Strategic Advice Provision in Repeated Human-Agent Interactions

This paper addresses the problem of automated advice provision in settings that involve repeated interactions between people and computer agents. This problem arises in many real world applications such as route selection systems and office assistants. To succeed in such settings agents must reason about how their actions in the present influence people’s future actions. This work models such settings as a family of repeated bilateral games of incomplete information called “choice selection processes”, in which players may share certain goals, but are essentially self-interested. The paper describes several possible models of human behavior that were inspired by behavioral economic theories of people’s play in repeated interactions. These models were incorporated into several agent designs to repeatedly generate offers to people playing the game. These agents were evaluated in extensive empirical investigations including hundreds of subjects that interacted with computers in...

• Type: Journal
• Year: 2012
• Where: AAAI
• Authors: Amos Azaria, Zinovi Rabinovich, Sarit Kraus, Claudia V. Goldman, Ya'akov Gal
• Keywords: AAAI 2012, Advice Provision, Empirical Investigations, Intelligent Agents, Work Models