A Multiagent Variant of Dyna-Q

This paper describes a multiagent variant of Dyna-Q called M-Dyna-Q. Dyna-Q is an integrated single-agent framework for planning, reacting, and learning. Like DynaQ, M-Dyna-Q employs two key ideas: learning results can serve as a valuable input for both planning and reacting, and results of planning and reacting can serve as a valuable input to learning. M-Dyna-Q extends Dyna-Q in that planning, reacting, and learning are jointly realized by multiple agents.

• Type: Conference
• Year: 2000
• Where: ICMAS
• Authors: Gerhard Weiß
• Keywords: Dyna-q Called M-dyna-q, ICMAS 2000, Integrated Single-agent Framework, Intelligent Agents, Valuable Input