arXiv Machine Learning November 2, 2026 By Yuxin Chen, Yuejie Chi, Jianqing Fan, Gen Li, Yuting Wei, Yuling Yan

Statistical Foundations of Reinforcement Learning: A Non-Asymptotic Perspective

Read the original on arXiv Machine Learning →

The monograph "Statistical Foundations of Reinforcement Learning: A Non-Asymptotic Perspective" surveys recent advances in finite-sample statistical theory for reinforcement learning. It focuses on tabular Markov decision processes and examines three sampling settings—generative model, online, and offline RL—alongside model-based and model-free algorithmic paradigms. The work emphasizes minimax-optimal sample complexity, provides self-contained analyses, and briefly explores extensions such as robust, multi-agent, federated, and human-feedback RL.

Machine-generated by The Flow from the publisher's headline and feed description — not written or checked by a human. The full article lives at arXiv Machine Learning.

arXiv AI

Jun 9

On the Complexity of Offline Reinforcement Learning with $Q^\star$-Approximation and Partial Coverage

arXiv:2602. 12107v2 Announce Type: replace-cross Abstract: We study offline reinforcement learning under $Q^\star$-approximation and partial coverage, a setting that motivates practical algorithms such as Conservative $Q$-Learning (CQL; Kumar et al.

By Haolin Liu, Braham Snyder, Chen-Yu Wei

reinforcement-learning

arXiv Machine Learning

Jul 21

Non-Asymptotic Best Policy Identification Guarantees in Online Reinforcement Learning

arXiv:2607. 17201v1 Announce Type: cross Abstract: In this work we study the Best Policy Identification (BPI) problem in online, tabular Reinforcement Learning.

By Joseph Lazzaro, Alessio Russo, Aldo Pacchiano

agents reinforcement-learning

arXiv Machine Learning

Jun 25

Auto-exploration for online reinforcement learning

arXiv:2512. 06244v2 Announce Type: replace Abstract: The exploration-exploitation dilemma in reinforcement learning (RL) is a fundamental challenge to efficient RL algorithms.

By Caleb Ju, Guanghui Lan

reinforcement-learning

arXiv AI

Jun 10

Model-Based Reinforcement Learning in Discrete-Action Non-Markovian Reward Decision Processes

arXiv:2512. 14617v2 Announce Type: replace-cross Abstract: Many practical decision-making problems involve tasks whose success depends on the entire system history, rather than on achieving a state with desired properties.

By Alessandro Trapasso, Luca Iocchi, Fabio Patrizi

agents reinforcement-learning benchmarks

arXiv Machine Learning

Jun 16

Fast Non-Episodic Finite-Horizon RL with K-Step Lookahead Thresholding

arXiv:2602. 00781v2 Announce Type: replace Abstract: Online reinforcement learning in non-episodic, finite-horizon MDPs remains underexplored and is challenged by the need to estimate returns to a fixed terminal time.

By Jiamin Xu, Kyra Gan

reinforcement-learning benchmarks

arXiv AI

Oct 27

Provably Efficient Q-learning for Robust Reinforcement Learning

The paper introduces a sample‑efficient asynchronous Q‑learning algorithm for robust reinforcement learning in infinite‑horizon, discounted robust MDPs with total‑variation uncertainty. It proves that, given a single Markovian trajectory, the algorithm achieves an entrywise ε‑approximation of the optimal Q‑function with a sample complexity bounded by a nearly minimax‑optimal expression involving the discount factor, uncertainty level, mixing time, and occupancy probability. This result improves significantly over prior bounds for robust RL.

By Yuchen Jiao, Gen Li

agents reinforcement-learning robotics

One email a morning, machine-written

Related stories

On the Complexity of Offline Reinforcement Learning with $Q^\star$-Approximation and Partial Coverage

Non-Asymptotic Best Policy Identification Guarantees in Online Reinforcement Learning

Auto-exploration for online reinforcement learning

Model-Based Reinforcement Learning in Discrete-Action Non-Markovian Reward Decision Processes

Fast Non-Episodic Finite-Horizon RL with K-Step Lookahead Thresholding

Provably Efficient Q-learning for Robust Reinforcement Learning