File(s) under permanent embargo
Moody learners - explaining competitive behaviour of reinforcement learning agents
conference contributionposted on 2020-01-01, 00:00 authored by P Barros, A Tanevska, F Cruz Naranjo, A Sciutti
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.
EventIEEE Computational Intelligence Society. International Conference (10th : 2020 : Online from Valparaíso, Chile)
SeriesIEEE Computational Intelligence Society International Conference
Pagination1 - 8
PublisherInstitute of Electrical and Electronics Engineers
LocationOnline from Valparaíso, Chile
Place of publicationPiscataway, N.J.
Publication classificationE1 Full written paper - refereed
Title of proceedingsICDL-EpiRob 2020 : Proceedings of the 10th IEEE International Conference on Development and Learning and Epigenetic Robotics
Read the peer-reviewed publication
Explainable Artificial IntelligenceReinforcement LearningIntrinsic ConfidenceScience & TechnologyTechnologyComputer Science, Artificial IntelligenceEngineering, Electrical & ElectronicRoboticsComputer ScienceEngineeringExplainable Artificial IntelligenceReinforcement LearningIntrinsic ConfidenceNETWORK