Language understanding for text-based games using deep reinforcement learning

Karthik Narasimhan, Tejas D. Kulkarni, Regina Barzilay

Research output: Chapter in Book/Report/Conference proceedingConference contribution

111 Scopus citations

Abstract

In this paper, we consider the task of learning control policies for text-based games. In these games, all interactions in the virtual world are through text and the underlying state is not observed. The resulting language barrier makes such environments challenging for automatic game players. We employ a deep reinforcement learning framework to jointly learn state representations and action policies using game rewards as feedback. This framework enables us to map text descriptions into vector representations that capture the semantics of the game states. We evaluate our approach on two game worlds, comparing against baselines using bag-ofwords and bag-of-bigrams for state representations. Our algorithm outperforms the baselines on both worlds demonstrating the importance of learning expressive representations.1.

Original languageEnglish (US)
Title of host publicationConference Proceedings - EMNLP 2015
Subtitle of host publicationConference on Empirical Methods in Natural Language Processing
PublisherAssociation for Computational Linguistics (ACL)
Pages1-11
Number of pages11
ISBN (Electronic)9781941643327
DOIs
StatePublished - Jan 1 2015
Externally publishedYes
EventConference on Empirical Methods in Natural Language Processing, EMNLP 2015 - Lisbon, Portugal
Duration: Sep 17 2015Sep 21 2015

Publication series

NameConference Proceedings - EMNLP 2015: Conference on Empirical Methods in Natural Language Processing

Other

OtherConference on Empirical Methods in Natural Language Processing, EMNLP 2015
CountryPortugal
CityLisbon
Period9/17/159/21/15

All Science Journal Classification (ASJC) codes

  • Computational Theory and Mathematics
  • Computer Science Applications
  • Information Systems

Fingerprint Dive into the research topics of 'Language understanding for text-based games using deep reinforcement learning'. Together they form a unique fingerprint.

  • Cite this

    Narasimhan, K., Kulkarni, T. D., & Barzilay, R. (2015). Language understanding for text-based games using deep reinforcement learning. In Conference Proceedings - EMNLP 2015: Conference on Empirical Methods in Natural Language Processing (pp. 1-11). (Conference Proceedings - EMNLP 2015: Conference on Empirical Methods in Natural Language Processing). Association for Computational Linguistics (ACL). https://doi.org/10.18653/v1/d15-1001