Papers › Distributed Deep Reinforcement Learning: Learn how to play Atari games in 21 minutes

Distributed Deep Reinforcement Learning: Learn how to play Atari games in 21 minutes

9 Jan 2018arXiv:1801.02852archive 2025-07-28

Igor Adamski, Robert Adamski, Tomasz Grel, Adam Jędrych, Kamil Kaczmarek, Henryk Michalewski

We present a study in Distributed Deep Reinforcement Learning (DDRL) focused on scalability of a state-of-the-art Deep Reinforcement Learning algorithm known as Batch Asynchronous Advantage ActorCritic (BA3C). We show that using the Adam optimization algorithm with a batch size of up to 2048 is a viable choice for carrying out large scale machine learning computations. This, combined with careful reexamination of the optimizer's hyperparameters, using synchronous training on the node level (while keeping the local, single node part of the algorithm asynchronous) and minimizing the memory footprint of the model, allowed us to achieve linear scaling for up to 64 CPU nodes. This corresponds to a training time of 21 minutes on 768 CPU cores, as opposed to 10 hours when using a single node with 24 cores achieved by a baseline single-node implementation.

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

deepsense-ai/Distributed-BA3C officialmentioned in papermentioned on GitHubtf 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 Reinforcement Learning Playing the Game of 2048 Reinforcement Learning Reinforcement Learning (RL)reinforcement-learning

1 archive task tag without a task page not shown.

Results from the paper archive 2025-07-28

Task	Dataset	Model	Metric	Value	Rank at snapshot	Leaderboard	Report
Atari Games	Atari 2600 Beam Rider	DDRL A3C	Score	14900	#24 of 49	Archive leaderboard	report
Atari Games	Atari 2600 Boxing	DDRL A3C	Score	98	#21 of 45	Archive leaderboard	report
Atari Games	Atari 2600 Breakout	DDRL A3C	Score	350	#36 of 58	Archive leaderboard	report
Atari Games	Atari 2600 Pong	DDRL A3C	Score	20	#28 of 52	Archive leaderboard	report
Atari Games	Atari 2600 Seaquest	DDRL A3C	Score	1832	#39 of 57	Archive leaderboard	report
Atari Games	Atari 2600 Space Invaders	DDRL A3C	Score	650	#49 of 55	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

Adam

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