Evolutionary Machine Ethics

Living reference work entry
Part of the Springer Reference Geisteswissenschaften book series (SPREFGEIST)

Abstract

Machine ethics is a sprouting interdisciplinary field of enquiry arising from the need of imbuing autonomous agents with some capacity for moral decision-making. Its overall results are not only important for equipping agents with a capacity for moral judgment, but also for helping better understand morality, through the creation and testing of computational models of ethics theories. Computer models have become well defined, eminently observable in their dynamics, and can be transformed incrementally in expeditious ways. We address, in work reported and surveyed here, the emergence and evolution of cooperation in the collective realm. We discuss how our own research with Evolutionary Game Theory (EGT) modelling and experimentation leads to important insights for machine ethics, such as the design of moral machines, multi-agent systems, and contractual algorithms, plus their potential application in human settings too.

Keywords

Machine Ethics Evolutionary Game Theory Intention Recognition Commitment Guilt 

Notes

Acknowledgments

Profound thanks are due to our co-authors of joint published work herein cited, without which the personal summing up and specific philosophical viewpoint above would not have been possible at all. Alphabetically: Ari Saptawijaya, Francisco C. Santos, Luis Martinez-Vaquero, and Tom Lenaerts. Furthermore, L. M. Pereira acknowledges support from grant FCT/MEC NOVA LINCS PEst UID/CEC/04516/2013. TAH from Teesside URF funding (11200174).

