Abstract
This paper explores the problem of cooperation of autonomous agents. Why it is important for autonomous agents to solve social dilemma problems is explained. They must be solved in a way that does not restrict the autonomy of agents. For that purpose, a social sanction by the disclosure of information is proposed. Agents were made to play the Prisoner's Dilemma game repetitively, each time changing the other party of the match, under the condition that the match history would be disclosed to the public. Computer simulation shows that 1) under the disclosure of information, even a selfish agent comes to cooperate for its own sake, and 2) an agent can learn how to cooperate through interactions with other agents. Thus autonomous agents can solve the dilemma problem by themselves. The paper then discusses the role of commitment in solving the social dilemma problems.
This is a preview of subscription content, log in via an institution to check access.
Preview
Unable to display preview. Download preview PDF.
References
Angeline, P. J., “An Alternate Interpretation of the Iterated Prisoner's Dilemma and the Evolution of Non-Mutual Cooperation”, Artificial Life VI, pp.353–358, 1994.
Axelrod, R., and Hamilton, W. D.: “The Evolution of Cooperation,” Science, Vol. 211, Mar. 1981, pp. 1390–1396.
Axelrod, R.: The Evolution of Cooperation, Basic Books Inc., 1984.
Axelrod, R., and Dion, D.: “The Further Evolution of Cooperation,” Science, Vol. 242, Dec. 1988, pp. 1385–1390.
Banks, S., “Exploring the Foundations of artificial Societies: Experiments in Evolving Solutions to Iterated N-player Prisoner's Dilemma.
Batali, J., and Kitcher, P., “Evolutionary Dynamics of Altruistic behavior in Optional and Compulsory Versions of the Iterated Prisoner's Dilemma”, Artificial Life VI, pp.343–348, 1994.
Frank, R. H.: Passions within reason, The strategic role of the emotions, W.W. Norton & Company, Inc., 1988.
Ito, A., and Yano, H.: “The Emergence of Cooperation in a Society of Autonomous Agents,” First Intl. Conf. on Multi Agent Systems, (ICMAS'95), pp.201–208, San Fransisco, 1995.
Liebrand, W. B. G. and Messick, D. M. (eds.), Frontiers in Social Dilemmas Research, Springer, 1996.
Lindgren, K.: “Evolutionary Phenomena in Simple Dynamics,” Artificial Life II, C. G. Langton (eds.), Addison Wesley, 1992, pp. 295–312.
Oliphant, M., “Evolving Cooperation in the Non-Iterated Prisoner's Dilemma: The Importance of Spatial Organization”, Artificial Life VI, pp.349–352, 1994.
Osborne, M. J. and Rubinstein, A., A Course in Game Theory, The MIT Press, 1994.
Ray, T. S.: “An Approach to the Synthesis of Life,” Artificial Life II, C. G. Langton et al. (ed.), Addison-Wesley, 1991.
Rosenschein, J. S., and Genesereth, M. R.: “Deals Among Rational Agents,” Proc. 9th Intl. Joint Conf. on Artificial Intelligence (IJ-CAI'85), Aug. 1985, pp. 91–99.
Rosenschein, J. S., and Zlotkin, G.: Rules of encounter, Designing Conventionbs for Automated Negotiation among Computers, The MIT Press, 1994.
Werner, G. M, and and Dyer, M. G., “Evolution of Communication in Artificial Organisms,” C. G. Langton (eds.), Artificial Life II, Addison Wesley, 1992, pp. 659–687.
Wu, J. and Axelrod, R., “How to Cope with Noise in the Iterated Prisoner's Dilemma”, Journal of Conflict Resolution, pp.1–5(1994)
Author information
Authors and Affiliations
Editor information
Rights and permissions
Copyright information
© 1997 Springer-Verlag Berlin Heidelberg
About this paper
Cite this paper
Ito, A. (1997). How do autonomous agents solve social dilemmas?. In: Cavedon, L., Rao, A., Wobcke, W. (eds) Intelligent Agent Systems Theoretical and Practical Issues. IAS 1996. Lecture Notes in Computer Science, vol 1209. Springer, Berlin, Heidelberg. https://doi.org/10.1007/3-540-62686-7_36
Download citation
DOI: https://doi.org/10.1007/3-540-62686-7_36
Published:
Publisher Name: Springer, Berlin, Heidelberg
Print ISBN: 978-3-540-62686-2
Online ISBN: 978-3-540-68433-6
eBook Packages: Springer Book Archive