All learning is local: Multi-agent learning in global reward games
Author(s)
Chang, Yu-Han
Ho, Tracey
Kaelbling, Leslie P.
Date Issued
January 2004
Series/Report no.
Computer Science (CS);
Abstract
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 effectively learn a near-optimal policy in a wide variety of settings. A sequence of increasingly complex empirical tests verifies the efficacy of this technique.
Subjects
Kalman filtering
multi-agent systems
Q-learning
reinforcement learning
Persistent DSpace Link
