Agents' uncertainty in argumentation-based negotiation: Classification and implementation

In this paper, we tackle the problem of uncertainty in argumentation-based agent negotiation by analyzing the different situations of this uncertainty. In particular, we analyze two types of agents' uncertainty called Type I and Type II. Uncertainty Type I is the agent's uncertainty about selecting the right moves during the dialogue. Uncertainty Type II is the agent's uncertainty that the selected move will be accepted by the addressee. More precisely, we discuss these uncertainties in two cases based on the different classes that arguments can belong to. In addition to the theoretical analysis of arguments uncertainty, we implemented the proposed approach by applying it on a concrete case study (Buyer/Seller scenario). The obtained empirical results confirm the effectiveness of using our uncertainty-aware techniques and show that our negotiating agents outperform others (which do not use such techniques). We believe that such analysis will advance the research in the area of argumentation-based negotiation in multiagent systems and contribute to the automation of the agents' negotiation.