Moody Learners -- Explaining Competitive Behaviour of Reinforcement Learning Agents
This work addresses the problem of interpreting agent behavior in competitive scenarios for researchers and practitioners in reinforcement learning, but it appears incremental as it builds on existing explanation methods.
The paper tackled the challenge of explaining competitive behavior in reinforcement learning agents by proposing the Moody framework, which provides a holistic representation of competitive dynamics, as demonstrated through experiments in the Chef's Hat card game.
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, do not show the temporal-relation between the selected actions. We address this problem by proposing the \emph{Moody framework}. We evaluate our model by performing a series of experiments using the competitive multiplayer Chef's Hat card game and discuss how our model allows the agents' to obtain a holistic representation of the competitive dynamics within the game.