Partitioning in multi-agent reinforcement learning

This paper addresses automatic partitioning of state spaces in complex reinforcement learning tasks using multiple agents, without a priori domain knowledge regarding task structures. Partitioning a state/input space into multiple regions helps to exploit differential characteristics of regions and differential characteristics of agents, thus facilitating learning and reducing the complexity of agents especially when function approximators are used. We develop a method for optimizing the partitioning of the space through experience without the use of a priori domain knowledge. The method is experimentally tested and compared to a number of other algorithms. As expected, we found that the multi-agent method with automatic partitioning outperformed single-agent learning.