Scale-free Adversarial Reinforcement Learning

arXiv:2403.00930v1 Announce Type: new
Abstract: This paper initiates the study of scale-free learning in Markov Decision Processes (MDPs), where the scale of rewards/losses is unknown to the learner. We design a generic algorithmic framework, \underline{S}cale \underline{C}lipping \underline{B}ound (\texttt{SCB}), and instantiate this framework in both the adversarial Multi-armed Bandit (MAB) setting and the adversarial MDP setting. Through this framework, we achieve the first minimax optimal expected regret bound and the first high-probability regret bound in scale-free adversarial MABs, resolving an open …

abstract adversarial arxiv cs.ai cs.lg decision design framework free losses markov paper processes reinforcement reinforcement learning scale study through type