Abstract: We propose using a genetic algorithm to select hyperparameters in multi agent reinforcement learning settings. In particular, we look at this in the context of cooperation and altruism. We show through the use of 3 continuous space games, that certain algorithmic hyperparameters are better suited to allow to agents to learn altruistic behaviors. The agents learn using fuzzy actor critic learning algorithms in either a hierarchical structure or a single actor critic policy. The genetic algorithm selects the discount factors, the reward weights, and the standard deviation of noise applied to actor during learning. The genetic algorithm uses a fitness function based on the ratio of successful tests the group of agents can pass after training. This automated selection of these specific hyperparameters show that they are important for cooperation and also not trivial to select.
PDF
IEEEXplore
Keywords: multi-agent reinforcement learning, altruism, cooperation, fuzzy systems.