Deep Attention Recurrent Q-Network

A deep learning approach to reinforcement learning led to a general learner able to train on visual input to play a variety of arcade games at the human and superhuman levels. Its creators at the Google DeepMind's team called the approach: Deep Q-Network (DQN). We present an extension of DQN by...

Full description

Saved in:
Bibliographic Details
Published inarXiv.org
Main Authors Sorokin, Ivan, Seleznev, Alexey, Pavlov, Mikhail, Fedorov, Aleksandr, Ignateva, Anastasiia
Format Paper
LanguageEnglish
Published Ithaca Cornell University Library, arXiv.org 05.12.2015
Subjects
Algorithms
Games
Machine learning
Online AccessGet full text

Cover

More Information
Summary:A deep learning approach to reinforcement learning led to a general learner able to train on visual input to play a variety of arcade games at the human and superhuman levels. Its creators at the Google DeepMind's team called the approach: Deep Q-Network (DQN). We present an extension of DQN by "soft" and "hard" attention mechanisms. Tests of the proposed Deep Attention Recurrent Q-Network (DARQN) algorithm on multiple Atari 2600 games show level of performance superior to that of DQN. Moreover, built-in attention mechanisms allow a direct online monitoring of the training process by highlighting the regions of the game screen the agent is focusing on when making decisions.
ISSN:2331-8422