Contrastive UCB: Provably Efficient Contrastive Self-Supervised Learning in Online Reinforcement Learning

arXiv:2207.14800v2 Announce Type: replace
Abstract: In view of its power in extracting feature representation, contrastive self-supervised learning has been successfully integrated into the practice of (deep) reinforcement learning (RL), leading to efficient policy learning in various applications. Despite its tremendous empirical successes, the understanding of contrastive learning for RL remains elusive. To narrow such a gap, we study how RL can be empowered by contrastive learning in a class of Markov decision processes (MDPs) and Markov games (MGs) with low-rank …

arxiv cs.lg online reinforcement learning reinforcement reinforcement learning self-supervised learning stat.ml supervised learning type