Moody Learners -- Explaining Competitive Behaviour of Reinforcement Learning Agents

TL;DR

This paper introduces the Moody framework, a novel approach for explaining the decision-making and competitive behavior of reinforcement learning agents by capturing temporal relations in their actions.

Contribution

The paper presents the Moody framework, which enhances understanding of RL agents' competitive dynamics by incorporating temporal relations between actions, demonstrated through experiments in a multiplayer card game.

Findings

Moody framework effectively captures temporal action relations.

Agents using Moody show improved understanding of competitive dynamics.

Framework applicable to complex competitive environments.

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, 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.