arXiv Machine Learning June 3, 2026 By Harin Lee, Kevin Jamieson

Minimax Optimal Strategy for Delayed Observations in Online Reinforcement Learning

Read the original on arXiv Machine Learning →

arXiv:2603. 03480v2 Announce Type: replace Abstract: We study reinforcement learning with delayed state observation, where the agent observes the current state after some random number of time steps.

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 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 11

Reinforcement Learning with Action-Triggered Observations

arXiv:2510. 02149v2 Announce Type: replace Abstract: We introduce Action-Triggered Sporadically Traceable Markov Decision Processes (ATST-MDPs), a reinforcement learning framework for partial observability in which full state observations occur stochastically at each step, with probability determined by the chosen action.

By Alexander Ryabchenko, Wenlong Mou

agents reinforcement-learning

arXiv Machine Learning

Jul 1

Policy Optimization Achieves Data-Dependent Regret Bounds in MDPs with Unknown Transitions

arXiv:2606. 31769v1 Announce Type: new Abstract: We study policy optimization for online episodic tabular Markov decision processes with unknown transition kernels, aiming for best-of-both-worlds guarantees together with data-dependent regret bounds.

By Mingyi Li, Taira Tsuchiya, Kenji Yamanishi

reinforcement-learning safety

arXiv Machine Learning

Jun 2

Online Learning in MDPs with Partially Adversarial Transitions and Losses

arXiv:2602. 09474v2 Announce Type: replace Abstract: We study reinforcement learning in MDPs whose transition function is stochastic at most steps but may behave adversarially at a fixed subset of $\Lambda$ steps per episode.

By Ofir Schlisselberg, Tal Lancewicki, Yishay Mansour

reinforcement-learning safety

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 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

One email a morning, machine-written

Related stories

Non-Asymptotic Best Policy Identification Guarantees in Online Reinforcement Learning

Reinforcement Learning with Action-Triggered Observations

Policy Optimization Achieves Data-Dependent Regret Bounds in MDPs with Unknown Transitions

Online Learning in MDPs with Partially Adversarial Transitions and Losses

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

Auto-exploration for online reinforcement learning