Iterated Reasoning with Mutual Information in Cooperative and Byzantine Decentralized TeamingDownload PDF

29 Sept 2021, 00:32 (edited 05 May 2022)ICLR 2022 PosterReaders: Everyone
  • Keywords: Multi-agent Reinforcement Learning, Cooperation and Coordination, Policy Gradient Optimization, Mutual Information, Iterated Reasoning
  • Abstract: Information sharing is key in building team cognition and enables coordination and cooperation. High-performing human teams also benefit from acting strategically with hierarchical levels of iterated communication and rationalizability, meaning a human agent can reason about the actions of their teammates in their decision-making. Yet, the majority of prior work in Multi-Agent Reinforcement Learning (MARL) does not support iterated rationalizability and only encourage inter-agent communication, resulting in a suboptimal equilibrium cooperation strategy. In this work, we show that reformulating an agent's policy to be conditional on the policies of its neighboring teammates inherently maximizes Mutual Information (MI) lower-bound when optimizing under Policy Gradient (PG). Building on the idea of decision-making under bounded rationality and cognitive hierarchy theory, we show that our modified PG approach not only maximizes local agent rewards but also implicitly reasons about MI between agents without the need for any explicit ad-hoc regularization terms. Our approach, InfoPG, outperforms baselines in learning emergent collaborative behaviors and sets the state-of-the-art in decentralized cooperative MARL tasks. Our experiments validate the utility of InfoPG by achieving higher sample efficiency and significantly larger cumulative reward in several complex cooperative multi-agent domains.
  • One-sentence Summary: We propose a MARL framework with iterated and hierarchical rationalizability through mutual information for decision-making in fully-decentralized cooperative and Byzantine scenarios.
  • Supplementary Material: zip
17 Replies