Deep Attention Recurrent Q-Network

Ivan Sorokin, Alexey Seleznev, Mikhail Pavlov, Aleksandr Fedorov, Anastasiia Ignateva
12/5/2015
cs.LG

Official code: 5vision/DARQN (115 stars, last commit 2015-11-07).

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.

View on arXivView PDF

Code Implementations(1)

5vision/DARQNOfficial100%

Deep Attention Recurrent Q-Network

11538Lua, ShellNov 7, 201510 years ago

Similar Papers

ViZDoom: A Doom-based AI Research Platform for Visual Reinforcement Learning

86% match1 repo2.1k2016

Ludax: A GPU-Accelerated Domain Specific Language for Board Games

86% match2025

Deep Reinforcement Learning

86% match4 repos10.9k2018

The Animal-AI Environment: A Virtual Laboratory For Comparative Cognition and Artificial Intelligence Research

85% match1 repo992023

Deep Reinforcement Learning: An Overview

85% match1 repo1512017

Towards Human-Like RL: Taming Non-Naturalistic Behavior in Deep RL via Adaptive Behavioral Costs in 3D Games

85% match2023

Cite this paper

@article{sorokin2015deep,
  title  = {Deep Attention Recurrent Q-Network},
  author = {Ivan Sorokin and Alexey Seleznev and Mikhail Pavlov and Aleksandr Fedorov and Anastasiia Ignateva},
  year   = {2015},
  eprint = {1512.01693},
  archivePrefix = {arXiv},
  url    = {https://arxiv.org/abs/1512.01693}
}

Add a badge to your README

Shows whether official code is linked for this paper.

Code of Paper badge
[![Code of Paper](https://codeofpaper.com/badge/1512.01693.svg)](https://codeofpaper.com/paper/1512.01693)

Discussion