We study offline reinforcement learning (RL) with linear MDPs under the infinite-horizon discounted setting which aims to learn a policy that maximizes the expected discounted cumulative reward using a pre-collected dataset. Existing algorithms for this setting either require a uniform data coverage assumptions or are computationally inefficient for finding an $ε$-optimal policy with $O(ε^{-2})$ sample complexity. In this paper, we propose a primal dual algorithm for offline RL with linear MDPs in the infinite-horizon discounted setting. Our algorithm is the first computationally efficient algorithm in this setting that achieves sample complexity of $O(ε^{-2})$ with partial data coverage assumption. Our work is an improvement upon a recent work that requires $O(ε^{-4})$ samples. Moreover, we extend our algorithm to work in the offline constrained RL setting that enforces constraints on additional reward signals.
We propose a new stochastic primal-dual optimization algorithm for planning in a large discounted Markov decision process with a generative model and linear function approximation. Assuming that the feature map approximately satisfies standard realizability and Bellman-closedness conditions and also that the feature vectors of all state-action pairs are representable as convex combinations of a small core set of state-action pairs, we show that our method outputs a near-optimal policy after a polynomial number of queries to the generative model. Our method is computationally efficient and come…
A Policy Gradient Primal-Dual Algorithm for Constrained MDPs with Uniform PAC Guarantees
The University of Tokyo（东京大学）；OMRON SINIC X（欧姆龙SINIC X公司）；Mizuho–DL Financial Technology（瑞穗-DL金融科技公司）；Nara Institute of Science and Technology（奈良先端科学技术大学院大学）；RIKEN Center for Advanced Intelligence Project（理化学研究所革新智能综合研究中心）；Osaka University（大阪大学）；Kyoto University（京都大学）
This work studies the question of Representation Learning in RL: how can we learn a compact low-dimensional representation such that on top of the representation we can perform RL procedures such as exploration and exploitation, in a sample efficient manner. We focus on the low-rank Markov Decision Processes (MDPs) where the transition dynamics correspond to a low-rank transition matrix. Unlike prior works that assume the representation is known (e.g., linear MDPs), here we need to learn the representation for the low-rank MDP. We study both the online RL and offline RL settings. For the onlin…
Convergence and sample complexity of natural policy gradient primal-dual methods for constrained MDPs
University of Tennessee, Knoxville（田纳西大学）；University of Maryland, College Park（马里兰大学）；Apple Inc.（苹果公司）；University of Illinois Urbana-Champaign（伊利诺伊大学厄巴纳-香槟分校）；University of Southern California（南加州大学）
UC Santa Barbara（加州大学圣巴巴拉分校）；Salesforce Research（Salesforce研究院）
We consider the problem of offline reinforcement learning (RL) -- a well-motivated setting of RL that aims at policy optimization using only historical data. Despite its wide applicability, theoretical understandings of offline RL, such as its optimal sample complexity, remain largely open even in basic settings such as \emph{tabular} Markov Decision Processes (MDPs). In this paper, we propose Off-Policy Double Variance Reduction (OPDVR), a new variance reduction based algorithm for offline RL. Our main result shows that OPDVR provably identifies an $ε$-optimal policy with $\widetilde{O}(H^2/d…
McGill University（麦吉尔大学）；Mila；University of Massachusetts（马萨诸塞大学）；Facebook AI Research（Facebook人工智能研究院）；Microsoft Research（微软研究院）
We study the problem of Safe Policy Improvement (SPI) under constraints in the offline Reinforcement Learning (RL) setting. We consider the scenario where: (i) we have a dataset collected under a known baseline policy, (ii) multiple reward signals are received from the environment inducing as many objectives to optimize. We present an SPI formulation for this RL setting that takes into account the preferences of the algorithm's user for handling the trade-offs for different reward signals while ensuring that the new policy performs at least as well as the baseline policy along each individual …
