Acquiring various behaviors by isomorphism of actions in reinforcement learning

The advantage of emergence is that various solutions are emerged. However, it takes large computation cost to emerge them due to the number of iterations of simulation required. So we try to reduces the computation cost without losing variety of solutions by introducing the abstraction technique in artificial intelligence. This paper presents an isomorphism based reinforcement learning by the isomorphism of actions that reduces the learning cost without losing variety of solutions. Isomorphism is one of the concepts in enumerative combinatorics of mathematics. First we explain the isomorphism of actions, we then explain the isomorphism of behaviors. The isomorphic behaviors which perform the same task can be obtained by transforming the learning result of the task by an“appropriate permutation”. This method is significant for realizing the learning of various behaviors for the dynamic environment or multiagent