Language Understanding for Text-based Games using Deep Reinforcement Learning
Name
mud-play15.pdf
Size
512.76 KB
Format
Adobe PDF
Checksum (MD5)
f6199a0265df0786fd46b93dffff94fe
Author(s)
Narasimhan, Karthik Rajagopal
Kulkarni, Tejas Dattatraya
Barzilay, Regina
Date Issued
September 2015
Journal
Proceedings of the 2015 Conference on Empirical Methods in Natural Language Processing
Publisher
Association for Computational Linguistics
Citation
Narasimhan, Karthik, Tejas D. Kulkarni, and Regina Barzilay. "Language Understanding for Text-based Games using Deep Reinforcement Learning." 2015 Conference on Empirical Methods in Natural Language Processing (September 2015).
Version
Author's final manuscript
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.
MIT Department
Massachusetts Institute of Technology. Department of Brain and Cognitive Sciences
Massachusetts Institute of Technology. Department of Electrical Engineering and Computer Science
Terms of Use
Creative Commons Attribution-Noncommercial-Share Alike
Persistent DSpace Link
DOI of Published Version
https://aclweb.org/anthology/D/D15/D15-1001.pdf
