In this paper, we study a large-scale distributed coordination problem and propose efficient adaptive strategies to solve the problem. The basic problem is to allocate finite number of resources to individual agents such that there is as little congestion as possible and the fraction of unutilized resources is reduced as far as possible. In the absence of a central planner and global information, agents can employ adaptive strategies that uses only finite knowledge about the competitors. In this paper, we show that a combination of finite information sets and reinforcement learning can increase the utilization rate of resources substantially.
↧