We address the problem of finding the optimal policy of a constrained Markov decision process (CMDP) using a gradient descent-based algorithm. Previous results have shown that a primal-dual approach can achieve an $\mathcal{O}(1/\sqrt{T})$ global convergence rate for both the optimality gap and the constraint violation. We propose a new algorithm called policy mirror descent-primal dual (PMD-PD) algorithm that can provably achieve a faster $\mathcal{O}(\log(T)/T)$ convergence rate for both the optimality gap and the constraint violation. For the primal (policy) update, the PMD-PD algorithm uti…
Near-Optimal Regret for Policy Optimization in Contextual MDPs with General Offline Function Approximation
Department of XXX, University of YYY, Location, Country；School of ZZZ, Institute of WWW, Location, Country；Blavatnik School of Computer Science, Tel Aviv University；Google Research；School of Electrical Engineering, Tel Aviv University
We address the issue of safety in reinforcement learning. We pose the problem in an episodic framework of a constrained Markov decision process. Existing results have shown that it is possible to achieve a reward regret of $\tilde{\mathcal{O}}(\sqrt{K})$ while allowing an $\tilde{\mathcal{O}}(\sqrt{K})$ constraint violation in $K$ episodes. A critical question that arises is whether it is possible to keep the constraint violation even smaller. We show that when a strictly safe policy is known, then one can confine the system to zero constraint violation with arbitrarily high probability while …
Princeton University（普林斯顿大学）；Peking University（北京大学）；University of Illinois Urbana-Champaign（伊利诺伊大学厄巴纳-香槟分校）
Sample-efficiency guarantees for offline reinforcement learning (RL) often rely on strong assumptions on both the function classes (e.g., Bellman-completeness) and the data coverage (e.g., all-policy concentrability). Despite the recent efforts on relaxing these assumptions, existing works are only able to relax one of the two factors, leaving the strong assumption on the other factor intact. As an important open problem, can we achieve sample-efficient offline RL with weak assumptions on both factors? In this paper we answer the question in the positive. We analyze a simple algorithm based on…
A Unified Algorithmic Framework for Hybrid Reinforcement Learning in Tabular MDPs with Shifted Transition Dynamics
Southern University of Science and Technology（南方科技大学）；Harbin Institute of Technology, Shenzhen（哈尔滨工业大学（深圳））；City University of Hong Kong（香港城市大学）；Fudan University（复旦大学）；Shanghai Academy of AI for Science（上海人工智能研究院）
The Hong Kong University of Science Technology（香港科技大学）；Peking University（北京大学）；University of Virginia（弗吉尼亚大学）
Offline reinforcement learning (RL) aims at learning an optimal strategy using a pre-collected dataset without further interactions with the environment. While various algorithms have been proposed for offline RL in the previous literature, the minimax optimality has only been (nearly) established for tabular Markov decision processes (MDPs). In this paper, we focus on offline RL with linear function approximation and propose a new pessimism-based algorithm for offline linear MDP. At the core of our algorithm is the uncertainty decomposition via a reference function, which is new in the litera…
Peking University（北京大学）；National University of Singapore（新加坡国立大学）；Beijing International Center for Mathematical Research（北京国际数学研究中心）
As an important framework for safe Reinforcement Learning, the Constrained Markov Decision Process (CMDP) has been extensively studied in the recent literature. However, despite the rich results under various on-policy learning settings, there still lacks some essential understanding of the offline CMDP problems, in terms of both the algorithm design and the information theoretic sample complexity lower bound. In this paper, we focus on solving the CMDP problems where only offline data are available. By adopting the concept of the single-policy concentrability coefficient $C^*$, we establish a…
Technion（以色列理工学院）；Facebook AI Research（Facebook人工智能研究院）
