Towards Solving Text-based Games by Producing Adaptive Action Spaces

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 $F_1$ score on the test set.

References in corpus (7)

• Neural Machine Translation by Jointly Learning to Align and Translate
• Sequence to Sequence Learning with Neural Networks
• On the Properties of Neural Machine Translation: Encoder-Decoder Approaches
• Adversarial Learning for Neural Dialogue Generation
• Order Matters: Sequence to sequence for sets
• A Network-based End-to-End Trainable Task-oriented Dialogue System
• TextWorld: A Learning Environment for Text-based Games

Cited by in corpus (2)

• Action Assembly: Sparse Imitation Learning for Text Based Games with Combinatorial Action Spaces
• Keep CALM and Explore: Language Models for Action Generation in Text-based Games