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 these 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. 2003 Elsevier B.V. All rights reserved.

• Type: Journal
• Year: 2004
• Where: AI
• Authors: Rina Azoulay-Schwartz, Sarit Kraus
• Keywords: AI 2004, Artificial Intelligence, Collaborative Interaction, Information, Strategy Profile