Higher Replay Ratio Empowers Sample-Efficient Multi-Agent Reinforcement Learning

arXiv:2404.09715v1 Announce Type: new
Abstract: One of the notorious issues for Reinforcement Learning (RL) is poor sample efficiency. Compared to single agent RL, the sample efficiency for Multi-Agent Reinforcement Learning (MARL) is more challenging because of its inherent partial observability, non-stationary training, and enormous strategy space. Although much effort has been devoted to developing new methods and enhancing sample efficiency, we look at the widely used episodic training mechanism. In each training step, tens of frames are collected, but only …

agent arxiv cs.ai cs.lg cs.ma multi-agent reinforcement reinforcement learning sample type