TY - JOUR
AU - 
AB - State 1: The old bridge You are standing very close to the bridge’s In this paper, we consider the task of learn- eastern foundation. If you go east you will ing control policies for text-based games. be back on solid ground ... The bridge In these games, all interactions in the vir- sways in the wind. tual world are through text and the un- derlying state is not observed. The re- Command: Go east sulting language barrier makes such envi- State 2: Ruined gatehouse ronments challenging for automatic game The old gatehouse is near collapse. Part of players. We employ a deep reinforcement its northern wall has already fallen down ... learning framework to jointly learn state East of the gatehouse leads out to a small representations and action policies using open area surrounded by the remains of the game rewards as feedback. This frame- castle. There is also a standing archway of- work enables us to map text descriptions fering passage to a path along the old south- into vector representations that capture the ern inner wall. semantics of the game states. We eval- Exits: Standing archway, castle corner, uate our approach on two game worlds, Bridge over 
TI - Language Understanding for Text-based Games using Deep Reinforcement Learning
JF - Proceedings of the 2015 Conference on Empirical Methods in Natural Language Processing
DO - 10.18653/v1/d15-1001
DA - 2015-01-01
UR - https://www.deepdyve.com/lp/unpaywall/language-understanding-for-text-based-games-using-deep-reinforcement-FTH6cheEbf
DP - DeepDyve
ER -