Programming agents as a means of capturing self-strategy

ABSTRACT

In this paper we report results of an extensive evaluation of people's ability to reproduce the strategies they use in simple real-life settings. Having the ability to reliably capture people's strategies in different environments is highly desirable in Multi-Agent Systems (MAS). However, as trivial and daily as these strategies are, the process is not straightforward and people often have a different belief of how they act. We describe our experiments in this area, based on the participation of a pool of subjects in four different games with variable complexity and characteristics. The main measure used for determining the closeness between the two types of strategies used is the level of similarity between the actions taken by the participants and those taken by agents they programmed in identical world states. Our results indicate that generally people have the ability to reproduce their game strategies for the class of games we consider. However, this process should be handled carefully as some individuals tend to exhibit a behavior different from the one they program into their agents. The paper evaluates one possible method for enhancing the process of strategy reproduction.

REFERENCES

• 1: M. Bertrand and S. Mullainathan. Do people mean what they say? implications for subjective survey data. American Economic Review, 91(2):67--72, 2001.
• 2: Michal Chalamish , David Sarne , Sarit Kraus, Mass programmed agents for simulating human strategies in large scale systems, Proceedings of the 6th international joint conference on Autonomous agents and multiagent systems, May 14-18, 2007, Honolulu, Hawaii [doi>10.1145/1329125.1329291]
• 3: A. Chavez and P. Maes. Kasbah: An agent marketplace for buying and selling goods. In PAAM, 1996.
• 4: J. Eichberger, W. Güth, and W. Müller. Attitudes towards risk: An experiment. Metroeconomica, 54(1):89--124, February 2003.
• 5: H. C. T. Force. A report on the use of traffic simulation models in the san diego region. Technical report, Institute of Transportation Engineers, Highway Capacity Task Force, 2004.
• 6: H. Futura and M. Yashui. Evacuation simulation in underground mall by artificial life technology. In ISUMA, 2003.
• 7: Nathan Griffiths , Michael Luck, Coalition formation through motivation and trust, Proceedings of the second international joint conference on Autonomous agents and multiagent systems, July 14-18, 2003, Melbourne, Australia [doi>10.1145/860575.860579]
• 8: Barbara J. Grosz , Sarit Kraus , Shavit Talman , Boaz Stossel , Moti Havlin, The Influence of Social Dependencies on Decision-Making: Initial Investigations with a New Game, Proceedings of the Third International Joint Conference on Autonomous Agents and Multiagent Systems, p.782-789, July 19-23, 2004, New York, New York [doi>10.1109/AAMAS.2004.264]
• 9: C. Harries, J. S. Evans, and I. Dennis. Measuring doctors' self-insight into their treatment decisions. Applied Cognitive Psychology, 14:455--477, 2000.
• 10: G. Kempen, M. van Heuvelen, R. van den Brink, A. Kooijman, M. Klein, P. Houx, and J. Ormel. Factors affecting contrasting results between self-reported and performance-based levels of physical limitations. Age and Ageing, 25(6):458--464, 1996.
• 11: D. Massaguer, V. Balasubramanian, S. Mehrotra, and N. Venkatasubramanian. Multi-agent simulation of disaster response. In ATDM AAMAS, 2006.
• 12: Daniel Massaguer , Vidhya Balasubramanian , Sharad Mehrotra , Nalini Venkatasubramanian, Synthetic humans in emergency response drills, Proceedings of the fifth international joint conference on Autonomous agents and multiagent systems, May 08-12, 2006, Hakodate, Japan [doi>10.1145/1160633.1160919]
• 13: Yohei Murakami , Kazuhisa Minami , Tomoyuki Kawasoe , Toru Ishida, Multi-Agent Simulation for Crisis Management, Proceedings of the IEEE Workshop on Knowledge Media Networking, p.135, July 10-12, 2002
• 14: Y. Murakami, Y. Sugimoto, and T. Ishida. Modeling human behavior for virtual training systems. In AAAI, 2005.
• 15: M. Rabin. Psychology and economics. Journal of Economic Literature, 36(1):11--46, March 1998.
• 16: Gita Sukthankar , Katia Sycara, Policy recognition for multi-player tactical scenarios, Proceedings of the 6th international joint conference on Autonomous agents and multiagent systems, May 14-18, 2007, Honolulu, Hawaii [doi>10.1145/1329125.1329145]
• 17: Tomoichi Takahashi , Satoshi Tadokoro , Masayuki Ohta , Nobuhiro Ito, Agent Based Approach in Disaster Rescue Simulation - From Test-Bed of Multiagent System to Practical Application, RoboCup 2001: Robot Soccer World Cup V, p.102-111, January 2002
• 18: M. Twyman, C. Harries, and N. Harvey. Learning to use and assess advice about risk. Forum: Qualitative Social Research, 7(1), 2006.
• 19: B. Ulicny and D. Thalmann. Towards interactive real-time crowd behavior simulation. Computer Graphics Forum, 2002.
• 20: M. L. Weitzman. Optimal search for the best alternative. Econometrica, 47(3):641--54, May 1979.
• 21: Y. Zhang, K. Biggers, L. He, S. Reddy, D. Sepulvado, J. Yen, and T. Ioerger. A distributed intelligent agent architecture for simulating aggregate-level behavior and interactions on the battlefield. In SCI, pages 58--63, 2001.
• 22: B. J. Zikmund-Fisher. De-escalation after repeated negative feedback: emergent expectations of failure. JBDM, 54:365--379, 2004.

INDEX TERMS

Primary Classification:
  I. Computing Methodologies
  I.2 ARTIFICIAL INTELLIGENCE
        I.2.11 Distributed Artificial Intelligence

General Terms:
Experimentation, Human Factors

Keywords:
human behavior, large-scale MAS, strategic behavior