Comprehensible Context-driven Text Game Playing

05/06/2019
by   Xusen Yin, et al.
0

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 runs 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 Convolution 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.

READ FULL TEXT

page 1

page 2

page 3

page 4

research
11/03/2018

Auto-ML Deep Learning for Rashi Scripts OCR

In this work we propose an OCR scheme for manuscripts printed in Rashi f...
research
03/31/2017

Factorization tricks for LSTM networks

We present two simple ways of reducing the number of parameters and acce...
research
07/09/2019

Comparing the Performance of the LSTM and HMM Language Models via Structural Similarity

Language models based on deep neural networks and traditional stochastic...
research
03/11/2018

Deep reinforcement learning for time series: playing idealized trading games

Deep Q-learning is investigated as an end-to-end solution to estimate th...
research
04/26/2020

Detect Language of Transliterated Texts

Informal transliteration from other languages to English is prevalent in...
research
10/01/2020

How LSTM Encodes Syntax: Exploring Context Vectors and Semi-Quantization on Natural Text

Long Short-Term Memory recurrent neural network (LSTM) is widely used an...
research
05/27/2022

Improving Bidding and Playing Strategies in the Trick-Taking game Wizard using Deep Q-Networks

In this work, the trick-taking game Wizard with a separate bidding and p...

Please sign up or login with your details

Forgot password? Click here to reset