A Virtual Maze Game to Explain Reinforcement Learning

Youri Coppens; Eugenio Bargiacchi; Ann Nowe

A Virtual Maze Game to Explain Reinforcement Learning

Youri Coppens, Eugenio Bargiacchi, Ann Nowe

Research output: Chapter in Book/Report/Conference proceeding › Conference paper

83 Downloads (Pure)

Abstract

We demonstrate how Virtual Reality can explain the basic concepts of Reinforcement Learning through an interactive maze game. A player takes the role of an autonomous learning agent and must learn the shortest path to a hidden treasure through experience. This application visualises the learning process of Watkins' Q(λ), one of the fundamental algorithms in the field. A video can be found at https://youtu.be/sLJRiUBhQqM.

Original language	English
Title of host publication	Proceedings of the 31st Benelux Conference on Artificial Intelligence (BNAIC 2019) and the 28th Belgian Dutch Conference on Machine Learning (Benelearn 2019)
Editors	Katrien Beuls, Bart Bogaerts, Gianluca Bontempi, Pierre Geurts, Nick Harley, Bertrand Lebichot, Tom Lenaerts, Gilles Louppe, Paul Van Eecke
Publisher	CEUR Workshop Proceedings
Number of pages	2
Volume	2491
ISBN (Electronic)	1613-0073
Publication status	Published - 8 Nov 2019
Event	BNAIC 2019 - Brussels, Belgium Duration: 7 Nov 2019 → 8 Nov 2019

Conference

Conference	BNAIC 2019
Country/Territory	Belgium
City	Brussels
Period	7/11/19 → 8/11/19

Keywords

Reinforcement Learning
Education
Virtual Reality

Access to Document

Coppens, Bargiacchi, Nowé - 2019 - A Virtual Maze Game to Explain Reinforcement LearningFinal published version, 1.13 MBLicence: CC BY

http://ceur-ws.org/Vol-2491/demo21.pdfLicence: CC BY

Handle.net

Persistent link

FWOAL937: Towards Explainable Reinforcement Learning
Nowe, A. (Administrative Promotor)
1/01/19 → 31/12/22
Project: Fundamental

BNAIC 2019
Coppens, Y. (Participant)
6 Nov 2019 → 8 Nov 2019
Activity: Participating in or organising an event › Participation in conference
A Virtual Maze Game to Explain Reinforcement Learning
Coppens, Y. (Speaker) & Bargiacchi, E. (Speaker)
7 Nov 2019
Activity: Talk or presentation › Talk or presentation at a conference

Cite this

Coppens, Y., Bargiacchi, E., & Nowe, A. (2019). A Virtual Maze Game to Explain Reinforcement Learning. In K. Beuls, B. Bogaerts, G. Bontempi, P. Geurts, N. Harley, B. Lebichot, T. Lenaerts, G. Louppe, & P. Van Eecke (Eds.), Proceedings of the 31st Benelux Conference on Artificial Intelligence (BNAIC 2019) and the 28th Belgian Dutch Conference on Machine Learning (Benelearn 2019) (Vol. 2491). CEUR Workshop Proceedings. http://ceur-ws.org/Vol-2491/demo21.pdf

Coppens, Youri ; Bargiacchi, Eugenio ; Nowe, Ann. / A Virtual Maze Game to Explain Reinforcement Learning. Proceedings of the 31st Benelux Conference on Artificial Intelligence (BNAIC 2019) and the 28th Belgian Dutch Conference on Machine Learning (Benelearn 2019) . editor / Katrien Beuls ; Bart Bogaerts ; Gianluca Bontempi ; Pierre Geurts ; Nick Harley ; Bertrand Lebichot ; Tom Lenaerts ; Gilles Louppe ; Paul Van Eecke. Vol. 2491 CEUR Workshop Proceedings, 2019.

@inproceedings{e2d3dc41173945ea97308a5443950948,

title = "A Virtual Maze Game to Explain Reinforcement Learning",

abstract = "We demonstrate how Virtual Reality can explain the basic concepts of Reinforcement Learning through an interactive maze game. A player takes the role of an autonomous learning agent and must learn the shortest path to a hidden treasure through experience. This application visualises the learning process of Watkins' Q(λ), one of the fundamental algorithms in the field. A video can be found at https://youtu.be/sLJRiUBhQqM.",