In many sequential decision-making problems, the goal is to optimize a utility function while satisfying a set of constraints on different utilities. This learning problem is formalized through Constrained Markov Decision Processes (CMDPs). In this paper, we investigate the exploration-exploitation dilemma in CMDPs. While learning in an unknown CMDP, an agent should trade-off exploration to discover new information about the MDP, and exploitation of the current knowledge to maximize the reward while satisfying the constraints. While the agent will eventually learn a good or optimal policy, we …
We present a unified framework based on primal-dual stochastic mirror descent for approximately solving infinite-horizon Markov decision processes (MDPs) given a generative model. When applied to an average-reward MDP with $A_{tot}$ total state-action pairs and mixing time bound $t_{mix}$ our method computes an $ε$-optimal policy with an expected $\widetilde{O}(t_{mix}^2 A_{tot} ε^{-2})$ samples from the state-transition matrix, removing the ergodicity dependence of prior art. When applied to a $γ$-discounted MDP with $A_{tot}$ total state-action pairs our method computes an $ε$-optimal policy…
Robust Markov Decision Processes (MDPs) are a powerful framework for modeling sequential decision-making problems with model uncertainty. This paper proposes the first first-order framework for solving robust MDPs. Our algorithm interleaves primal-dual first-order updates with approximate Value Iteration updates. By carefully controlling the tradeoff between the accuracy and cost of Value Iteration updates, we achieve an ergodic convergence rate of $O \left( A^{2} S^{3}\log(S)\log(ε^{-1}) ε^{-1} \right)$ for the best choice of parameters on ellipsoidal and Kullback-Leibler $s$-rectangular unce…
We study the problem of learning policy of an infinite-horizon, discounted cost, Markov decision process (MDP) with a large number of states. We compute the actions of a policy that is nearly as good as a policy chosen by a suitable oracle from a given mixture policy class characterized by the convex hull of a set of known base policies. To learn the coefficients of the mixture model, we recast the problem as an approximate linear programming (ALP) formulation for MDPs, where the feature vectors correspond to the occupation measures of the base policies defined on the state-action space. We th…
Microsoft Research（微软研究院）；University of Toronto（多伦多大学）；Hamilton Health Sciences（汉密尔顿健康科学中心）；Population Health Research Institute（人口健康研究所）；Duke University（杜克大学）；Massachusetts Institute of Technology（麻省理工学院）
Reinforcement learning (RL) tasks are typically framed as Markov Decision Processes (MDPs), assuming that decisions are made at fixed time intervals. However, many applications of great importance, including healthcare, do not satisfy this assumption, yet they are commonly modelled as MDPs after an artificial reshaping of the data. In addition, most healthcare (and similar) problems are offline by nature, allowing for only retrospective studies. To address both challenges, we begin by discussing the Semi-MDP (SMDP) framework, which formally handles actions of variable timings. We next present …
Simon Fraser University（西蒙弗雷泽大学）；SAIT AI Lab（SAIT人工智能实验室）；Amii（阿尔伯塔机器智能研究所）；University of Alberta（阿尔伯塔大学）；DeepMind（深度思维）；Mila（米拉人工智能研究所）；McGill University（麦吉尔大学）
We study policy optimization in an infinite horizon, $γ$-discounted constrained Markov decision process (CMDP). Our objective is to return a policy that achieves large expected reward with a small constraint violation. We consider the online setting with linear function approximation and assume global access to the corresponding features. We propose a generic primal-dual framework that allows us to bound the reward sub-optimality and constraint violation for arbitrary algorithms in terms of their primal and dual regret on online linear optimization problems. We instantiate this framework to us…
Northwestern University（西北大学）；George Washington University（乔治华盛顿大学）；Yale University（耶鲁大学）；Johns Hopkins University（约翰斯·霍普金斯大学）；University of North Carolina at Chapel Hill（北卡罗来纳大学教堂山分校）
We study the offline reinforcement learning (RL) in the face of unmeasured confounders. Due to the lack of online interaction with the environment, offline RL is facing the following two significant challenges: (i) the agent may be confounded by the unobserved state variables; (ii) the offline data collected a prior does not provide sufficient coverage for the environment. To tackle the above challenges, we study the policy learning in the confounded MDPs with the aid of instrumental variables. Specifically, we first establish value function (VF)-based and marginalized importance sampling (MIS…
