318
views
0
recommends
+1 Recommend
0 collections
    0
    shares
      • Record: found
      • Abstract: found
      • Article: found
      Is Open Access

      Language Understanding for Text-based Games Using Deep Reinforcement Learning

      Preprint
      , ,

      Read this article at

          There is no author summary for this article yet. Authors can add summaries to their articles on ScienceOpen to make them more accessible to a non-specialist audience.

          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-of-words and bag-of-bigrams for state representations. Our algorithm outperforms the baselines on both worlds demonstrating the importance of learning expressive representations.

          Related collections

          Most cited references4

          • Record: found
          • Abstract: not found
          • Conference Proceedings: not found

          Improved Semantic Representations From Tree-Structured Long Short-Term Memory Networks

            Bookmark
            • Record: found
            • Abstract: not found
            • Article: not found

            Prioritized sweeping: Reinforcement learning with less data and less time

              Bookmark
              • Record: found
              • Abstract: not found
              • Book Chapter: not found

              Learning to Parse Natural Language Commands to a Robot Control System

                Bookmark

                Author and article information

                Journal
                2015-06-30
                2015-09-11
                Article
                1506.08941
                be628682-ee91-4d95-9e20-e384d7019b8a

                http://arxiv.org/licenses/nonexclusive-distrib/1.0/

                History
                Custom metadata
                11 pages, Appearing at EMNLP, 2015
                cs.CL cs.AI

                Theoretical computer science,Artificial intelligence
                Theoretical computer science, Artificial intelligence

                Comments

                Comment on this article