Optimistic Regret Bounds for Online Learning in Adversarial Markov Decision Processes

arXiv:2405.02188v1 Announce Type: cross
Abstract: The Adversarial Markov Decision Process (AMDP) is a learning framework that deals with unknown and varying tasks in decision-making applications like robotics and recommendation systems. A major limitation of the AMDP formalism, however, is pessimistic regret analysis results in the sense that although the cost function can change from one episode to the next, the evolution in many settings is not adversarial. To address this, we introduce and study a new variant of AMDP, which …

abstract adversarial analysis applications arxiv cs.ai cs.lg deals decision framework however major making markov online learning process processes recommendation recommendation systems results robotics sense stat.ml systems tasks type