Language Understanding for Text-based Games using Deep Reinforcement Learning

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