keywords = "Reinforcement Learning, Education, Virtual Reality",

author = "Youri Coppens and Eugenio Bargiacchi and Ann Nowe",

year = "2019",

month = nov,

day = "8",

language = "English",

volume = "2491",

editor = "Katrien Beuls and Bart Bogaerts and Gianluca Bontempi and Pierre Geurts and Nick Harley and Bertrand Lebichot and Tom Lenaerts and Gilles Louppe and {Van Eecke}, Paul",

booktitle = "Proceedings of the 31st Benelux Conference on Artificial Intelligence (BNAIC 2019) and the 28th Belgian Dutch Conference on Machine Learning (Benelearn 2019)",

publisher = "CEUR Workshop Proceedings",

note = "BNAIC 2019 ; Conference date: 07-11-2019 Through 08-11-2019",

}

Coppens, Y, Bargiacchi, E & Nowe, A 2019, A Virtual Maze Game to Explain Reinforcement Learning. in K Beuls, B Bogaerts, G Bontempi, P Geurts, N Harley, B Lebichot, T Lenaerts, G Louppe & P Van Eecke (eds), Proceedings of the 31st Benelux Conference on Artificial Intelligence (BNAIC 2019) and the 28th Belgian Dutch Conference on Machine Learning (Benelearn 2019) . vol. 2491, CEUR Workshop Proceedings, BNAIC 2019, Brussels, Belgium, 7/11/19. <http://ceur-ws.org/Vol-2491/demo21.pdf>

A Virtual Maze Game to Explain Reinforcement Learning. / Coppens, Youri; Bargiacchi, Eugenio; Nowe, Ann.
Proceedings of the 31st Benelux Conference on Artificial Intelligence (BNAIC 2019) and the 28th Belgian Dutch Conference on Machine Learning (Benelearn 2019) . ed. / Katrien Beuls; Bart Bogaerts; Gianluca Bontempi; Pierre Geurts; Nick Harley; Bertrand Lebichot; Tom Lenaerts; Gilles Louppe; Paul Van Eecke. Vol. 2491 CEUR Workshop Proceedings, 2019.

Research output: Chapter in Book/Report/Conference proceeding › Conference paper

TY - GEN

T1 - A Virtual Maze Game to Explain Reinforcement Learning

AU - Coppens, Youri

AU - Bargiacchi, Eugenio

AU - Nowe, Ann

PY - 2019/11/8

Y1 - 2019/11/8

N2 - We demonstrate how Virtual Reality can explain the basic concepts of Reinforcement Learning through an interactive maze game. A player takes the role of an autonomous learning agent and must learn the shortest path to a hidden treasure through experience. This application visualises the learning process of Watkins' Q(λ), one of the fundamental algorithms in the field. A video can be found at https://youtu.be/sLJRiUBhQqM.

AB - We demonstrate how Virtual Reality can explain the basic concepts of Reinforcement Learning through an interactive maze game. A player takes the role of an autonomous learning agent and must learn the shortest path to a hidden treasure through experience. This application visualises the learning process of Watkins' Q(λ), one of the fundamental algorithms in the field. A video can be found at https://youtu.be/sLJRiUBhQqM.

KW - Reinforcement Learning

KW - Education

KW - Virtual Reality

M3 - Conference paper

VL - 2491

BT - Proceedings of the 31st Benelux Conference on Artificial Intelligence (BNAIC 2019) and the 28th Belgian Dutch Conference on Machine Learning (Benelearn 2019)

A2 - Beuls, Katrien

A2 - Bogaerts, Bart

A2 - Bontempi, Gianluca

A2 - Geurts, Pierre

A2 - Harley, Nick

A2 - Lebichot, Bertrand

A2 - Lenaerts, Tom

A2 - Louppe, Gilles

A2 - Van Eecke, Paul

PB - CEUR Workshop Proceedings

T2 - BNAIC 2019

Y2 - 7 November 2019 through 8 November 2019

ER -

Coppens Y, Bargiacchi E, Nowe A. A Virtual Maze Game to Explain Reinforcement Learning. In Beuls K, Bogaerts B, Bontempi G, Geurts P, Harley N, Lebichot B, Lenaerts T, Louppe G, Van Eecke P, editors, Proceedings of the 31st Benelux Conference on Artificial Intelligence (BNAIC 2019) and the 28th Belgian Dutch Conference on Machine Learning (Benelearn 2019) . Vol. 2491. CEUR Workshop Proceedings. 2019

A Virtual Maze Game to Explain Reinforcement Learning

Abstract

Conference

Keywords

Access to Document

Handle.net

Fingerprint

Projects

FWOAL937: Towards Explainable Reinforcement Learning

Activities

BNAIC 2019

A Virtual Maze Game to Explain Reinforcement Learning

Cite this