DeepAI AI Chat
Log In Sign Up

Towards Solving Text-based Games by Producing Adaptive Action Spaces

by   Ruo Yu Tao, et al.
McGill University

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.


page 2

page 9


LeDeepChef: Deep Reinforcement Learning Agent for Families of Text-Based Games

While Reinforcement Learning (RL) approaches lead to significant achieve...

Algorithmic Improvements for Deep Reinforcement Learning applied to Interactive Fiction

Text-based games are a natural challenge domain for deep reinforcement l...

Exploration Based Language Learning for Text-Based Games

This work presents an exploration and imitation-learning-based agent cap...

Bootstrapped Q-learning with Context Relevant Observation Pruning to Generalize in Text-based Games

We show that Reinforcement Learning (RL) methods for solving Text-Based ...

Learning Dynamic Knowledge Graphs to Generalize on Text-Based Games

Playing text-based games requires skill in processing natural language a...

Actively Learning what makes a Discrete Sequence Valid

Deep learning techniques have been hugely successful for traditional sup...

Zero-Shot Learning of Text Adventure Games with Sentence-Level Semantics

Reinforcement learning algorithms such as Q-learning have shown great pr...