DocumentCode :
2464198
Title :
Maintaining cooperation in homogeneous multi-agent system
Author :
Hao, Jianye ; Leung, Ho-fung
Author_Institution :
Dept. of Comput. Sci. & Eng., Chinese Univ. of Hong Kong, Hong Kong, China
fYear :
2012
fDate :
14-17 Oct. 2012
Firstpage :
301
Lastpage :
306
Abstract :
During multi-agent interactions, robust strategies are needed to help the agents to coordinate their actions to achieve efficient outcomes. A large body of previous work focuses on designing strategies towards the goal of Nash equilibrium, which can be extremely inefficient in many situations such as prisoner´s dilemma game. A number of improved algorithms based on Q-learning have been developed recently for agents to achieve mutual cooperation in games like prisoner´s dilemma. However, almost all of them involve only two agents playing the same game repeatedly. However, this may not reflect the real scenario in practical multi-agent interaction situations. In practical multi-agent environments, each agent may interact with multiple agents at the same time and each agent may only be allowed to interact with a specific set of agents, which is determined by the system´s underlying topology. In this paper, we propose a learning framework by taking into consideration the underlying interaction topology of the agents. We show that the system can maintain certain level of cooperation though the agents are individually rational. To better understand this phenomenon, we also develop a mathematical model to analyze the dynamics resulting from the learning framework. The theoretical results of the mathematical model are shown to be able to successfully predict the transition point and the expected behaviors of the system compared with the simulation results.
Keywords :
game theory; learning (artificial intelligence); multi-agent systems; Nash equilibrium; Q-learning framework; agent interaction topology; cooperation maintenance; homogeneous multiagent system; mathematical model; multiagent interactions; mutual cooperation; prisoner dilemma game; transition point; Equations; Games; Heuristic algorithms; Mathematical model; Sociology; Statistics; Topology; Prisoner´s Dilemma Game; Q-learning;
fLanguage :
English
Publisher :
ieee
Conference_Titel :
Systems, Man, and Cybernetics (SMC), 2012 IEEE International Conference on
Conference_Location :
Seoul
Print_ISBN :
978-1-4673-1713-9
Electronic_ISBN :
978-1-4673-1712-2
Type :
conf
DOI :
10.1109/ICSMC.2012.6377718
Filename :
6377718
Link To Document :
بازگشت