Comprehensible Context-driven Text Game Playing

Abstract

In order to train a computer agent to play a text-based computer game, we must represent each hidden state of the game. A Long Short-Term Memory (LSTM) model running over observed texts is a common choice for state construction. However, a normal Deep Q-learning Network (DQN) for such an agent requires millions of steps of training or more to converge. As such, an LSTM-based DQN can take tens of days to finish the training process. Though we can use a Convolutional Neural Network (CNN) as a text-encoder to construct states much faster than the LSTM, doing so without an understanding of the syntactic context of the words being analyzed can slow convergence. In this paper, we use a fast CNN to encode position- and syntax-oriented structures extracted from observed texts as states. We additionally augment the reward signal in a universal and practical manner. Together, we show that our improvements can not only speed up the process by one order of magnitude but also learn a superior agent.

arXiv commentIEEE Conference on Games 2019 Long Paper

References in corpus (7)

• Distributed Representations of Words and Phrases and their Compositionality
• Convolutional Sequence to Sequence Learning
• Deep Reinforcement Learning for Dialogue Generation
• Learn What Not to Learn: Action Elimination with Deep Reinforcement Learning
• TextWorld: A Learning Environment for Text-based Games
• What can you do with a rock? Affordance extraction via word embeddings
• Language Expansion In Text-Based Games

Cited by in corpus (4)

• How to Avoid Being Eaten by a Grue: Structured Exploration Strategies for Textual Worlds
• Interactive Fiction Games: A Colossal Adventure
• Playing Text-Based Games with Common Sense
• How To Avoid Being Eaten By a Grue: Exploration Strategies for Text-Adventure Agents