Action decision congruence between human and deep reinforcement learning agents during a coordinated action task

Research output: Chapter in Book/Report/Conference proceedingConference abstractpeer-review

51 Downloads (Pure)

Abstract

Deep reinforcement learning (DRL) is capable of training agents that exceed human-levels of performance in multi-agenttasks. However, the behaviors exhibited by these agents are not guaranteed to be human-like or human-compatible. Thisposes a problem if the goal is to design agents capable of collaborating with humans or augmenting human actions in co-operative or team-based tasks. Indeed, recommender systems designed to augment human decision-making need to notonly recommend actions that align with the task goal, but which also maintain coordinative behaviors between agents.The current study simultaneously explored skill learning performance of human learners when working alongside dif-ferent artificial agents (AAs) during a collaborative problem-solving task, as well as evaluated the effectiveness of thesame AAs as action decision recommender systems to aid learning. The action decisions of the AAs were either modelledby a heuristic model based on human performance or by a deep neural network trained by reinforcement learning usingself-play. In addition to evaluating skill learning performance, the current study also tested the congruence betweenthe decisions of the AAs with actual decisions made by humans. Results demonstrate that the performance of humanswas significantly worse when working alongside the DRL AA compared to the heuristic AA. Additionally, the actiondecisions participants made also showed less allignment with the recommendations made by the DRL AA.
Original languageEnglish
Title of host publicationProceedings of the 45th Annual Conference of the Cognitive Science Society
EditorsM. Goldwater, F. K. Anggoro, B. K. Hayes, D. C. Ong
Place of PublicationSeattle, WA
PublisherCognitive Science Society
Pages3724
Number of pages1
Publication statusPublished - 2023
EventAnnual Conference of the Cognitive Science Society (45th : 2023) - Sydney, Australia
Duration: 26 Jul 202329 Jul 2023

Publication series

NameAnnual Conference of the Cognitive Science Society
Volume45
ISSN (Electronic)1069-7977

Conference

ConferenceAnnual Conference of the Cognitive Science Society (45th : 2023)
Country/TerritoryAustralia
CitySydney
Period26/07/2329/07/23

Bibliographical note

Copyright the Author(s) 2023. Version archived for private and non-commercial use with the permission of the author/s and according to publisher conditions. For further rights please contact the publisher.

Fingerprint

Dive into the research topics of 'Action decision congruence between human and deep reinforcement learning agents during a coordinated action task'. Together they form a unique fingerprint.

Cite this