Using Awareness to Promote Richer, More Human-Like Behaviors in Artificial Agents

  • Logan YliniemiEmail author
  • Kagan Tumer
Conference paper
Part of the Lecture Notes in Computer Science book series (LNCS, volume 10003)


The agents community has produced a wide variety of compelling solutions for many real-world problems, and yet there is still a significant disconnect between the behaviors that an agent can learn and those that exemplify the rich behaviors exhibited by humans. This problem exists both with agents interacting solely with an environment, as well as agents interacting with other agents. The solutions created to date are typically good at solving a single, well-defined problem with a particular objective, but lack in generalizability.

In this work, we discuss the possibility of using an awareness framework, coupled with the optimization of multiple dynamic objectives, in tandem with the cooperation and coordination concerns intrinsic to multiagent systems, to create a richer set of agent behaviors. We propose future directions of research that may lead toward more-human capabilities in general agent behaviors.


Indifference Curve Context Switch Human Decision Making Process Complex Optimization Problem Preference Curve 
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.


  1. 1.
    Agogino, A., Tumer, K.: Entropy based anomaly detection applied to space shuttle main engines. In: IEEE Aerospace Conference (2006)Google Scholar
  2. 2.
    Athan, T.W., Papalambros, P.Y.: A note on weighted criteria methods for compromise solutions in multi-objective optimization. Eng. Optim. 27, 155–176 (1996)CrossRefGoogle Scholar
  3. 3.
    Barrett, S., Stone, P.: Cooperating with unknown teammates in complex domains: a robot soccer case study of ad hoc teamwork. In: Proceedings of the Twenty-Ninth AAAI Conference on Artificial Intelligence, January 2015Google Scholar
  4. 4.
    Bloembergen, D., Hennes, D., McBurney, P., Tuyls, K.: Trading in markets with noisy information: an evolutionary analysis. Connection Sci. 27(3), 253–268 (2015)CrossRefGoogle Scholar
  5. 5.
    Brézillon, P.: Context in artificial intelligence: I. a survey of the literature. Comput. Artif. Intell. 18, 321–340 (1999)zbMATHGoogle Scholar
  6. 6.
    Brys, T., Harutyunyan, A., Vrancx, P., Taylor, M.E., Kudenko, D., Nowé, A.: Multi-objectivization of reinforcement learning problems by reward shaping. In: 2014 International Joint Conference on Neural Networks (IJCNN), pp. 2315–2322. IEEE (2014)Google Scholar
  7. 7.
    Brys, T., Taylor, M.E., Nowé, A.: Using ensemble techniques and multi-objectivization to solve reinforcement learning problems. In: ECAI, pp. 981–982 (2014)Google Scholar
  8. 8.
    Carlson, A., Betteridge, J., Kisiel, B., Settles, B., Hruschka Jr., E.R., Mitchell, T.M.: Toward an architecture for never-ending language learning. In: AAAI, vol. 5, p. 3 (2010)Google Scholar
  9. 9.
    Das, I., Dennis, J.E.: A closer look at drawbacks of minimizing weighted sums of objectives for pareto set generation in multicriteria optimization problems. Struct. Optim. 14, 63–69 (1997)CrossRefGoogle Scholar
  10. 10.
    Deb, K., Pratap, A., Agarwal, S., Meyarivan, T.: A fast elitist multi-objective genetic algorithm: NSGA-II. Evol. Comput. 6, 182–197 (2002)CrossRefGoogle Scholar
  11. 11.
    Edgeworth, F.Y., Psychics, M.: An Essay on the Application of Mathematics to Moral Sciences. C. Kegan Paul and Company, London (1881)Google Scholar
  12. 12.
    Elidrisi, M., Johnson, N., Gini, M.: Fast learning against adaptive adversarial opponents. In: Proceedings of the 11th International Conference on Autonomous Agents and Multiagent Systems, November 2012, Valencia, Spain (2012)Google Scholar
  13. 13.
    Erickson, T.: Some problems with the notion of context-aware computing. Commun. ACM 45(2), 102–104 (2002)CrossRefGoogle Scholar
  14. 14.
    Fagin, R., Halpern, J.Y.: Belief, awareness, and limited reasoning. Artif. Intell. 34(1), 39–76 (1987)MathSciNetzbMATHCrossRefGoogle Scholar
  15. 15.
    Feil-Seifer, D.: Distance-based computational models for facilitating robot interaction with children. J. Hum. Rob. Interact. 1(1), 55–77 (2012)CrossRefGoogle Scholar
