Improved Algorithm for Adversarial Linear Mixture MDPs with Bandit Feedback and Unknown Transition

arXiv:2403.04568v1 Announce Type: new
Abstract: We study reinforcement learning with linear function approximation, unknown transition, and adversarial losses in the bandit feedback setting. Specifically, we focus on linear mixture MDPs whose transition kernel is a linear mixture model. We propose a new algorithm that attains an $\widetilde{O}(d\sqrt{HS^3K} + \sqrt{HSAK})$ regret with high probability, where $d$ is the dimension of feature mappings, $S$ is the size of state space, $A$ is the size of action space, $H$ is the episode length …

abstract adversarial algorithm approximation arxiv cs.lg feedback focus function kernel linear losses reinforcement reinforcement learning stat.ml study transition type