Sample Efficient Reinforcement Learning with Partial Dynamics Knowledge

arXiv:2312.12558v2 Announce Type: replace
Abstract: The problem of sample complexity of online reinforcement learning is often studied in the literature without taking into account any partial knowledge about the system dynamics that could potentially accelerate the learning process. In this paper, we study the sample complexity of online Q-learning methods when some prior knowledge about the dynamics is available or can be learned efficiently. We focus on systems that evolve according to an additive disturbance model of the form $S_{h+1} …

abstract arxiv complexity cs.lg dynamics knowledge literature math.oc online reinforcement learning paper process q-learning reinforcement reinforcement learning sample stat.ml study type