Cooperative Behavior of Agents That Model the Other and the Self in Noisy Iterated Prisoners´ Dilemma Simulation

We developed self learning for simulation study of mutual understanding between peer agents. We designed them to use various types of coplayer models and a reinforcement learning algorithm to learn to play a noisy iterated prisoners\´ dilemma game so that the pay-off for the agent itself is maximized. We measured the mutual-modeling ability of each type of agent in terms of cooperative behavior when playing with another equivalent agent. We observed that agents with a complex coplayer model, which includes a model of the agent itself, showed higher cooperation than agents with a simpler coplayer model only. Moreover, in low-noise environments, Level-M agent, which develops equivalent models of the self and the other, showed higher cooperation than other types of agents. These results suggest the importance of "self-observation" in the design of communicative agents