Strategic Information Disclosure to People with Multiple Alternatives

Amos Azaria, Zinovi Rabinovich, Sarit Kraus, Claudia V. Goldman

Research output: Chapter in Book/Report/Conference proceedingConference contributionpeer-review

13 Scopus citations


This paper studies how automated agents can persuade humans to behave in certain ways. The motivation behind such agent's behavior resides in the utility function that the agent's designer wants to maximize and which may be different from the user's utility function. Specifically, in the strategic settings studied, the agent provides correct yet partial information about a state of the world that is unknown to the user but relevant to his decision. Persuasion games were designed to study interactions between automated players where one player sends state information to the other to persuade it to behave in a certain way. We show that this game theory based model is not sufficient to model human-agent interactions, since people tend to deviate from the rational choice. We use machine learning to model such deviation in people from this game theory based model. The agent generates a probabilistic description of the world state that maximizes its benefit and presents it to the users. The proposed model was evaluated in an extensive empirical study involving road selection tasks that differ in length, costs and congestion. Results showed that people's behavior indeed deviated significantly from the behavior predicted by the game theory based model. Moreover, the agent developed in our model performed better than an agent that followed the behavior dictated by the game-theoretical models.

Original languageEnglish
Title of host publicationProceedings of the 25th AAAI Conference on Artificial Intelligence, AAAI 2011
Number of pages7
ISBN (Electronic)9781577355083
StatePublished - 11 Aug 2011
Externally publishedYes
Event25th AAAI Conference on Artificial Intelligence, AAAI 2011 - San Francisco, United States
Duration: 7 Aug 201111 Aug 2011

Publication series

NameProceedings of the 25th AAAI Conference on Artificial Intelligence, AAAI 2011


Conference25th AAAI Conference on Artificial Intelligence, AAAI 2011
Country/TerritoryUnited States
CitySan Francisco


Dive into the research topics of 'Strategic Information Disclosure to People with Multiple Alternatives'. Together they form a unique fingerprint.

Cite this