2002 · 21 citations · 10 references
ComputingComputer ScienceRobotics EngineeringArtificial IntelligenceMulti-robot SystemsRoboticsIntelligent AgentsMulti-agent Robot LearningMulti-agent SystemsMulti-robot LearningReinforcement LearningCooperative Robot LearningLearning In Multi-agent SystemsMulti-agent LearningMulti-agent Reinforcement LearningReinforcementReinforcement Learning For RoboticsVirtual Agent Interaction
To realize a speed up in learning without homogenizing the agents' behaviors in a multi-agent system, it is important to selectively share learning results. This paper describes a method designed to permit multiple agents to learn cooperatively. The advantage of our method is to dynamically switch the learning mode between mimetism and reinforcement learning according to the situation. Mimetism seeks stability in its behavior, while individual reinforcement leaning seeks the better solution. Accordingly, selective mimetism that allows the agents to partially share learning results,works to prevent homogenization among the agents. Experimental results are given for a ball-pushing task between the two virtual agents for evaluating the effectiveness of our method. This method will be useful for cooperative reinforcement learning with adaptive mimetism based on propagating the learned behaviors of a virtual agent to a physical robot in order to accelerate leaning in a physical environment.
10
Genetic algorithms in search, optimization, and machine learning
Choice Reviews Online · 1989 · 49.3K citations
Christopher J. Watkins, Peter Dayan · Machine Learning · 1992 · 3.7K citations
Machine learning: An artificial intelligence approach
Mark Stefik · Artificial Intelligence · 1985 · 982 citations
Learning to coordinate without sharing information
Sandip Sen, Mahendra Sekaran, John Hale · 1994 · 311 citations