Stable repeated strategies for information exchange between two autonomous agents

This paper deals with the problem of designing a strategy profile which will enable collaborative interaction between agents. In particular, we consider the problem of information sharing among agents. Providing information in a single interaction as a response to queries is often nonbeneficial. But there are stable strategy profiles that make sharing information beneficial in the long run. This paper presents there types of mechanisms and specifies under which conditions it is beneficial to the agents to answer queries. We analyze a model of repeated encounters in which two agents ask each other queries over time. We present different strategies that enable information exchange, and compare them according to the expected utility for the agents, and the conditions required for the cooperative equilibrium to exist.

[1]  F. Marmor PROTOCOLS , 1950 .

[2]  Sandip Debnath,et al.  Believing others: pro and cons , 2000, Proceedings Fourth International Conference on MultiAgent Systems.

[3]  W. Hamilton,et al.  The evolution of cooperation. , 1984, Science.

[4]  Moshe Tennenholtz,et al.  Adaptive Load Balancing: A Study in Multi-Agent Learning , 1994, J. Artif. Intell. Res..

[5]  Somesh Jha,et al.  Strategies for Querying Information Agents , 1998, CIA.

[6]  Sanjeev Goyal,et al.  Learning from Neighbors , 1995 .

[7]  Franciszek Seredynski,et al.  Coevolutionary Game-Theoretic Multi-Agent Systems , 1996, ISMIS.

[8]  S. Goyal,et al.  Learning from neighbours , 1998 .

[9]  Patrick Brézillon,et al.  Lecture Notes in Artificial Intelligence , 1999 .

[10]  David Carmel,et al.  Learning Models of Intelligent Agents , 1996, AAAI/IAAI, Vol. 1.

[11]  A. Rubinstein,et al.  Bargaining and Markets. , 1991 .

[12]  W. Raub,et al.  Reputation and Efficiency in Social Interactions: An Example of Network Effects , 1990, American Journal of Sociology.

[13]  Franciszek Seredynski,et al.  Coevolutionary Game-Theoretic Multi-Agent Systems: the Application to Mapping and Scheduling Problem , 1996 .

[14]  SystemsDavid C. Parkes,et al.  Learning and Adaption in Multiagent , 1997 .

[15]  Andrew W. Moore,et al.  Reinforcement Learning: A Survey , 1996, J. Artif. Intell. Res..

[16]  Neeraj Arora,et al.  LEARNING TO TAKE RISKS , 1992 .

[17]  Ronitt Rubinfeld,et al.  Efficient algorithms for learning to play repeated games against computationally bounded adversaries , 1995, Proceedings of IEEE 36th Annual Foundations of Computer Science.

[18]  G. Zacharia Collaborative reputation mechanisms for online communities , 1999 .

[19]  Sandip Sen,et al.  Believing others: Pros and cons , 2002, Artif. Intell..

[20]  Drew Fudenberg,et al.  Game theory (3. pr.) , 1991 .

[21]  R. Radner Repeated Principal-Agent Games with Discounting , 1985 .

[22]  Sandip Sen,et al.  Reciprocity: a foundational principle for promoting cooperative behavior among self-interested agents , 1996 .

[23]  Robert H. Crites,et al.  Multiagent reinforcement learning in the Iterated Prisoner's Dilemma. , 1996, Bio Systems.

[24]  Sandip Sen,et al.  Individual learning of coordination knowledge , 1998, J. Exp. Theor. Artif. Intell..

[25]  Masaki Aoyagi,et al.  Mutual Observability and the Convergence of Actions in a Multi-Person Two-Armed Bandit Model , 1998 .