Utilizing Generalized Learning Automata for Finding Optimal Policies in MMDPs

Multi agent Markov decision processes (MMDPs), as the generalization of Markov decision processes to the multi agent case, have long been used for modeling multi agent system and are used as a suitable framework for Multi agent Reinforcement Learning. In this paper, a generalized learning automata based algorithm for finding optimal policies in MMDP is proposed. In the proposed algorithm, MMDP problem is described as a directed graph in which the nodes are the states of the problem, and the directed edges represent the actions that result in transition from one state to another. Each state of the environment is equipped with a generalized learning automaton whose actions are moving to different adjacent states of that state. Each agent moves from one state to another and tries to reach the goal state. In each state, the agent chooses its next transition with help of the generalized learning automaton in that state. The experimental results have shown that the proposed algorithm have better learning performance in terms of the speed of reaching the optimal policy as compared to existing learning algorithms.