Multiagent Reinforcement Learning in the Iterated Prisoner´s Dilemma: Fast cooperation through evolved payoffs

In this paper, we investigate the importance of rewards in Multiagent Reinforcement Learning in the context of the Iterated Prisoner´s Dilemma. We use an evolutionary algorithm to evolve valid payoff structures with the aim of encouraging mutual cooperation. An exhaustive analysis is performed by investigating the effect of: i) the lower and upper bounds of the search space of the payoff values, ii) the reward sign, iii) the population size, and iv) the mutation operators used. Our results indicate that valid structures that encourage cooperation can quickly be obtained, while their analysis shows that: i) they should contain a mixture of positive and negative values and ii) the magnitude of the positive values should be much smaller than the magnitude of the negative values.