Artificial Neural Network Ensemble Approach for Creating a Negotiation Model with Ethical Artificial Agents

Negotiation is one of the most prevalent methods that agents, in a multi-agent system, use to reach agreements. Nowadays, one important aspect of negotiation is moral behaviors of agents that involve in negotiation. For this reason, we propose an ethical classifier that uses artificial neural networks ensembles. To evaluate the performance of the proposed method, we conduct experiments including comparisons with alternative methods for ethical classification. As the result of experiments suggest, the proposed method shows improved ethical recognition performance, in comparison with other widely used methods.