All learning is Local: Multi-agent Learning in Global Reward Games

In large multiagent games, partial observability, coordination, and credit assignment persistently plague attempts to design good learning algorithms. We provide a simple and efficient algorithm that in part uses a linear system to model the world from a single agent’s limited perspective, and takes advantage of Kalman filtering to allow an agent to construct a good training signal and learn an effective policy.

• Type: Conference
• Year: 2003
• Where: NIPS
• Authors: Yu-Han Chang, Tracey Ho, Leslie Pack Kaelbling
• Keywords: Agent’s Limited Perspective, Assignment Persistently Plague, Large Multiagent Games, NIPS 2003, NIPS 2007