most citedControl as Probabilistic Inference as an Emergent Communication Mechanism in Multi-Agent Reinforcement Learning

3 citations · 3 across the 1 of their papers we have counts for

collaborators

1 paper

cs.AI2023★ 3 cited

Control as Probabilistic Inference as an Emergent Communication Mechanism in Multi-Agent Reinforcement Learning

Tomoaki Nakamura, Akira Taniguchi, Tadahiro Taniguchi

This paper proposes a generative probabilistic model integrating emergent communication and multi-agent reinforcement learning. The agents plan their actions by probabilistic infer…