Decentralized coordination via task decomposition and reward shaping
Atıl Işçen, Kagan Tumer · 2013
In this work, we introduce a method for decentralized co-ordination in cooperative multiagent multi-task problems where the subtasks and agents are homogeneous. Using the method proposed, the agents cooperate at the high level task selection using the knowledge they gather by learning sub-tasks. We introduce a subtask selection method for single agent multi-task MDPs and we extend the work to mul-tiagent multi-task MDPs by using reward shaping at the subtask level to coordinate the agents. Our results on a multi-rover problem show that agents which use the combi-nation of task decomposition and subtask based difference rewards result in significant improvement both in terms of learning speed, and converged policies.