Emotional Multiagent Reinforcement Learning in Social Dilemmas

  • Chao Yu
  • Minjie Zhang
  • Fenghui Ren
Conference paper
Part of the Lecture Notes in Computer Science book series (LNCS, volume 8291)

Abstract

Social dilemmas have attracted extensive interest in multiagent system research in order to study the emergence of cooperative behaviors among selfish agents. Without extra mechanisms or assumptions, directly applying multiagent reinforcement learning in social dilemmas will end up with convergence to the Nash equilibrium of mutual defection among the agents. This paper investigates the importance of emotions in modifying agent learning behaviors in order to achieve cooperation in social dilemmas. Two fundamental variables, individual wellbeing and social fairness, are considered in the appraisal of emotions that are used as intrinsic rewards for learning. Experimental results reveal that different structural relationships between the two appraisal variables can lead to distinct agent behaviors, and under certain circumstances, cooperation can be obtained among the agents.

Keywords

Multiagent System Individual Wellbeing Social Dilemma Mutual Defection Intrinsic Reward 
These keywords were added by machine and not by the authors. This process is experimental and the keywords may be updated as the learning algorithm improves.
This is a preview of subscription content, log in to check access.

Preview

Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.

References

  1. 1.
    Hofmann, L., Chakraborty, N., Sycara, K.: The evolution of cooperation in self-interested agent societies: a critical study. In: The 10th International Conference on Autonomous Agents and Multiagent Systems, pp. 685–692 (2011)Google Scholar
  2. 2.
    Salazar, N., Rodriguez-Aguilar, J., Arcos, J., Peleteiro, A., Burguillo-Rial, J.: Emerging cooperation on complex networks. In: The 10th International Conference on Autonomous Agents and Multiagent Systems, pp. 669–676 (2011)Google Scholar
  3. 3.
    Nowak, M.: Five rules for the evolution of cooperation. Science 314(5805), 1560–1563 (2006)CrossRefGoogle Scholar
  4. 4.
    Perc, M., Szolnoki, A.: Coevolutionary games–a mini review. BioSystems 99(2), 109–125 (2010)CrossRefGoogle Scholar
  5. 5.
    Sutton, R., Barto, A.: Reinforcement learning: An introduction. MIT Press, Cambridge (1998)Google Scholar
  6. 6.
    Busoniu, L., Babuska, R., De Schutter, B.: A comprehensive survey of multiagent reinforcement learning. IEEE Trans. Syst. Man Cybern. C. Appl. Re. 38(2), 156–172 (2008)CrossRefGoogle Scholar
  7. 7.
    Conlisk, J.: Why bounded rationality? J. Econ. Lit. 34(2), 669–700 (1996)Google Scholar
  8. 8.
    Stimpson, J., Goodrich, M., Walters, L.: Satisficing and learning cooperation in the prisoner’s dilemma. In: International Joint Conference on Artificial Intelligence, pp. 535–544. AAAI Press, California (2001)Google Scholar
  9. 9.
    Rumbell, T., Barnden, J., Denham, S., Wennekers, T.: Emotions in autonomous agents: comparative analysis of mechanisms and functions. J. Auton. Agents Multi-AG 25(1), 1–45 (2012)CrossRefGoogle Scholar
  10. 10.
    Ahn, H., Picard, R.: Affective cognitive learning and decision making: The role of emotions. In: Proceedings of the 18th European Meeting on Cybernetics and Systems Research, pp. 1–6. North-Holland, Amsterdam (2006)Google Scholar
  11. 11.
    Salichs, M., Malfaz, M.: A new approach to modeling emotions and their use on a decision-making system for artificial agents. IEEE Trans. Affec. Comput. 3(1), 56–68 (2012)CrossRefGoogle Scholar
