Deep Attention Recurrent Q-Network
Machine Learning
2015-12-08 v1
Abstract
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.
Cite
@article{arxiv.1512.01693,
title = {Deep Attention Recurrent Q-Network},
author = {Ivan Sorokin and Alexey Seleznev and Mikhail Pavlov and Aleksandr Fedorov and Anastasiia Ignateva},
journal= {arXiv preprint arXiv:1512.01693},
year = {2015}
}
Comments
7 pages, 5 figures, Deep Reinforcement Learning Workshop, NIPS 2015