References

  1. Abeler, Johannes, Juljana Calaki, Kai Andree, and Christoph Basek. 2010. The power of apology. Economics Letters 107(2): 233–235.Google Scholar
  2. Axelrod, Robert. 1984. The evolution of cooperation, vol. 5145. New York: Basic Books (AZ).Google Scholar
  3. Back, Istvan, and Andreas Flache. 2008. The adaptive rationality of interpersonal commitment. Rationality and Society 20(1): 65–83.Google Scholar
  4. Boden, M. A. 2008. Information, computation, and cognitive science. Handbook of the Philosophy of Science 8: 749–769.Google Scholar
  5. Byrne, Ruth M. J. 2007. The rational imagination: How people create alternatives to reality. Cambridge, MA: MIT Press.Google Scholar
  6. Charniak, Eugene, and Robert P. Goldman. 1993. A Bayesian model of plan recognition. Artificial Intelligence 64(1): 53–79.Google Scholar
  7. Cherry, Todd L., and David M. McEvoy. 2013. Enforcing compliance with environmental agreements in the absence of strong institutions: An experimental analysis. Environmental and Resource Economics 54(1): 1–15.Google Scholar
  8. Chopra, Amit K., and Munindar P. Singh. 2009. Multiagent commitment alignment. In Proceedings of The 8th international conference on autonomous agents and multiagent systems-volume 2, 937–944. Budapest: International Foundation for Autonomous Agents and Multiagent Systems.Google Scholar
  9. Chopra, Amit K., Samuel H. Christie V, and Munindar P. Singh. 2017. Splee: a declarative information-based language for multiagent interaction protocols. In Proceedings of the 16th conference on autonomous agents and multiagent systems, 1054–1063. International Foundation for Autonomous Agents and Multiagent Systems.Google Scholar
  10. Cohen, Philip R., and Hector J. Levesque. 1990. Intention is choice with commitment. Artificial Intelligence 42(2–3: 213–261.Google Scholar
  11. Collins, John David, Edward Jonathan Hall, and Laurie Ann Paul, eds. 2004. Causation and counterfactuals. Cambridge, MA: MIT Press.Google Scholar
  12. Correia, Vasco. 2016. Weakness of will and self-control’. In Morality and emotion, 35. London: Routledge, 83–98. ISBN 978-1-138-12130-0.Google Scholar
  13. Deacon, Terrence W. 2003. The hierarchic logic of emergence: Untangling the interdependence of evolution and self-organization. In Evolution and learning: The Baldwin effect reconsidered (Chapter 14): 273–308, Cambridge, MA.Google Scholar
  14. Dennett, Daniel Clement. 2005. Sweet dreams: Philosophical obstacles to a science of consciousness. Cambridge, MA: MIT Press.Google Scholar
  15. Fehr, Ernst, and Simon Gächter. 2002. Altruistic punishment in humans. Nature 415(6868): 137–140.Google Scholar
  16. Fischbacher, Urs, and Verena Utikal. 2013. On the acceptance of apologies. Games and Economic Behavior 82: 592–608.Google Scholar
  17. Fodor, Jerry A. 1974. Special sciences (or: the disunity of science as a working hypothesis). Synthese 28(2): 97–115.CrossRefGoogle Scholar
  18. Gaspar, Augusta. 2016. Morality and empathy vs. empathy and morality. In Morality and Emotion, 62–82. London: Routledge, 83–98. ISBN 978-1-138-12130-0.Google Scholar
  19. Hamilton, William D., and Robert Axelrod. 1981. The evolution of cooperation. Science 211(27): 1390–1396.Google Scholar
  20. Han, The Anh. 2013. Intention recognition, commitments and their roles in the evolution of cooperation: from artificial intelligence techniques to evolutionary game theory models. SAPERE series, vol. 9. Berlin.Google Scholar
  21. Han, The Anh. 2016. Emergence of social punishment and cooperation through prior commitments. In Proceedings of the 30th AAAI conference on artificial intelligence (AAAI 2016), 2494–2500, Phoenix.Google Scholar
  22. Han, The Anh, and Tom Lenaerts. 2016. A synergy of costly punishment and commitment in cooperation dilemmas. Adaptive Behavior 24(4): 237–248.Google Scholar
  23. Han, The Anh, and Luis Moniz Pereira. 2013a. Context-dependent incremental decision making scrutinizing the intentions of others via bayesian network model construction. Intelligent Decision Technologies 7(4): 293–317.Google Scholar
  24. Han, The Anh, and Luis Moniz Pereira. 2013b. Intention-based decision making via intention recognition and its applications. In Human Behavior Recognition Technologies: Intelligent Applications for Monitoring and Security. Hershey, PA: IGI Global, pp 174–211.Google Scholar
  25. Han, The Anh, and Luis Moniz Pereira. 2013c. State-of-the-art of intention recognition and its use in decision making. AI Communications 26(2): 237–246.Google Scholar
  26. Han The Anh, Luis Moniz Pereira, and Francisco C. Santos. 2011. Intention recognition promotes the emergence of cooperation. Adaptive Behavior 19(4): 264–279.Google Scholar
