Negotiation Behaviors Based on Artificial Intelligence and Social and Cognitive Human-Agent Interaction

Behaviors, in which the characters such as conciliatory (Con), neutral (Neu), or aggressive (Agg) define a ´psychological´ aspect of the human personality, play an important role for negotiation agent. Elsewhere, learning in negotiation is fundamental for understanding human behaviors as well as for developing new solution concepts. In this paper, a brief description of SISINE (Integrated System of Simulation for Negotiation) project, which aims to develop innovative teaching methodology of negotiation skills, is given. Then, a negotiation strategy essentially based on negotiation behaviors of the human personality is suggested for SISINE. Such negotiation behaviors which are based on the characters Con, Neu, and Agg, and acquired first by reinforcement learning (Q-learning, and Sarsa-Learning) approaches, and second by Neural Networks (NN) are then developed. From this, the suggested strategy is developed and the negotiation behavior results presented. The suggested strategy displays the ability to provide agents, through a basic buying strategy, with a first intelligence level.