Generalized multiagent learning with performance bound

Abstract – Despite increasing deployment of agent technologies in several business and industry domains, user confidence in fully automated agent driven applications is noticeably lacking. The main reasons for such lack of trust in complete automation are scalability and nonexistence of reasonable guarantees in the performance of self-adapting software. In this paper we address the latter issue in the context of learning agents in a Multiagent System (MAS). Performance guarantees for existing on-line Multiagent Learning (MAL) algorithms are realizable only in the limit, thereby seriously limiting its practical utility. Our goal is to provide certain meaningful guarantees about the performance of a learner in a MAS, while it is learning. In particular, we present a novel MAL algorithm that 1) converges to a best response against stationary opponents, 2) converges to a Nash equilibrium in self-play and 3) achieves a constant bounded expected regret at any time (no-average-regret asymp...

• Type: Journal
• Year: 2007
• Where: AAMAS
• Authors: Bikramjit Banerjee, Jing Peng
• Keywords: AAMAS 2007, Agent Driven Applications, Certain Meaningful Guarantees, Intelligent Agents, On-line Multiagent Learning