arXiv Machine Learning By Mingyi Li, Taira Tsuchiya, Kenji Yamanishi

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

Read the original on arXiv Machine Learning →

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.

Summary generated by The Flow from the publisher's feed. The full article lives at arXiv Machine Learning.

arXiv Machine Learning
Jun 3

Data- and Variance-dependent Regret Bounds for Online Tabular MDPs

arXiv:2602. 01903v2 Announce Type: replace Abstract: This work studies online episodic tabular Markov decision processes (MDPs) with known transitions and develops best-of-both-worlds algorithms that achieve refined data-dependent regret bounds in the adversarial regime and variance-dependent regret bounds in the stochastic regime.

By Mingyi Li, Taira Tsuchiya, Kenji Yamanishi