Negotiation Strategies with Incomplete Information and Social and Cognitive System for Intelligent Human-Agent Interaction
Résumé
Finding the adequate (win-win solutions for both parties) negotiation strategy with incomplete information for autonomous agents, even in one-toone negotiation, is a complex problem. Elsewhere, negotiation behaviors, in which the characters such as conciliatory, neutral, or aggressive define a ‘psychological’ aspect of the negotiator personality, play an important role. More, learning in negotiation is fundamental for understanding human behaviors as well as for developing new solution concepts of teaching methodologies of negotiation strategies (skills). First part of this Chapter aims to develop negotiation strategies for autonomous agents with incomplete information, where negotiation behaviors, based on time-dependent behaviors, are suggested to be used in combination (inspired from empirical human negotiation research). The suggested combination of behaviors allows agents to improve the negotiation process in terms of agent utilities, round number to reach an agreement, and percentage of agreements. Second part of this Chapter aims to develop a SOcial and COgnitive SYStem (SOCOSYS) for learning negotiation strategies from interaction (human-agent or agent-agent), where the characters conciliatory, neutral, or aggressive, are suggested to be integrated in negotiation behaviors (inspired from research works aiming to analyze human behavior and those on social negotiation psychology). The suggested strategy displays the ability to provide agents, through a basic buying strategy, with a first intelligence level, with SOCOSYS to learn from interaction (human-agent or agent-agent).