Fight, Flight, or Negotiate: Believable Strategies for Conversing Under Crisis

This paper describes a model of conversation strategies implemented in virtual humans designed to help people learn negotiation skills. We motivate and discuss these strategies and their use to allow a virtual human to engage in complex adversarial negotiation with a human trainee. Choice of strategy depends on both the personality of the agent and assessment of the likelihood that the negotiation can be beneficial. Execution of strategies can be performed by choosing specific dialogue behaviors such as whether and how to respond to a proposal. Current assessment of the value of the topic, the utility of the strategy, and affiliation toward the other conversants can be used to dynamically change strategies throughout the course of a conversation. Examples will be given from the SASO-ST project, in which a trainee learns to negotiate by interacting with virtual humans who employ these strategies.

[1]  Jeffrey S. Rosenschein,et al.  Rules of Encounter - Designing Conventions for Automated Negotiation among Computers , 1994 .

[2]  David R. Traum,et al.  Negotiation over tasks in hybrid human-agent teams for simulation-based training , 2003, AAMAS '03.

[3]  David R. Traum,et al.  Embodied agents for multi-party dialogue in immersive virtual worlds , 2002, AAMAS '02.

[4]  David V. Pynadath,et al.  PsychSim: Agent-based Modeling of Social Interactions and Influence , 2004, ICCM.

[5]  Rose Dieng,et al.  Computational Conflicts: Conflict Modeling for Distributed Intelligent Systems , 2000 .

[6]  K. Scherer,et al.  Appraisal processes in emotion. , 2003 .

[7]  David R. Traum,et al.  Evaluation of Multi-party Virtual Reality Dialogue Interaction , 2004, LREC.

[8]  R. Walton,et al.  A Behavioral Theory of Labor Negotiations: an Analysis of a Social Interaction System , 1965 .

[9]  James F. Allen,et al.  A Plan Recognition Model for Subdialogues in Conversations , 1987, Cogn. Sci..

[10]  Stacy Marsella,et al.  A domain-independent framework for modeling emotion , 2004, Cognitive Systems Research.

[11]  Randall W. Hill,et al.  Steve Goes to Bosnia: Towards a New Generation of Virtual Humans for Interactive Experiences , 2001 .

[12]  Linda L. Putnam,et al.  Reciprocity in negotiations: An analysis of bargaining interaction , 1982 .

[13]  Randall W. Hill,et al.  Toward a New Generation of Virtual Humans for Interactive Experiences , 2002, IEEE Intell. Syst..

[14]  Alan L. Sillars,et al.  CODING VERBAL CONFLICT TACTICS: NONVERBAL AND PERCEPTUAL CORRELATES OF THE “AVOIDANCE‐DISTRIBUTIVE‐INTEGRATIVE” DISTINCTION , 1982 .

[15]  David R. Traum,et al.  Modelling Grounding and Discourse Obligations Using Update Rules , 2000, ANLP.

[16]  Justine Cassell,et al.  Relational agents: a model and implementation of building user trust , 2001, CHI.

[17]  J. Cassell,et al.  Embodied conversational agents , 2000 .

[18]  Linda L. Putnam,et al.  Interaction Goals in Negotiation , 1990 .

[19]  Wenji Mao,et al.  Social judgment in multiagent interactions , 2004, Proceedings of the Third International Joint Conference on Autonomous Agents and Multiagent Systems, 2004. AAMAS 2004..