From Centralized to Self-Supervised: Pursuing Realistic Multi-Agent Reinforcement Learning

Violet Xiang, L. Cross, J.-P. Fränken, N. Haber.

NeurIPS 2023 ALOE Workshop · Poster

Comparing centralized, decentralized, asynchronous, and self-supervised multi-agent RL pipelines reveals how centralized-information assumptions can overstate performance in realistic mixed-motive settings.