University of Michigan（密歇根大学）；University of Southern California（南加州大学）；Princeton University（普林斯顿大学）；Northwestern University（西北大学）
We consider online learning for episodic stochastically constrained Markov decision processes (CMDPs), which plays a central role in ensuring the safety of reinforcement learning. Here the loss function can vary arbitrarily across the episodes, and both the loss received and the budget consumption are revealed at the end of each episode. Previous works solve this problem under the restrictive assumption that the transition model of the Markov decision processes (MDPs) is known a priori and establish regret bounds that depend polynomially on the cardinalities of the state space $\mathcal{S}$ an…
University of Illinois Urbana-Champaign（伊利诺伊大学厄巴纳-香槟分校）
MDPs with low-rank transitions -- that is, the transition matrix can be factored into the product of two matrices, left and right -- is a highly representative structure that enables tractable learning. The left matrix enables expressive function approximation for value-based learning and has been studied extensively. In this work, we instead investigate sample-efficient learning with density features, i.e., the right matrix, which induce powerful models for state-occupancy distributions. This setting not only sheds light on leveraging unsupervised learning in RL, but also enables plug-in solu…
Stanford University（斯坦福大学）；Princeton University（普林斯顿大学）；Northwestern University（西北大学）；Simons Institute for the Theory of Computing（西蒙斯计算理论研究所）
We study offline reinforcement learning (RL), which aims to learn an optimal policy based on a dataset collected a priori. Due to the lack of further interactions with the environment, offline RL suffers from the insufficient coverage of the dataset, which eludes most existing theoretical analysis. In this paper, we propose a pessimistic variant of the value iteration algorithm (PEVI), which incorporates an uncertainty quantifier as the penalty function. Such a penalty function simply flips the sign of the bonus function for promoting exploration in online RL, which makes it easily implementab…
Hong Kong University of Science and Technology（香港科技大学）；Tsinghua University（清华大学）；Northwestern University（西北大学）；Tencent Robotics X（腾讯Robotics X实验室）；Shanghai AI Laboratory（上海人工智能实验室）
Offline reinforcement learning (RL) provides a promising direction to exploit massive amount of offline data for complex decision-making tasks. Due to the distribution shift issue, current offline RL algorithms are generally designed to be conservative in value estimation and action selection. However, such conservatism can impair the robustness of learned policies when encountering observation deviation under realistic conditions, such as sensor errors and adversarial attacks. To trade off robustness and conservatism, we propose Robust Offline Reinforcement Learning (RORL) with a novel conser…
University of Illinois at Urbana-Champaign（伊利诺伊大学厄巴纳-香槟分校）；Salesforce Research（Salesforce研究院）
Recent theoretical work studies sample-efficient reinforcement learning (RL) extensively in two settings: learning interactively in the environment (online RL), or learning from an offline dataset (offline RL). However, existing algorithms and theories for learning near-optimal policies in these two settings are rather different and disconnected. Towards bridging this gap, this paper initiates the theoretical study of policy finetuning, that is, online RL where the learner has additional access to a "reference policy" $μ$ close to the optimal policy $π_\star$ in a certain sense. We consider th…
Off-Policy Evaluation for Missingness-Aware Policies in MDPs with Rewards Missing Not at Random
Department of Statistics, University of Michigan at Ann Arbor（密歇根大学安娜堡分校统计学系）；Department of Statistics（统计学系）；Applied Probability, University of California at Santa Barbara（加州大学圣巴巴拉分校应用概率系）；Department of Mathematical Sciences, University of Texas at Dallas（德克萨斯大学达拉斯分校数学科学系）
