Language Understanding for Text-based Games using Deep Reinforcement Learning

Citations Over TimeTop 1% of 2015 papers

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.

Related Papers

• → A Method of Accounting Bigrams in Topic Models(2015)15 cited
• → A method for sentence analysis of Japanese based on bigrams of cognitive units(1996)
• → A Corpus-Based Study of the Rate of Changes in Frequency of Syntactic Bigrams in English and Russian(2019)
• → A Bigram-based Inference Model for Retrieving Abbreviated Phrases in Source Code(2020)