Mastering Memory Tasks with World Models

arXiv:2403.04253v1 Announce Type: new
Abstract: Current model-based reinforcement learning (MBRL) agents struggle with long-term dependencies. This limits their ability to effectively solve tasks involving extended time gaps between actions and outcomes, or tasks demanding the recalling of distant observations to inform current actions. To improve temporal coherence, we integrate a new family of state space models (SSMs) in world models of MBRL agents to present a new method, Recall to Imagine (R2I). This integration aims to enhance both long-term memory …

abstract agents arxiv cs.lg current dependencies family long-term memory reinforcement reinforcement learning solve state struggle tasks temporal type world world models