{"about":{"site":"https://codewithpapers.app","non_affiliation":"Code with Papers and Syntology are not affiliated with, endorsed by, or sponsored by Papers with Code, Meta, or the pwc-archive mirror.","licence":"CC BY-SA 4.0","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","attribution":"https://codewithpapers.app/attribution","modified":"archive material modified by Syntology; see the attribution page"},"url":"/paper/distributed-deep-reinforcement-learning-learn","title":"Distributed Deep Reinforcement Learning: Learn how to play Atari games in 21 minutes","arxiv_id":"1801.02852","date":"2018-01-09","proceeding":null,"authors":["Igor Adamski","Robert Adamski","Tomasz Grel","Adam Jędrych","Kamil Kaczmarek","Henryk Michalewski"],"abstract":"We present a study in Distributed Deep Reinforcement Learning (DDRL) focused\non scalability of a state-of-the-art Deep Reinforcement Learning algorithm\nknown as Batch Asynchronous Advantage ActorCritic (BA3C). We show that using\nthe Adam optimization algorithm with a batch size of up to 2048 is a viable\nchoice for carrying out large scale machine learning computations. This,\ncombined with careful reexamination of the optimizer's hyperparameters, using\nsynchronous training on the node level (while keeping the local, single node\npart of the algorithm asynchronous) and minimizing the memory footprint of the\nmodel, allowed us to achieve linear scaling for up to 64 CPU nodes. This\ncorresponds to a training time of 21 minutes on 768 CPU cores, as opposed to 10\nhours when using a single node with 24 cores achieved by a baseline single-node\nimplementation.","url_abs":"http://arxiv.org/abs/1801.02852v2","url_pdf":"http://arxiv.org/pdf/1801.02852v2.pdf","source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","row_kind":"abstracts"},"code_links":[{"paper_slug":"distributed-deep-reinforcement-learning-learn","repo_url":"https://github.com/deepsense-ai/Distributed-BA3C","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"tf","reach":null}],"tasks":[{"task_slug":"atari-games","task_name":"Atari Games"},{"task_slug":null,"task_name":"CPU"},{"task_slug":"deep-reinforcement-learning","task_name":"Deep Reinforcement Learning"},{"task_slug":"2048","task_name":"Playing the Game of 2048"},{"task_slug":"reinforcement-learning","task_name":"Reinforcement Learning"},{"task_slug":"reinforcement-learning-1","task_name":"Reinforcement Learning (RL)"},{"task_slug":"reinforcement-learning-2","task_name":"reinforcement-learning"}],"methods":[{"method_slug":"adam","method_name":"Adam"}],"datasets_introduced":[],"methods_introduced":[],"results":[{"leaderboard":"/sota/atari-games-on-atari-2600-beam-rider","task":"Atari Games","dataset":"Atari 2600 Beam Rider","model":"DDRL A3C","rank_in_archive_order":24,"of":49,"metrics":{"Score":"14900"},"uses_additional_data":false},{"leaderboard":"/sota/atari-games-on-atari-2600-boxing","task":"Atari Games","dataset":"Atari 2600 Boxing","model":"DDRL A3C","rank_in_archive_order":21,"of":45,"metrics":{"Score":"98"},"uses_additional_data":false},{"leaderboard":"/sota/atari-games-on-atari-2600-breakout","task":"Atari Games","dataset":"Atari 2600 Breakout","model":"DDRL A3C","rank_in_archive_order":36,"of":58,"metrics":{"Score":"350"},"uses_additional_data":false},{"leaderboard":"/sota/atari-games-on-atari-2600-pong","task":"Atari Games","dataset":"Atari 2600 Pong","model":"DDRL A3C","rank_in_archive_order":28,"of":52,"metrics":{"Score":"20"},"uses_additional_data":false},{"leaderboard":"/sota/atari-games-on-atari-2600-seaquest","task":"Atari Games","dataset":"Atari 2600 Seaquest","model":"DDRL A3C","rank_in_archive_order":39,"of":57,"metrics":{"Score":"1832"},"uses_additional_data":false},{"leaderboard":"/sota/atari-games-on-atari-2600-space-invaders","task":"Atari Games","dataset":"Atari 2600 Space Invaders","model":"DDRL A3C","rank_in_archive_order":49,"of":55,"metrics":{"Score":"650"},"uses_additional_data":false}],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=1801.02852","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}