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

Rene Raab*, Kurt Driessens

*Corresponding author for this work

Research output: Chapter in Book/Report/Conference proceedingConference Abstract/Poster in proceedingAcademic

Original languageEnglish
Title of host publicationProceedings of the Reference AI & ML Conference for Belgium, Netherlands & Luxemburg
PublisherCEUR Workshop Proceedings
Volume2491
Publication statusPublished - 2019
Event31st Benelux Conference on Artificial Intelligence and the 28th Belgian Dutch Conference on Machine Learning - Brussels, Belgium
Duration: 6 Nov 20198 Nov 2019
Conference number: 31

Publication series

SeriesCEUR Workshop Proceedings
Volume2491
ISSN1613-0073

Conference

Conference31st Benelux Conference on Artificial Intelligence and the 28th Belgian Dutch Conference on Machine Learning
Abbreviated titleBNAIC/BENELEARN 2019
Country/TerritoryBelgium
CityBrussels
Period6/11/198/11/19

Keywords

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

Cite this