Adaptive manager-side control policy in contract net protocol for massively multi-agent systems

We describe a new adaptive manager-side control policy for the contract net protocol for a massively multi-agent system (MMAS). To improve overall performance of MMAS, tasks must be allocated to appropriate agents. From this viewpoint, a number of negotiation protocols were proposed in the MAS context, but most assume a small-scale, unbusy environment. We previously reported that, using contract net protocol (CNP), the overall efficiency could improve by an adequate control of degree of fluctuation in the awarding phase depending on the state of MMAS. In this paper, we propose the method to estimate these states from the bid values, which have hitherto not been used effectively. Then the manager-side policy flexibly and autonomously with some degree of fluctuation responsive to the estimated states is introduced. We also evaluate that our proposed CNP policy.