  12. 12.
    Sequeira, P., Melo, F., Paiva, A.: Emotion-based intrinsic motivation for reinforcement learning agents. In: D’Mello, S., Graesser, A., Schuller, B., Martin, J.-C. (eds.) ACII 2011, Part I. LNCS, vol. 6974, pp. 326–336. Springer, Heidelberg (2011)CrossRefGoogle Scholar
  13. 13.
    Bazzan, A., Bordini, R.: A framework for the simulation of agents with emotions. In: Proceedings of the 5th International Conference on Autonomous Agents, pp. 292–299. ACM, New York (2001)CrossRefGoogle Scholar
  14. 14.
    Szolnoki, A., Xie, N., Wang, C., Perc, M.: Imitating emotions instead of strategies in spatial games elevates social welfare. Europhys. Lett. 96(3), 38002 (2011)CrossRefGoogle Scholar
  15. 15.
    Bazzan, A., Peleteiro, A., Burguillo, J.: Learning to cooperate in the iterated prisoner’s dilemma by means of social attachments. J. Braz. Comp. Soc. 17(3), 163–174 (2011)MathSciNetCrossRefGoogle Scholar
  16. 16.
    Albert, R., Barabási, A.: Statistical mechanics of complex networks. Rev. Mod. Phys. 74, 47–97 (2002)CrossRefMATHGoogle Scholar
  17. 17.
    Singh, S., Lewis, R., Barto, A.: Where do rewards come from. In: Proceedings of the Annual Conference of the Cognitive Science Society, pp. 2601–2606. Cognitive Science Society, Inc., Austin (2009)Google Scholar
  18. 18.
    Singh, S., Lewis, R., Barto, A., Sorg, J.: Intrinsically motivated reinforcement learning: An evolutionary perspective. IEEE Trans. Auton. Mental Develop. 2(2), 70–82 (2010)CrossRefGoogle Scholar
  19. 19.
    Marsella, S., Gratch, J., Petta, P.: Computational models of emotion. Blueprint for Affective Computing: A Source Book. Oxford University Press, Oxford (2010)Google Scholar
  20. 20.
    Ellsworth, P., Scherer, K.: Appraisal processes in emotion. Oxford University Press, New York (2003)Google Scholar
  21. 21.
    de Jong, S., Tuyls, K.: Human-inspired computational fairness. J. Auton. Agents Multi-AG 22(1), 103–126 (2011)CrossRefGoogle Scholar
  22. 22.
    Smith, C.A., Lazarus, R.S.: Appraisal components, core relational themes, and the emotions. Cognition and Emotion 7(3-4), 233–269 (1993)CrossRefGoogle Scholar
  23. 23.
    Watts, D., Strogatz, S.: Collective dynamics of ‘small-world’ networks. Nature 393(6684), 440–442 (1998)CrossRefGoogle Scholar
  24. 24.
    Abdallah, S., Lesser, V.: Learning the task allocation game. In: Proceedings of the Fifth International Joint Conference on Autonomous Agents and Multiagent Systems, pp. 850–857 (2006)Google Scholar
  25. 25.
    Sandholm, T., Crites, R.: Multiagent reinforcement learning in the iterated prisoner’s dilemma. Biosystems 37(1-2), 147–166 (1996)CrossRefGoogle Scholar
  26. 26.
    Vrancx, P., Tuyls, K., Westra, R.: Switching dynamics of multi-agent learning. In: the 7th International Joint Conference on Autonomous Agents and Multiagent Systems, pp. 307–313. ACM Press, New York (2008)Google Scholar
  27. 27.
    Tanabe, S., Masuda, N.: Evolution of cooperation facilitated by reinforcement learning with adaptive aspiration levels. J. Theor. Biol. 293, 151–160 (2011)MathSciNetCrossRefGoogle Scholar

Copyright information

© Springer-Verlag Berlin Heidelberg 2013

Authors and Affiliations

  • Chao Yu
    • 1
  • Minjie Zhang
    • 1
  • Fenghui Ren
    • 1
  1. 1.School of Computer Science and Software EngineeringUniversity of WollongongWollongongAustralia

Personalised recommendations