Pinocchio : Answering Human-Agent Negotiation Questions through Realistic Agent Design

We present the Interactive Arbitration Guide Online (IAGO) platform, a tool for designing human-aware agents for use in negotiation. Current state-of-the-art research platforms are ideally suited for agent-agent interaction. While helpful, these often fail to address the reality of human negotiation, which involves irrational actors, natural language, and deception. To illustrate the strengths of the IAGO platform, the authors describe four agents which are designed to showcase the key design features of the system. We go on to show how these agents might be used to answer core questions in human-centered computing, by reproducing classical human-human negotiation results in a 2x2 human-agent study. The study presents results largely in line with expectations of human-human negotiation outcomes, and helps to demonstrate the validity and usefulness of the IAGO platform.

[1]  Andrew Ortony,et al.  Reducing Mistrust in Agent-Human Negotiations , 2014, IEEE Intelligent Systems.

[2]  Nicholas R. Jennings,et al.  Approximate and online multi-issue negotiation , 2007, AAMAS '07.

[3]  Jonathan Gratch,et al.  Humans versus Computers: Impact of Emotion Expressions on People's Decision Making , 2015, IEEE Transactions on Affective Computing.

[4]  Jonathan Gratch,et al.  The effect of expression of anger and happiness in computer agents on negotiations with humans , 2011, AAMAS.

[5]  H. Chad Lane,et al.  Teaching Negotiation Skills through Practice and Reflection with Virtual Humans , 2006, Simul..

[6]  Koen V. Hindriks,et al.  Accepting optimally in automated negotiation with incomplete information , 2013, AAMAS.

[7]  Jonathan Gratch,et al.  IAGO: Interactive Arbitration Guide Online (Demonstration) , 2016, AAMAS.

[8]  Jonathan Gratch,et al.  IAGO: Interactive Arbitration Guide Online , 2016, AAMAS 2016.

[9]  Jonathan Gratch,et al.  An Effective Conversation Tactic for Creating Value over Repeated Negotiations , 2015, AAMAS.

[10]  C. D. De Dreu,et al.  The interpersonal effects of emotions in negotiations: a motivated information processing approach. , 2004, Journal of personality and social psychology.

[11]  J. Blascovich Social influence within immersive virtual environments , 2002 .

[12]  James J. White Machiavelli and the Bar: Ethical Limitations on Lying in Negotiation , 1980, Discussions in Dispute Resolution.

[13]  Thomas E. Becker,et al.  Lying in negotiations: how individual and situational factors influence the use of neutralization strategies , 2005 .

[14]  Jonathan Gratch,et al.  The Misrepresentation Game: How to win at negotiation while seeming like a nice guy , 2016, AAMAS.

[15]  Jeremy N. Bailenson,et al.  Avatars Versus Agents: A Meta-Analysis Quantifying the Effect of Agency on Social Influence , 2015, Hum. Comput. Interact..

[16]  Sarit Kraus,et al.  Strategic Negotiation in Multiagent Environments , 2001, Intelligent robots and autonomous agents.

[17]  Catholijn M. Jonker,et al.  Virtual Reality Negotiation Training Increases Negotiation Knowledge and Skill , 2012, IVA.

[18]  Philip L. Smith,et al.  Mutually Dependent: Power, Trust, Affect and the Use of Deception in Negotiation , 2009 .

[19]  B. Grosz,et al.  Colored Trails : A Formalism for Investigating Decision-making in Strategic Environments , 2005 .

[20]  Jonathan Gratch,et al.  Trust me: multimodal signals of trustworthiness , 2016, ICMI.

[21]  Nicholas R. Jennings,et al.  Using similarity criteria to make issue trade-offs in automated negotiations , 2002, Artif. Intell..

[22]  Jacques L. Koko,et al.  The Art and Science of Negotiation , 2009 .

[23]  L. Thompson Information exchange in negotiation , 1991 .

[24]  Ya'akov Gal,et al.  A study of computational and human strategies in revelation games , 2014, Autonomous Agents and Multi-Agent Systems.

[25]  Valentin Robu,et al.  Modeling complex multi-issue negotiations using utility graphs , 2005, AAMAS '05.

[26]  Avi Rosenfeld,et al.  NegoChat: a chat-based negotiation agent , 2014, AAMAS.