Optimal Single-Policy Sample Complexity and Transient Coverage for Average-Reward Offline RL

• URL: http://arxiv.org/abs/2506.20904v1
• Date: Thu, 26 Jun 2025 00:22:39 GMT
• Title: Optimal Single-Policy Sample Complexity and Transient Coverage for Average-Reward Offline RL
• Authors: Matthew Zurek, Guy Zamir, Yudong Chen,
• Abstract summary: We study offline reinforcement learning in average-reward MDPs, which presents increased challenges from the perspectives of distribution shift and non-uniform coverage.<n>We develop sharp guarantees depending only on the target policy, specifically the bias span and a novel policy hitting radius, yielding the first fully single-policy sample complexity bound for average-reward offline RL.
• Score: 6.224756774400233
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: We study offline reinforcement learning in average-reward MDPs, which presents increased challenges from the perspectives of distribution shift and non-uniform coverage, and has been relatively underexamined from a theoretical perspective. While previous work obtains performance guarantees under single-policy data coverage assumptions, such guarantees utilize additional complexity measures which are uniform over all policies, such as the uniform mixing time. We develop sharp guarantees depending only on the target policy, specifically the bias span and a novel policy hitting radius, yielding the first fully single-policy sample complexity bound for average-reward offline RL. We are also the first to handle general weakly communicating MDPs, contrasting restrictive structural assumptions made in prior work. To achieve this, we introduce an algorithm based on pessimistic discounted value iteration enhanced by a novel quantile clipping technique, which enables the use of a sharper empirical-span-based penalty function. Our algorithm also does not require any prior parameter knowledge for its implementation. Remarkably, we show via hard examples that learning under our conditions requires coverage assumptions beyond the stationary distribution of the target policy, distinguishing single-policy complexity measures from previously examined cases. We also develop lower bounds nearly matching our main result.

Related papers

• Convergence and Sample Complexity of First-Order Methods for Agnostic Reinforcement Learning [66.4260157478436]
  We study reinforcement learning in the policy learning setting.<n>The goal is to find a policy whose performance is competitive with the best policy in a given class of interest.
  arXiv  Detail & Related papers  (2025-07-06T14:40:05Z)
• Statistical Analysis of Policy Space Compression Problem [54.1754937830779]
  Policy search methods are crucial in reinforcement learning, offering a framework to address continuous state-action and partially observable problems. Reducing the policy space through policy compression emerges as a powerful, reward-free approach to accelerate the learning process. This technique condenses the policy space into a smaller, representative set while maintaining most of the original effectiveness.
  arXiv  Detail & Related papers  (2024-11-15T02:46:55Z)
• Bi-Level Offline Policy Optimization with Limited Exploration [1.8130068086063336]
  We study offline reinforcement learning (RL) which seeks to learn a good policy based on a fixed, pre-collected dataset. We propose a bi-level structured policy optimization algorithm that models a hierarchical interaction between the policy (upper-level) and the value function (lower-level) We evaluate our model using a blend of synthetic, benchmark, and real-world datasets for offline RL, showing that it performs competitively with state-of-the-art methods.
  arXiv  Detail & Related papers  (2023-10-10T02:45:50Z)
• Importance-Weighted Offline Learning Done Right [16.4989952150404]
  We study the problem of offline policy optimization in contextual bandit problems. The goal is to learn a near-optimal policy based on a dataset of decision data collected by a suboptimal behavior policy. We show that a simple alternative approach based on the "implicit exploration" estimator of citet2015 yields performance guarantees that are superior in nearly all possible terms to all previous results.
  arXiv  Detail & Related papers  (2023-09-27T16:42:10Z)
• Iteratively Refined Behavior Regularization for Offline Reinforcement Learning [57.10922880400715]
  In this paper, we propose a new algorithm that substantially enhances behavior-regularization based on conservative policy iteration. By iteratively refining the reference policy used for behavior regularization, conservative policy update guarantees gradually improvement. Experimental results on the D4RL benchmark indicate that our method outperforms previous state-of-the-art baselines in most tasks.
  arXiv  Detail & Related papers  (2023-06-09T07:46:24Z)
• Provable Offline Preference-Based Reinforcement Learning [95.00042541409901]
  We investigate the problem of offline Preference-based Reinforcement Learning (PbRL) with human feedback. We consider the general reward setting where the reward can be defined over the whole trajectory. We introduce a new single-policy concentrability coefficient, which can be upper bounded by the per-trajectory concentrability.
  arXiv  Detail & Related papers  (2023-05-24T07:11:26Z)
• Policy learning "without" overlap: Pessimism and generalized empirical Bernstein's inequality [94.89246810243053]
  This paper studies offline policy learning, which aims at utilizing observations collected a priori to learn an optimal individualized decision rule.<n>Existing policy learning methods rely on a uniform overlap assumption, i.e., the propensities of exploring all actions for all individual characteristics must be lower bounded.<n>We propose Pessimistic Policy Learning (PPL), a new algorithm that optimize lower confidence bounds (LCBs) instead of point estimates.
  arXiv  Detail & Related papers  (2022-12-19T22:43:08Z)
• Optimal Conservative Offline RL with General Function Approximation via Augmented Lagrangian [18.2080757218886]
  offline reinforcement learning (RL) refers to decision-making from a previously-collected dataset of interactions. We present the first set of offline RL algorithms that are statistically optimal and practical under general function approximation and single-policy concentrability.
  arXiv  Detail & Related papers  (2022-11-01T19:28:48Z)
• False Correlation Reduction for Offline Reinforcement Learning [115.11954432080749]
  We propose falSe COrrelation REduction (SCORE) for offline RL, a practically effective and theoretically provable algorithm. We empirically show that SCORE achieves the SoTA performance with 3.1x acceleration on various tasks in a standard benchmark (D4RL)
  arXiv  Detail & Related papers  (2021-10-24T15:34:03Z)
• CRPO: A New Approach for Safe Reinforcement Learning with Convergence Guarantee [61.176159046544946]
  In safe reinforcement learning (SRL) problems, an agent explores the environment to maximize an expected total reward and avoids violation of certain constraints. This is the first-time analysis of SRL algorithms with global optimal policies.
  arXiv  Detail & Related papers  (2020-11-11T16:05:14Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.