Papers › Deep Attention Recurrent Q-Network

Deep Attention Recurrent Q-Network

5 Dec 2015arXiv:1512.01693archive 2025-07-28

Ivan Sorokin, Alexey Seleznev, Mikhail Pavlov, Aleksandr Fedorov, Anastasiia Ignateva

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.

Paper PDF Code

In Syntology Open this paper in Syntology's Atlas, the map of the papers in Syntology's graph and their citations.

Code

5vision/DARQN officialmentioned in paper report

ulstu/ml mentioned on GitHub report

ulstu/robotics_ml mentioned on GitHub report

Repository list and official/mentioned flags are the archive's, frozen 2025-07-28. Reachability, where shown, is from one Syntology probe window (2026-09-16 to 2026-09-18); repositories not probed show nothing. GitHub stars are not tracked.

Code Syntology ran Syntology

Not run by Syntology. Nothing on this page verifies that the listed code works.

Tasks

Atari Games Deep Attention Hard Attention Reinforcement Learning Reinforcement Learning (RL)reinforcement-learning

Results from the paper archive 2025-07-28

Task	Dataset	Model	Metric	Value	Rank at snapshot	Leaderboard	Report
Atari Games	Atari 2600 Breakout	DARQN hard	Score	20	#51 of 58	Archive leaderboard	report
Atari Games	Atari 2600 Gopher	DARQN soft	Score	5356	#37 of 43	Archive leaderboard	report
Atari Games	Atari 2600 Seaquest	DARQN soft	Score	7263	#28 of 57	Archive leaderboard	report
Atari Games	Atari 2600 Space Invaders	DARQN soft	Score	650	#50 of 55	Archive leaderboard	report
Atari Games	Atari 2600 Tutankham	DARQN soft	Score	197	#25 of 44	Archive leaderboard	report

Ranks are positions in the archive's leaderboards as they stood at the 2025-07-28 snapshot. Results published since then are not among these rows, so a rank here is not a current standing.

Methods

Convolution DQN Dense Connections Q-Learning

Report a problem or propose a change · a person checks every report against the paper or source before anything changes; decisions are listed on /corrections