Moody Learners - Explaining Competitive Behaviour of Reinforcement Learning Agents

Abstract

Designing the decision-making processes of artificial agents that are involved in competitive interactions is a challenging task. In a competitive scenario, the agent does not only have a dynamic environment but also is directly affected by the opponents' actions. Observing the Q-values of the agent is usually a way of explaining its behavior, however, it does not show the temporal-relation between the selected actions. We address this problem by proposing the Moody framework that creates an intrinsic representation for each agent based on the Pleasure/Arousal model. We evaluate our model by performing a series of experiments using the competitive multiplayer Chef's Hat card game and discuss how by observing the intrinsic state generated by our model allows us to obtain a holistic representation of the competitive dynamics within the game.