关键词: 多Agent系统, 信任模型, Sarsa强化学习

Abstract:

Focusing on the requirement of trust management in multiAgent systems, the sarsa reinforcement learning (SRL) theory is applied to construct trust prediction model for multiAgent systems based on Agent’s behavior. First, basic formal description is conducted for trust decision, and behavior statespace structure is constructed based on timestamp according the interaction time sequence between network Agents. With SRL algorithm, overall trust relationship predicting model based on direct trust degree and feedback trust degree is proposed. The model makes full use of the advantages of the strong dynamic adaptive capacity of the SRL algorithm, brakes away from the inadequate dynamic adaptive capacity in the traditional software trust modeling process. Simulation in cumulative errors shows that, compared to the existing models the new model has remarkable enhancements in the trust decision accuracy.

Key words: multiAgent systems, trust model, Sarsa reinforcement learning