Approximation Techniques in Multiagent Learning

Abstract

Research in multiagent systems includes the investigation of algorithms that select actions for multiple agents coexisting in the same environment. Multiagent systems are becoming increasingly relevant within artificial intelligence, as software and robotic agents become more prevalent. Robotic soccer, disaster mitigation and rescue, automated driving, and information and e-commerce agents are examples of challenging multiagent domains. As the automation trend continues, we need robust algorithms for coordinating multiple agents, and for effectively responding to other external agents.