ELIGN: Expectation Alignment as a Multi-Agent Intrinsic Reward

1 code implementation • 9 Oct 2022 • Zixian Ma, Rose Wang, Li Fei-Fei, Michael Bernstein, Ranjay Krishna

These results identify tasks where expectation alignment is a more useful strategy than curiosity-driven exploration for multi-agent coordination, enabling agents to do zero-shot coordination.

Multi-agent Reinforcement Learning