Dr. Strategy: Model-Based Generalist Agents with Strategic Dreaming

arXiv:2402.18866v1 Announce Type: new
Abstract: Model-based reinforcement learning (MBRL) has been a primary approach to ameliorating the sample efficiency issue as well as to make a generalist agent. However, there has not been much effort toward enhancing the strategy of dreaming itself. Therefore, it is a question whether and how an agent can "dream better" in a more structured and strategic way. In this paper, inspired by the observation from cognitive science suggesting that humans use a spatial divide-and-conquer strategy …

agents arxiv cs.lg dreaming strategy type