDPs. In the simulator setting, we adapt the idea of UCB-AVG to develop a model-free algorithm that finds an $\epsilon$-optimal policy with sample complexity $\widetilde{O}(SAsp^2(h^*)\epsilon^{-2} + S^2Asp(h^*)\epsilon^{-1}).$ This sample complexity is near-optimal for weakly communicating MDPs, in view of the minimax lower bound $\Omega(SAsp(^*)\epsilon^{-2})$. Existing work mainly focuses on ergodic MDPs and the results typically depend on $t_{mix},$ the worst-case mixing time induced by a policy. We remark that the diameter $D$ and mixing time $t_{mix}$ are both lower bounded by $sp(h^*)$, and $t_{mix}$ can be arbitrarily large for certain MDPs. On the technical side, our approach integrates two key ideas: learning an $\gamma$-discounted MDP as an approximation, and leveraging reference-advantage decomposition for variance in optimistic Q-learning. As recognized in prior work, a naive approximation by discounted MDPs results in suboptimal guarantees. A distinguishing feature of our method is maintaining estimates of value-difference between state pairs to provide a sharper bound on the variance of reference advantage. We also crucially use a careful choice of the discounted factor $\gamma$ to balance approximation error due to discounting and the statistical learning error, and we are able to maintain a good-quality reference value function with $O(SA)$ space complexity. 
    more » « less