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.

A Comparison of Humanoid Robot Simulators: A Quantitative Approach

“…In recent years, the number of simulation tools available has grown substantially for the use of different kinds of robots [3]. For the use of humanoid robots, the development of novel solutions represents a complex challenge in the simulation due to the high number of joints, and the contact between different surfaces and textures [4,5]. In this regard, to evaluate available robot simulators, it is an important aspect for the scientific and academic community in order to facilitate the selection of the most suitable simulation tool [6].…”