Moody learners - explaining competitive behaviour of reinforcement learning agents

Barros, Pablo, Tanevska, Ana, Cruz Naranjo, Francisco and Sciutti, Alessandra 2020, Moody learners - explaining competitive behaviour of reinforcement learning agents, in ICDL-EpiRob 2020 : Proceedings of the 10th IEEE International Conference on Development and Learning and Epigenetic Robotics, Institute of Electrical and Electronics Engineers, Piscataway, N.J., pp. 1-8, doi: 10.1109/ICDL-EpiRob48136.2020.9278125.

Attached Files
Name Description MIMEType Size Downloads

Title Moody learners - explaining competitive behaviour of reinforcement learning agents
Author(s) Barros, Pablo
Tanevska, Ana
Cruz Naranjo, FranciscoORCID iD for Cruz Naranjo, Francisco orcid.org/0000-0002-1131-3382
Sciutti, Alessandra
Conference name IEEE Computational Intelligence Society. International Conference (10th : 2020 : Online from Valparaíso, Chile)
Conference location Online from Valparaíso, Chile
Conference dates 2020/10/26 - 2020/10/30
Title of proceedings ICDL-EpiRob 2020 : Proceedings of the 10th IEEE International Conference on Development and Learning and Epigenetic Robotics
Editor(s) [Unknown]
Publication date 2020
Series IEEE Computational Intelligence Society International Conference
Start page 1
End page 8
Total pages 8
Publisher Institute of Electrical and Electronics Engineers
Place of publication Piscataway, N.J.
Keyword(s) explainable artificial intelligence
reinforcement learning
intrinsic confidence
Summary 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.
Notes This conference was originally scheduled to be held in Valparaíso, Chile, however due to the 2020 COVID Pandemic, the event was held online.
ISBN 9781728173061
Language eng
DOI 10.1109/ICDL-EpiRob48136.2020.9278125
Indigenous content off
HERDC Research category E1 Full written paper - refereed
Persistent URL http://hdl.handle.net/10536/DRO/DU:30148031

Connect to link resolver
 
Unless expressly stated otherwise, the copyright for items in DRO is owned by the author, with all rights reserved.

Versions
Version Filter Type
Citation counts: TR Web of Science Citation Count  Cited 1 times in TR Web of Science
Scopus Citation Count Cited 2 times in Scopus
Google Scholar Search Google Scholar
Access Statistics: 57 Abstract Views, 2 File Downloads  -  Detailed Statistics
Created: Fri, 12 Feb 2021, 12:38:24 EST

Every reasonable effort has been made to ensure that permission has been obtained for items included in DRO. If you believe that your rights have been infringed by this repository, please contact drosupport@deakin.edu.au.