MULTI-AGENT REINFORCEMENT LEARNING BASED ON QUANTUM ANDANT COLONY ALGORITHM THEORY

In this paper, a novel multi-agent reinforcement learning algorithm is proposed based on Q-Learning, ant colony algorithm and quantum algorithm. As in reinforcement learning algorithm, when the number of agents is large enough, all of the action selection methods will be failed: the speed of learning is decreased sharply. So, we try to combine the ant colony algorithm, quantum algorithm with Q-learning to resolve the above problem. At last, both the theory analysis and experiment result demonstrate that the improved Q-learning is feasible and very efficient.