Learning sequences of compatible actions among agents

Action coordination in multiagent systems is a difficult task especially in dynamic environments. If the environment possesses cooperation, least communication, incompatibility and local information constraints, the task becomes even more difficult. Learning compatible action sequences to achieve a designated goal under these constraints is studied in this work. Two new multiagent learning algorithms called QACE and NoCommQACE are developed. To improve the performance of the QACE and NoCommQACE algorithms four heuristics, state iteration, means-ends analysis, decreasing reward and do-nothing, are developed. The proposed algorithms are tested on the blocks world domain and the performance results are reported.