Facing the challenge of human-agent negotiations via effective general opponent modeling

ABSTRACT

Automated negotiation agents capable of negotiating efficiently with people must deal with the fact that people are diverse in their behavior and each individual might negotiate in a different manner. Thus, automated agents must rely on a good opponent modeling component to model their counterpart and adapt their behavior to their partner. In this paper we present the KBAgent. The KBAgent is an automated negotiator that negotiates with each person only once, and uses past negotiation sessions of others as a knowledge base for general opponent modeling. The database is used to extract the likelihood of acceptance and proposals that may be offered by the opposite side. Experiments conducted with people show that the KBAgent negotiates efficiently with people and even achieves better utility values than another automated negotiator, shown to be efficient in negotiations with people. Moreover, the KBAgent achieves significantly better agreements, in terms of individual utility, than the human counterparts playing the same role.

REFERENCES

• 1: M. H. Bazerman and M. A. Neale. Negotiator rationality and negotiator cognition: The interactive roles of prescriptive and descriptive research. In H. P. Young, editor, Negotiation Analysis, pages 109--130. The University of Michigan Press, 1992.
• 2: S. R. Brown and L. E. Melamed. Experimental Design and Analysis. Sage Publications, Inc., CA, USA, 1990.
• 3: Andrew Byde , Mike Yearworth , Kay-Yut Chen , Claudio Bartolini , Nir Vulkan, AutONA: a system for automated multiple 1-1 negotiation, Proceedings of the 4th ACM conference on Electronic commerce, June 09-12, 2003, San Diego, CA, USA [doi>10.1145/779928.779957]
• 4: Robert M. Coehoorn , Nicholas R. Jennings, Learning on opponent's preferences to make effective multi-issue negotiation trade-offs, Proceedings of the 6th international conference on Electronic commerce, October 25-27, 2004, Delft, The Netherlands [doi>10.1145/1052220.1052229]
• 5: R. Cohen. Negotiating Across Cultures: Communication Obstacles in International Diplomacy. United States Institute of Peace Press, Washington, D.C., 1991.
• 6: I. Erev and A. Roth. Predicting how people play games: Reinforcement learning in experimental games with unique, mixed strategy equilibrium. American Economic Review, 88(4):848--881, 1998.
• 7: Ya'akov Gal , Avi Pfeffer , Francesca Marzo , Barbara J. Grosz, Learning social preferences in games, Proceedings of the 19th national conference on Artifical intelligence, p.226-231, July 25-29, 2004, San Jose, California
• 8: Koen Hindriks , Dmytro Tykhonov, Opponent modelling in automated multi-issue negotiation using Bayesian learning, Proceedings of the 7th international joint conference on Autonomous agents and multiagent systems, May 12-16, 2008, Estoril, Portugal
• 9: Ron Katz , Yair Amichai-Hamburger , Efrat Manisterski , Sarit Kraus, Different orientations of males and females in computer-mediated negotiations, Computers in Human Behavior, v.24 n.2, p.516-534, March, 2008 [doi>10.1016/j.chb.2007.02.008]
• 10: D. A. Lax and J. K. Sebenius. Thinking coalitionally: party arithmetic, process opportunism, and strategic sequencing. In H. P. Young, editor, Negotiation Analysis, pages 153--193. The University of Michigan Press, 1992.
• 11: M. LeBaron and V. Pillay. Conflict Across Cultures: A Unique Experience of Bridging Differences. Nicholas Brealey Publishing, Boston, MA, 2006.
• 12: T. Leonard and J. S. J. Hsu. Bayesian Methods - An Analysis for Statisticians and interdisciplinary Researchers. Cambridge University Press, Cambridge, UK, 1999.
• 13: Raz Lin , Sarit Kraus , Jonathan Wilkenfeld , James Barry, Negotiating with bounded rational agents in environments with incomplete information using an automated agent, Artificial Intelligence, v.172 n.6-7, p.823-851, April, 2008 [doi>10.1016/j.artint.2007.09.007]
• 14: R. D. Luce. Individual Choice Behavior: A Theoretical Analysis. John Wiley&Sons, NY, 1959.
• 15: R. D. McKelvey and T. R. Palfrey. An experimental study of the centipede game. Econometrica, 60(4):803--836, 1992.
• 16: J. F. Nash. The bargaining problem. Econ., 18:155--1622, 1950.
• 17: M. J. Osborne and A. Rubinstein. A Course In Game Theory. MIT Press, Cambridge MA, 1994.
• 18: Philippe Pasquier , Ramon Hollands , Frank Dignum , Iyad Rahwan , Liz Sonenberg, An empirical study of interest-based negotiation, Proceedings of the ninth international conference on Electronic commerce, August 19-22, 2007, Minneapolis, MN, USA [doi>10.1145/1282100.1282163]
• 19: Sabyasachi Saha , Anish Biswas , Sandip Sen, Modeling opponent decision in repeated one-shot negotiations, Proceedings of the fourth international joint conference on Autonomous agents and multiagent systems, July 25-29, 2005, The Netherlands [doi>10.1145/1082473.1082534]
• 20: Sabyasachi Saha , Sandip Sen, Negotiating efficient outcomes over multiple issues, Proceedings of the fifth international joint conference on Autonomous agents and multiagent systems, May 08-12, 2006, Hakodate, Japan [doi>10.1145/1160633.1160709]
• 21: S. Siegel. Non-Parametric Statistics for the Behavioral Sciences. McGraw-Hill, NY, USA, 1956.
• 22: David Traum , Stacy C. Marsella , Jonathan Gratch , Jina Lee , Arno Hartholt, Multi-party, Multi-issue, Multi-strategy Negotiation for Multi-modal Virtual Agents, Proceedings of the 8th international conference on Intelligent Virtual Agents, September 01-03, 2008, Tokyo, Japan [doi>10.1007/978-3-540-85483-8_12]
• 23: M. Wand and M. Jones. Kernel Smoothing. Chapman&Hall, London, 1995.

INDEX TERMS

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

General Terms:
Experimentation

Keywords:
automated bilateral negotiation, opponent modeling