File(s) under permanent embargo

Moody learners - explaining competitive behaviour of reinforcement learning agents

conference contribution
posted on 01.01.2020, 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.

History

Event

IEEE Computational Intelligence Society. International Conference (10th : 2020 : Online from Valparaíso, Chile)

Series

IEEE Computational Intelligence Society International Conference

Pagination

1 - 8

Publisher

Institute of Electrical and Electronics Engineers

Location

Online from Valparaíso, Chile

Place of publication

Piscataway, N.J.

Start date

26/10/2020

End date

30/10/2020

ISBN-13

9781728173061

Language

eng

Publication classification

E1 Full written paper - refereed

Editor/Contributor(s)

[Unknown]

Title of proceedings

ICDL-EpiRob 2020 : Proceedings of the 10th IEEE International Conference on Development and Learning and Epigenetic Robotics