  27. Han, The Anh, Luis Moniz Pereira, and Francisco C. Santos. 2012a. Corpus-based intention recognition in cooperation dilemmas. Artificial Life 18(4): 365–383.Google Scholar
  28. Han, The Anh, Luis Moniz Pereira, and Francisco C. Santos. 2012b. Intention recognition, commitment and the evolution of cooperation. In Evolutionary Computation (CEC), 2012 I.E. Congress on, 1–8. Brisbane: IEEE.Google Scholar
  29. Han, The Anh, Luis Moniz Pereira, and Francisco C. Santos. 2012c. The emergence of commitments and cooperation. In Proceedings of the 11th international conference on autonomous agents and multiagent systems-volume 1, 559–566. Valencia: International Foundation for Autonomous Agents and Multiagent Systems.Google Scholar
  30. Han, The Anh, Ari Saptawijaya, and Luis Moniz Pereira. 2012d. Moral reasoning under uncertainty. In International conference on logic for programming artificial intelligence and reasoning, 212–227. Springer, Berlin/Heidelberg.Google Scholar
  31. Han, The Anh, Luis Moniz Pereira, Francisco C. Santos, and Tom Lenaerts. 2013a. Good agreements make good friends. Scientific Reports 3.Google Scholar
  32. Han, The Anh, Luis Moniz Pereira, Francisco C. Santos, and Tom Lenaerts. 2013b. Why is it so hard to say sorry? evolution of apology with commitments in the iterated Prisoner’s Dilemma. In Proceedings of the twenty-third international joint conference on artificial intelligence, 177–183. Beijing: AAAI Press.Google Scholar
  33. Han, The Anh, Luis Moniz Pereira, and Tom Lenaerts. 2015a. Avoiding or restricting defectors in public goods games?. Journal of the Royal Society Interface 12(103): 20141203.Google Scholar
  34. Han, The Anh, Luis Moniz Pereira, Francisco C. Santos, and Tom Lenaerts. 2015b. Emergence of cooperation via intention recognition, commitment and apology–a research summary. AI Communications 28(4): 709–715.Google Scholar
  35. Han, The Anh, Francisco C. Santos, Tom Lenaerts, and Luis Moniz Pereira. 2015c. Synergy between intention recognition and commitments in cooperation dilemmas. Scientific Reports 5.Google Scholar
  36. Han, The Anh, Luis Moniz Pereira, and Tom Lenaerts. 2017a. Evolution of commitment and level of participation in public goods games. Autonomous Agents and Multi-Agent Systems 31(3): 561–583.Google Scholar
  37. Han, The Anh, Luís Moniz Pereira, Luis A. Martinez-Vaquero, and Tom Lenaerts. 2017b. Centralized vs. personalized commitments and their influence on cooperation in group interactions. In Proceedings of the 31st AAAI conference on artificial intelligence (AAAI 2017), 2999–3005, San Francisco.Google Scholar
  38. Hauser, Marc. 2006. Moral minds: How nature designed our universal sense of right and wrong. New York: Ecco/HarperCollins Publishers.Google Scholar
  39. Heinze, C. 2003. Modeling intention recognition for intelligent agent systems, PhD thesis, The University of Melbourne, Australia.Google Scholar
  40. Hodges, A. 1997. Alan Turing: One of the great philosophers. Phoenix/London: Phoenix.Google Scholar
  41. Hofbauer, Josef, and Karl Sigmund. 1998. Evolutionary games and population dynamics. Cambridge, UK: Cambridge University Press.Google Scholar
  42. John, Eileen. 2016. Moral feelings from rocky fictional ground. In Morality and emotion, 99. London: Routledge, 83–98. ISBN 978-1-138-12130-0.Google Scholar
  43. Levin, J. 2010. Functionalism. In The stanford encyclopaedia of philosophy, ed. E. N. Zalta. http://plato.stanford.edu/archives/sum2010/entries/functionalism/.
  44. Marsella, Stacy, and Jonathan Gratch. 2014. Computationally modeling human emotion. Communications of the ACM 57(12): 56–67.Google Scholar
  45. Martinez-Vaquero, Luis A., and José A. Cuesta. 2013. Evolutionary stability and resistance to cheating in an indirect reciprocity model based on reputation. Physical Review E 87(5): 052810.Google Scholar
  46. Martinez-Vaquero, Luis A., and José A. Cuesta. 2014. Spreading of intolerance under economic stress: Results from a reputation-based model. Physical Review E 90(2): 022805.Google Scholar
  47. Martinez-Vaquero, Luis A., The Anh Han, Luis Moniz Pereira, and Tom Lenaerts. 2015. Apology and forgiveness evolve to resolve failures in cooperative agreements. Scientific Reports 5.Google Scholar
  48. Martinez-Vaquero, Luis A., The Anh Han, Luis Moniz Pereira, and Tom Lenaerts. 2017. When agreement-accepting free-riders are a necessary evil for the evolution of cooperation. Scientific Reports 7.Google Scholar
  49. McCullough, Michael. 2008. Beyond revenge: The evolution of the forgiveness instinct. New Jersey: Wiley.Google Scholar
  50. McCullough, Michael E., Robert Kurzban, and Benjamin A. Tabak. 2010. Evolved mechanisms for revenge and forgiveness. In Understanding and reducing aggression, violence, and their consequences, 221–239. Miami.Google Scholar
