Learning to cooperate in multi-agent social dilemmas

Proceedings of the International Conference on Autonomous Agents

Volumn 2006, Issue , 2006, Pages 783-785

  De Cote, Enrique Munoz ^a   Lazaric, Alessandro ^a   Restelli, Marcello ^a   Bonarini, Andrea ^a  

^a POLITECNICO DI MILANO   (Italy)

Author keywords

[No Author keywords available]

Indexed keywords

PARETO OUTCOMES; Q-LEARNING; REINFORCEMENT LEARNING (RL) ALGORITHMS;

E-LEARNING; LEARNING ALGORITHMS; MULTI AGENT SYSTEMS; PARETO PRINCIPLE; UTILITY PROGRAMS;

REINFORCEMENT LEARNING;

EID: 34247191514     PISSN: None     EISSN: None     Source Type: Conference Proceeding    
DOI: 10.1145/1160633.1160770     Document Type: Conference Paper

References (5)

1. M. Bowling and M. Veloso. Multiagent learning using a variable learning rate. Artificial Intelligence, 136:215-250, 2002.
2. J. W. Crandall and M. A. Goodrich. Learning to compete, compromise, and cooperate in repeated general-sum games. In Proc. of ICML 2005, to appear.
3. M. W. Macy and A. Flache. Learning dynamics in social dilemmas. Proceedings of the National Academy of Sciences, 72(9):29-36, 2002.
4. J. L. Stimpson and M. A. Goodrich. Learning to cooperate in a social dilemma: A satisficing approach to bargaining. In Proceedings of ICML, 2003.
5. J. L. Stimpson, M. A. Goodrich, and L. C. Walters. Satisficing and learning cooperation in the prisoner's dilemma. In Proc. of IJCAI 2001, 2001.