An Adaptive Multi-agent Model for Automated Negotiation

The paper presents a model of heuristic negotiation between self-interested agents, which allows negotiation over multiple issues and learns the agent´s negotiation strategy. The agents are using different strategies to negotiate and several models to adjust their decision during negotiation. They are capable of increasing their performance with the experience, by adapting to the environment conditions. The agents´ performance, using multiple tactics, is compared to the agents having learning capabilities, based on reinforcement learning techniques. Several tests are performed, in a scenario similar to the TAC-SCM environment.