Task allocation method combining reorganization of agent networks and resource estimation in unknown environments

We propose a team formation method that integrates the estimating of the resources of neighboring agents in a hierarchically structured agent network in order to allocate tasks to the agents that have sufficient capabilities for doing tasks. A task for providing the required service in a distributed environment is often achieved by a number of subtasks that are dynamically constructed on demand in a bottom-up manner and then done by the team of appropriate agents. A number of studies were conducted for efficient team formation for quality services. However, most of them assume that resources in other agents are known, and this assumption is not adequate in real world applications. We omitted this assumption and instead extended the conventional team formation method in which learning a team formation is combined with the resource estimation of neighboring agents as well as the reorganization method of the agent network. We experimentally show that this extended method exhibited performance comparable to the conventional methods even though it does not require knowledge of resources in other agents.