Selectively Sharing Experiences Improves Multi-Agent Reinforcement Learning. (arXiv:2311.00865v1 [cs.LG])

We present a novel multi-agent RL approach, Selective Multi-Agent Prioritized
Experience Relay, in which agents share with other agents a limited number of
transitions they observe during training. The intuition behind this is that
even a small number of relevant experiences from other agents could help each
agent learn. Unlike many other multi-agent RL algorithms, this approach allows
for largely decentralized training, requiring only a limited communication
channel between agents. We show that our approach outperforms baseline
no-sharing decentralized training …

agent agents arxiv experience intuition learn multi-agent novel observe reinforcement reinforcement learning small training transitions