  51. McCullough, Michael E., Eric J. Pedersen, Benjamin A. Tabak, and Evan C. Carter. 2014. Conciliatory gestures promote forgiveness and reduce anger in humans. Proceedings of the National Academy of Sciences 111(30): 11211–11216.Google Scholar
  52. McDermott, Drew V. 2001. Mind and mechanism. Cambridge, MA: MIT Press.Google Scholar
  53. Mendonça, Dina. 2016. Emotions and akratic feelings. In Morality and emotion, 50. London: Routledge, 83–98. ISBN 978-1-138-12130-0.Google Scholar
  54. Mikhail, J. 2007. Universal moral grammar: Theory, evidence and the future. Trends in Cognitive Sciences 11(4): 143–152.CrossRefGoogle Scholar
  55. Nesse, Randolph M. 2001. Natural selection and the capacity for subjective commitment. In Evolution and the capacity for commitment, 1–44. New York.Google Scholar
  56. Nowak, M. A. 2006. Five rules for the evolution of cooperation. Science 314(5805): 1560–1563.CrossRefGoogle Scholar
  57. Nowak, Martin A., and Karl Sigmund. 1992. Tit for tat in heterogeneous populations. Nature 355(6357): 250–253.Google Scholar
  58. Ohtsubo, Yohsuke, and Esuka Watanabe. 2009. Do sincere apologies need to be costly? Test of a costly signaling model of apology. Evolution and Human Behavior 30(2): 114–123.Google Scholar
  59. Okamoto, Kyoko, and Shuichi Matsumura. 2000. The evolution of punishment and apology: an iterated prisoner’s dilemma model. Evolutionary Ecology 14(8): 703-720.Google Scholar
  60. Pereira, Luís Moniz. 2012a. Turing is among us. Journal of Logic and Computation 22(6): 1257–1277.CrossRefGoogle Scholar
  61. Pereira, Luís Moniz. 2012b. Evolutionary tolerance. In Philosophy and cognitive science, 263–287. Berlin/Heidelberg: Springer.CrossRefGoogle Scholar
  62. Pereira, L.M., and A. Saptawijaya. 1994. Agent morality via counterfactuals in logic programming, invited paper. In Proceedings of bridging the gap: Is logic and automated reasoning a foundation for human reasoning?, a 39th annual meeting of the Cognitive Science Society (CogSci 2017) workshop, CEUR workshop proceedings, vol. 1994, ed. U. Furbach and C. Schon, 39–53, 26 July, London.Google Scholar
  63. Pereira, L.M., and A. Saptawijaya. 2011. Modelling morality with prospective logic. In Machine ethics, ed. M. Anderson and S.L. Anderson, 398–421. Cambridge University Press. ISBN 978-0521112352.Google Scholar
  64. Pereira, Luís Moniz, and The Anh Han. 2011a. Intention recognition with evolution prospection and causal bayes networks. In Computational intelligence for engineering systems, 1–33. Springer, Netherlands.Google Scholar
  65. Pereira, Luís Moniz, and The Anh Han. 2011b. Elder care via intention recognition and evolution prospection. In International conference on applications of declarative programming and knowledge management, 170–187. Springer, Berlin/Heidelberg.Google Scholar
  66. Pereira, Luís Moniz, and Ari Saptawijaya. 2009. Modelling morality with prospective logic. International Journal of Reasoning-based Intelligent Systems 1(3–4): 209–221.Google Scholar
  67. Pereira, Luís Moniz, and Ari Saptawijaya. 2015. Abduction and beyond in logic programming with application to morality. In ed. L. Magnani, IfColog Journal of Logics and their Applications, Special issue on Abduction, 3(1):37–71. London: College Publications.Google Scholar
  68. Pereira, Luís Moniz, and Ari Saptawijaya. 2016a. Bridging two realms of machine ethics. In Programming machine ethics, 159–165. Berlin: Springer.Google Scholar
  69. Pereira, Luís Moniz, and Ari Saptawijaya. 2016b. Programming machine ethics, vol. 26. Berlin: Springer. ISBN 978-3-319-29353-0.Google Scholar
  70. Pereira, Luís Moniz, and Ari Saptawijaya. 2016c. Counterfactuals, logic programming and agent morality. In Applications of formal philosophy, 25–53. Cham: Springer, 2017, Berlin: Springer, 25–54. ISBN 978-3319585055.Google Scholar
  71. Pereira, Luis Moniz, Tom Lenaerts, Luis A. Martinez-Vaquero, and The Anh Han. 2017. Social manifestation of guilt leads to stable cooperation in multi-agent systems. In Proceedings of the 16th conference on autonomous agents and multiagent systems, 1422–1430. Sao Paulo: International Foundation for Autonomous Agents and Multiagent Systems.Google Scholar
  72. Pope, Alexander. 1931. An essay on criticism, part II. Lewis, W. Russel Street, Covent Garden (1711).Google Scholar
  73. Powers, Simon T., Daniel J. Taylor, and Joanna J. Bryson. 2012. Punishment can promote defection in group-structured populations. Journal of Theoretical Biology 311: 107–116.Google Scholar
  74. Prinz, Jesse. 2016. Emotions, morality, and identity. In Morality and emotion, 13–34. London: Routledge, 83–98. ISBN 978-1-138-12130-0.Google Scholar
