@inproceedings{tao2018towards,
author = {Tao, Ruo Yu (David) and Côté, Marc-Alexandre and Yuan, Xingdi and El Asri, Layla},
title = {Towards Solving Text-based Games by Producing Adaptive Action Spaces},
booktitle = {32nd Conference on Neural Information Processing Systems (NeurIPS 2018), Montréal, Canada.},
year = {2018},
month = {December},
abstract = {To solve a text-based game, an agent needs to formulate valid text commands for a given context and find the ones that lead to success. Recent attempts at solving text-based games with deep reinforcement learning have focused on the latter, i.e., learning to act optimally when valid actions are known in advance. In this work, we propose to tackle the first task and train a model that generates the set of all valid commands for a given context. We try three generative models on a dataset generated with Textworld. The best model can generate valid commands which were unseen at training and achieve high F1 score on the test set.},
url = {http://approjects.co.za/?big=en-us/research/publication/towards-solving-text-based-games-by-producing-adaptive-action-spaces/},
pages = {1-10},
}