Enhancing Reinforcement Learning Agents with Local Guides

arXiv:2402.13930v1 Announce Type: new
Abstract: This paper addresses the problem of integrating local guide policies into a Reinforcement Learning agent. For this, we show how to adapt existing algorithms to this setting before introducing a novel algorithm based on a noisy policy-switching procedure. This approach builds on a proper Approximate Policy Evaluation (APE) scheme to provide a perturbation that carefully leads the local guides towards better actions. We evaluated our method on a set of classical Reinforcement Learning problems, including …

abstract adapt agent agents algorithm algorithms arxiv cs.lg cs.sy eess.sy evaluation guide guides novel paper policy reinforcement reinforcement learning show type