  75. Raihani, Nichola J., and Redouan Bshary. 2015. The reputation of punishers. Trends in Ecology & Evolution 30(2): 98–103.Google Scholar
  76. Roy, P., B. Bouchard, A. Bouzouane, and S. Giroux. 2007. A hybrid plan recognition model for Alzheimer’s patients: Interleaved- erroneous dilemma. In Proceedings of IEEE/WIC/ACM Inter- national conference on intelligent agent technology, 131–137.Google Scholar
  77. Sadri, Fariba. 2011. Logic-based approaches to intention recognition. In Handbook of research on ambient intelligence and smart environments: Trends and perspectives, 346–375. Hershey, PA: IGI Global.Google Scholar
  78. Saptawijaya, Ari, and Luis Moniz Pereira. 2015a. Logic programming applied to machine ethics. In Portuguese conference on artificial intelligence, 414–422. Cham: Springer. LNCS vol. 9273. Berlin: Springer. ISBN 978-3-319-23485-4.Google Scholar
  79. Saptawijaya, Ari, and Luis Moniz Pereira. 2015b. The potential of logic programming as a computational tool to model morality. In A construction manual for robots’ ethical systems, 169–210. Switzerland: Springer.Google Scholar
  80. Saptawijaya, Ari, and Luis Moniz Pereira. 2015c. From logic programming to machine ethics. In Handbuch Maschinenethik, ed. O. Bendel, (2018). Berlin: Springer.Google Scholar
  81. Saptawijaya, A., and L.M. Pereira. 2016. Logic programming for modeling morality. In Special issue on “Formal representations of model-based reasoning and abduction”, of the logic journal of the IGPL, ed. L. Magnani and C. Casadio. 24(4): 510–525.  https://doi.org/10.1093/jigpal/jzw025, online 9 May, Aug 2016.
  82. Saptawijaya, Ari, and Luís Moniz Pereira. 2018. From logic programming to machine ethics. In Handbuch Maschinenethik, ed. O. Bendel. Berlin: Springer.Google Scholar
  83. Sarker, Md Omar Faruque, Torbjørn S. Dahl, Elsa Arcaute, and Kim Christensen. 2014. Local interactions over global broadcasts for improved task allocation in self-organized multi-robot systems. Robotics and Autonomous Systems 62(10): 1453–1462.Google Scholar
  84. Schneider, Frédéric, and Roberto A. Weber. 2013. Long-term commitment and cooperation. Tech. Rep., Working paper series, University of Zurich, Department of Economics.Google Scholar
  85. Searle, John R. 1995. The construction of social reality. New York: Simon and Schuster.Google Scholar
  86. Searle, John. 2010. Making the social world: The structure of human civilization. Oxford: Oxford University Press.Google Scholar
  87. Sigmund, Karl. 2010. The calculus of selfishness. Princeton: Princeton University Press.Google Scholar
  88. Smith, Nick. 2008. I was wrong: The meanings of apologies. Cambridge, UK: Cambridge University Press.Google Scholar
  89. Sterelny, Kim. 2012. The evolved apprentice. Cambridge, MA: MIT Press.Google Scholar
  90. Takaku, Seiji, Bernard Weiner, and Ken-Ichi Ohbuchi. 2001. A cross-cultural examination of the effects of apology and perspective taking on forgiveness. Journal of Language and Social Psychology 20(1–2): 144–166.Google Scholar
  91. Trivers, Robert L. 1971. The evolution of reciprocal altruism. The Quarterly Review of Biology 46(1): 35–57.CrossRefGoogle Scholar
  92. Turing, Alan M. 1950. Computing machinery and intelligence. Mind 59(236): 433–460.CrossRefGoogle Scholar
  93. Tzeng, Jeng-Yi. 2004. Toward a more civilized design: studying the effects of computers that apologize. International Journal of Human-Computer Studies 61(3): 319–345.CrossRefGoogle Scholar
  94. Utz, Sonja, Uwe Matzat, and Chris Snijders. 2009. On-line reputation systems: The effects of feedback comments and reactions on building and rebuilding trust in on-line auctions. International Journal of Electronic Commerce 13(3): 95–118.Google Scholar
  95. von Neumann, J., and O. von Morgenstern. 1944. Theory of games and economic behavior, vol. 1. Princeton: Princeton University Press.Google Scholar
  96. Winikoff, Michael. 2007. Implementing commitment-based interactions. In Proceedings of the 6th international joint conference on autonomous agents and multiagent systems, 128. Hawaii: ACM.Google Scholar
  97. Wooldridge, Michael, and Nicholas R. Jennings. 1999. The cooperative problem-solving process. Journal of Logic and Computation 9(4): 563–592.Google Scholar
  98. Wright, R. 2001. NonZero – The logic of human destiny. New York: Vintage.Google Scholar

Copyright information

© Springer Fachmedien Wiesbaden GmbH 2018

Authors and Affiliations

  1. 1.School of Computing, Media and the ArtsTeeside UniversityMiddlesbroughGroßbritannien
  2. 2.Faculdade de Ciências e TecnologiaUniversidade Nova de LisboaCaparicaPortugal

Personalised recommendations