  16. 16.
    Flener, P., Pearson, J., Ågren, M., Garcia-Avello, C., Celiktin, M., Dissing, S.: Air-traffic complexity resolution in multi-sector planning. J. Air Transp. Manage. 13(6), 323–328 (2007)CrossRefGoogle Scholar
  17. 17.
    Ghosh, A., Sen, S.: Agent-based distributed intrusion alert system. In: Sen, A., Das, N., Das, S.K., Sinha, B.P. (eds.) IWDC 2004. LNCS, vol. 3326, pp. 240–251. Springer, Heidelberg (2004). doi: 10.1007/978-3-540-30536-1_28 CrossRefGoogle Scholar
  18. 18.
    Giagkiozis, I., Fleming, P.J.: Methods for multi-objective optimization: an analysis. Inform. Sci. 293, 338–350 (2015)MathSciNetCrossRefGoogle Scholar
  19. 19.
    Hernandez-Leal, P., Munoz de Cote, E., Sucar, L.E.: A framework for learning and planning against switching strategies in repeated games. Connection Sci. 26(2), 103–122 (2014)CrossRefGoogle Scholar
  20. 20.
    Holmes Jr., O.W.: U.S. supreme court opinion: Schenck v. United States (1919)Google Scholar
  21. 21.
    Jeyadevi, S., Baskar, S., Babulal, C.K., Iruthayarajan, M.W.: Solving multiobjective optimal reactive power dispatch using modified NSGA-II. Int. J. Electr. Power Energ. Syst. 33(2), 219–228 (2011)CrossRefGoogle Scholar
  22. 22.
    Kaluža, B., Kaminka, G.A., Tambe, M.: Detection of suspicious behavior from a sparse set of multiagent interactions. In: Proceedings of the 11th International Conference on Autonomous Agents and Multiagent Systems, vol. 2, pp. 955–964. International Foundation for Autonomous Agents and Multiagent Systems (2012)Google Scholar
  23. 23.
    Lenat, D.B.: CYC: a large-scale investment in knowledge infrastructure. Commun. ACM 38(11), 33–38 (1995)CrossRefGoogle Scholar
  24. 24.
    Lenat, D.B., Guha, R.V., Pittman, K., Pratt, D., Shepherd, M.: CYC: toward programs with common sense. Commun. ACM 33(8), 30–49 (1990)CrossRefGoogle Scholar
  25. 25.
    Marler, R.T., Arora, J.S.: The weighted sum method for multi-objective optimization: new insights. Struct. Multi. Optim. 41, 853–862 (2009)MathSciNetzbMATHCrossRefGoogle Scholar
  26. 26.
    Marler, R.T., Arora, J.S.: Survey of multi-objective optimization methods for engineering. Struct. Multi. Optim. 26, 369–395 (2004)MathSciNetzbMATHCrossRefGoogle Scholar
  27. 27.
    McCarthy, J.: Programs with Common Sense. Defense Technical Information Center, Panama (1963)Google Scholar
  28. 28.
    McCarthy, J.: Generality in artificial intelligence. Commun. ACM 30(12), 1030–1035 (1987)MathSciNetzbMATHCrossRefGoogle Scholar
  29. 29.
    McCarthy, J.: Artificial intelligence, logic and formalizing common sense. In: Thomason, R.H. (ed.) Philosophical logic and artificial intelligence, pp. 161–190. Springer, Netherlands (1989)CrossRefGoogle Scholar
  30. 30.
    Messac, A., Hattis, P.D.: Physical programming design optimization for high speed civil transport (HSCT). J. Aircr. 33(2), 446–449 (1996)CrossRefGoogle Scholar
  31. 31.
    Pareto, V.: Manuale di Economia Politica. Piccola Biblioteca Scientifica, Societa Editrice Libraria (1906)Google Scholar
  32. 32.
    Pareto, V.: Manual of Political Economy. MacMillan Press Ltd., London (1927)Google Scholar
  33. 33.
    Pěchouček, M., Mařík, V.: Industrial deployment of multi-agent technologies: review and selected case studies. Auton. Agent. Multi-Agent Syst. 17(3), 397–431 (2008)CrossRefGoogle Scholar
  34. 34.
    Penn, R., Friedler, E., Ostfeld, A.: Multi-objective evolutionary optimization for greywater reuse in municipal sewer systems. Water Res. 47(15), 5911–5920 (2013)CrossRefGoogle Scholar
  35. 35.
    Powe, L.A.: Searching for the false shout of fire. Const. Comment. 19, 345 (2002)Google Scholar
  36. 36.
    Sato, H.: Inverted PBI in MOEA/D and its impact on the search performance on multi and many-objective optimization. In: Proceedings of the 2014 Conference on Genetic and Evolutionary Computation, pp. 645–652. ACM (2014)Google Scholar
  37. 37.
    Sato, H.: MOEA/D using constant-distance based neighbors designed for many-objective optimization. In: 2015 IEEE Congress on Evolutionary Computation (CEC), pp. 2867–2874. IEEE (2015)Google Scholar
  38. 38.
    Sen, S., Sekaran, M., Hale, J.: Learning to coordinate without sharing information. In: AAAI, pp. 426–431 (1994)Google Scholar
