A Generative Policy Gradient Approach for Learning to Play Text-Based Adventure Games

Rene Raab; Kurt Driessens

A Generative Policy Gradient Approach for Learning to Play Text-Based Adventure Games

^*Corresponding author for this work

Research output: Chapter in Book/Report/Conference proceeding › Conference Abstract/Poster in proceeding › Academic

Original language	English
Title of host publication	Proceedings of the Reference AI & ML Conference for Belgium, Netherlands & Luxemburg
Publisher	CEUR Workshop Proceedings
Publication status	Published - 2019
Event	31st Benelux Conference on Artificial Intelligence and the 28th Belgian Dutch Conference on Machine Learning - Brussels, Belgium Duration: 6 Nov 2019 → 8 Nov 2019 Conference number: 31

Publication series

Series	CEUR Workshop Proceedings
Volume	2491
ISSN	1613-0073

Conference

Conference	31st Benelux Conference on Artificial Intelligence and the 28th Belgian Dutch Conference on Machine Learning
Abbreviated title	BNAIC/BENELEARN 2019
Country/Territory	Belgium
City	Brussels
Period	6/11/19 → 8/11/19

Keywords

Deep reinforcement learning
Policy gradients
Representation learning
Text-based games
Variational autoencoders

Access to Document

http://ceur-ws.org/Vol-2491/abstract18.pdf

Cite this

@inbook{b22745db796c4883a316a49cc478269c,

title = "A Generative Policy Gradient Approach for Learning to Play Text-Based Adventure Games",

keywords = "Deep reinforcement learning, Policy gradients, Representation learning, Text-based games, Variational autoencoders",

author = "Rene Raab and Kurt Driessens",

year = "2019",

language = "English",

series = "CEUR Workshop Proceedings",

publisher = "CEUR Workshop Proceedings",

booktitle = "Proceedings of the Reference AI & ML Conference for Belgium, Netherlands & Luxemburg",

address = "Germany",

note = "31st Benelux Conference on Artificial Intelligence and the 28th Belgian Dutch Conference on Machine Learning, BNAIC/BENELEARN 2019 ; Conference date: 06-11-2019 Through 08-11-2019",

}

Raab, R & Driessens, K 2019, A Generative Policy Gradient Approach for Learning to Play Text-Based Adventure Games. in Proceedings of the Reference AI & ML Conference for Belgium, Netherlands & Luxemburg. CEUR Workshop Proceedings, CEUR Workshop Proceedings, vol. 2491, 31st Benelux Conference on Artificial Intelligence and the 28th Belgian Dutch Conference on Machine Learning, Brussels, Belgium, 6/11/19. <http://ceur-ws.org/Vol-2491/abstract18.pdf>

A Generative Policy Gradient Approach for Learning to Play Text-Based Adventure Games. / Raab, Rene; Driessens, Kurt.
Proceedings of the Reference AI & ML Conference for Belgium, Netherlands & Luxemburg. CEUR Workshop Proceedings, 2019. (CEUR Workshop Proceedings, Vol. 2491).

Research output: Chapter in Book/Report/Conference proceeding › Conference Abstract/Poster in proceeding › Academic

TY - CHAP

T1 - A Generative Policy Gradient Approach for Learning to Play Text-Based Adventure Games

AU - Raab, Rene

AU - Driessens, Kurt

N1 - Conference code: 31

PY - 2019

Y1 - 2019

KW - Deep reinforcement learning

KW - Policy gradients

KW - Representation learning

KW - Text-based games

KW - Variational autoencoders

M3 - Conference Abstract/Poster in proceeding

T3 - CEUR Workshop Proceedings

BT - Proceedings of the Reference AI & ML Conference for Belgium, Netherlands & Luxemburg

PB - CEUR Workshop Proceedings

T2 - 31st Benelux Conference on Artificial Intelligence and the 28th Belgian Dutch Conference on Machine Learning

Y2 - 6 November 2019 through 8 November 2019

ER -