Paper Info
Title
Hysteretic q-learning : an algorithm for decentralized reinforcement learning in cooperative multi-agent teams
Abstract
Abstract—Multi-agent systems,(MAS) are a field of study of growing,interest in a variety of domains,such,as robotics or distributed,controls. The article focuses on,decentralized reinforcement learning (RL) in cooperative MAS, where a team of independent,learning,robots,(IL) try to coordinate,their individual,behavior,to reach,a coherent,joint behavior. We assume,that each robot has no information,about its teammates’ actions. To date, RL approaches for such ILs did not guarantee convergence,to the optimal,joint policy in scenarios where,the coordination,is difficult. We report an investigation of existing algorithms for the learning of coordination in cooperative MAS, and suggest a Q-Learning extension for ILs, called Hysteretic Q-Learning. This algorithm,does,not require any,additional communication,between,robots. Its advantages,are showing,off and,compared,to other methods,on various applications,: bi- matrix games, collaborative ball balancing task and pursuit domain.
Year
DOI
Venue
2007
10.1109/IROS.2007.4399095
IROS
Keywords
Field
DocType
learning (artificial intelligence),multi-agent systems,multi-robot systems,cooperative multiagent teams,decentralized reinforcement learning,hysteretic Q-learning,independent learning robot,multiagent systems
Convergence (routing),Robot learning,Computer science,Algorithm,Q-learning,Multi-agent system,Independent learning,Artificial intelligence,Robot,Robotics,Reinforcement learning
Conference
Citations 
PageRank 
References 
10
0.55
13
Authors
3
Name
Order
Citations
PageRank
Laëtitia Matignon1889.43
Guillaume J. Laurent29712.60
Nadine Le Fort-Piat37710.09