  39. 39.
    Serafini, L., Bouquet, P.: Comparing formal theories of context in AI. Artif. Intell. 155(1), 41–67 (2004)MathSciNetzbMATHCrossRefGoogle Scholar
  40. 40.
    Shaw, R.: Don’t panic: behaviour in major incidents. Disaster Prev. Manag. Int. J. 10(1), 5–10 (2001)CrossRefGoogle Scholar
  41. 41.
    Tambe, M.: Electric elves: what went wrong and why. AI Mag. 29(2), 23 (2008)Google Scholar
  42. 42.
    Tambe, M., Scerri, P., Pynadath, D.V.: Adjustable autonomy for the real world. J. Artif. Intell. Res. 17(1), 171–228 (2002)MathSciNetzbMATHGoogle Scholar
  43. 43.
    Taylor, M.E., Kuhlmann, G., Stone, P.: Autonomous transfer for reinforcement learning. In: Proceedings of the 7th International Joint Conference on Autonomous Agents And Multiagent Systems, vol. 1, pp. 283–290. International Foundation for Autonomous Agents and Multiagent Systems (2008)Google Scholar
  44. 44.
    Taylor, M.E., Stone, P.: An introduction to intertask transfer for reinforcement learning. AI Mag. 32(1), 15 (2011)Google Scholar
  45. 45.
    Thrun, S., Mitchell, T.M.: Lifelong robot learning. In: Steels, L. (ed.) The Biology and Technology of Intelligent Autonomous Agents. NATO ASI Series, vol. 144, pp. 165–196. Springer, Heidelberg (1995)CrossRefGoogle Scholar
  46. 46.
    Tumer, K., Agogino, A.: Distributed agent-based air traffic flow management. In: Proceedings of the 6th International Joint Conference on Autonomous Agents and Multiagent Systems, p. 255. ACM (2007)Google Scholar
  47. 47.
    Wang, Z., Boularias, A., Mülling, K., Peters, J.: Balancing safety and exploitability in opponent modeling. In: AAAI (2011)Google Scholar
  48. 48.
    Wendland, M.F.: The calumet tragedy + death of a city in Northern Michigan, 1913–1914. Am. Heritage 37(3), 39 (1986)Google Scholar
  49. 49.
    Xu, H., Zhang, Z., Alipour, K., Xue, K., Gao, X.Z.: Prototypes selection by multi-objective optimal design: application to a reconfigurable robot in sandy terrain. Ind. Rob. Int. J. 38(6), 599–613 (2011)CrossRefGoogle Scholar
  50. 50.
    Yang, R., Ford, B., Tambe, M., Lemieux, A.: Adaptive resource allocation for wildlife protection against illegal poachers. In: Proceedings of the 2014 International Conference on Autonomous Agents and Multi-agent Systems, pp. 453–460. International Foundation for Autonomous Agents and Multiagent Systems (2014)Google Scholar
  51. 51.
    Yliniemi, L., Agogino, A.K., Tumer, K.: Evolutionary agent-based simulation of the introduction of new technologies in air traffic management. In: Genetic and Evolutionary Computation Conference (GECCO) (2014)Google Scholar
  52. 52.
    Yliniemi, L., Agogino, A.K., Tumer, K.: Multirobot coordination for space exploration. AI Mag. 4(35), 61–74 (2014)Google Scholar
  53. 53.
    Yliniemi, L., Tumer, K.: Multi-objective multiagent credit assignment through difference rewards in reinforcement learning. In: Dick, G., et al. (eds.) SEAL 2014. LNCS, vol. 8886, pp. 407–418. Springer, Heidelberg (2014). doi: 10.1007/978-3-319-13563-2_35 Google Scholar
  54. 54.
    Yliniemi, L., Tumer, K.: PaCcET: an objective space transformation to iteratively convexify the Pareto front. In: Dick, G., et al. (eds.) SEAL 2014. LNCS, vol. 8886, pp. 204–215. Springer, Heidelberg (2014). doi: 10.1007/978-3-319-13563-2_18 Google Scholar
  55. 55.
    Yliniemi L., Tumer, K.: Complete coverage in the multi-objective PaCcET framework. In: Silva, S. (ed.) Genetic and Evolutionary Computation Conference (2015)Google Scholar
  56. 56.
    Yliniemi, L., Wilson, D., Tumer, K.: Multi-objective multiagent credit assignment in NSGA-II using difference evaluations. In: Proceedings of the 2015 International Conference on Autonomous Agents and Multiagent Systems, pp. 1635–1636. International Foundation for Autonomous Agents and Multiagent Systems (2015)Google Scholar
  57. 57.
    Zitzler, E., Laumanns, M., Thiele, L.: SPEA2: improving the strength Pareto evolutionary algorithm. Comput. Eng. 3242(103) (2001)Google Scholar

Copyright information

© Springer International Publishing AG 2016

Authors and Affiliations

  1. 1.University of Nevada, RenoRenoUSA
  2. 2.Oregon State UniversityCorvallisUSA

Personalised recommendations