{"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/accelerated-methods-for-deep-reinforcement","title":"Accelerated Methods for Deep Reinforcement Learning","arxiv_id":"1803.02811","date":"2018-03-07","proceeding":null,"authors":["Adam Stooke","Pieter Abbeel"],"abstract":"Deep reinforcement learning (RL) has achieved many recent successes, yet\nexperiment turn-around time remains a key bottleneck in research and in\npractice. We investigate how to optimize existing deep RL algorithms for modern\ncomputers, specifically for a combination of CPUs and GPUs. We confirm that\nboth policy gradient and Q-value learning algorithms can be adapted to learn\nusing many parallel simulator instances. We further find it possible to train\nusing batch sizes considerably larger than are standard, without negatively\naffecting sample complexity or final performance. We leverage these facts to\nbuild a unified framework for parallelization that dramatically hastens\nexperiments in both classes of algorithm. All neural network computations use\nGPUs, accelerating both data collection and training. Our results include using\nan entire DGX-1 to learn successful strategies in Atari games in mere minutes,\nusing both synchronous and asynchronous algorithms.","url_abs":"http://arxiv.org/abs/1803.02811v2","url_pdf":"http://arxiv.org/pdf/1803.02811v2.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":"accelerated-methods-for-deep-reinforcement","repo_url":"https://github.com/RexGLiu/rlpyt_crbp","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"MIT"}},{"paper_slug":"accelerated-methods-for-deep-reinforcement","repo_url":"https://github.com/akterskii/rlpyt","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"MIT"}},{"paper_slug":"accelerated-methods-for-deep-reinforcement","repo_url":"https://github.com/alexsax/testing_rlpyt","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"gone","observed_at":"2026-09-17","how":"tree_404+repo_404"}},{"paper_slug":"accelerated-methods-for-deep-reinforcement","repo_url":"https://github.com/astooke/accel_rl","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"none","reach":{"status":"ok"}},{"paper_slug":"accelerated-methods-for-deep-reinforcement","repo_url":"https://github.com/astooke/rlpyt","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"MIT"}},{"paper_slug":"accelerated-methods-for-deep-reinforcement","repo_url":"https://github.com/eac-replication/eac-replication","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"MIT"}},{"paper_slug":"accelerated-methods-for-deep-reinforcement","repo_url":"https://github.com/michael-snower/ppo","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"tf","reach":null},{"paper_slug":"accelerated-methods-for-deep-reinforcement","repo_url":"https://github.com/sarahisyoung/rlpyt","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"MIT"}}],"tasks":[{"task_slug":"atari-games","task_name":"Atari Games"},{"task_slug":"deep-reinforcement-learning","task_name":"Deep Reinforcement Learning"},{"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":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=1803.02811","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1803.02811"}},"developers":"https://syntology.ai/developers","read_at":"2026-09-24T18:15:14+00:00","read_at_is":"when the build read Syntology's graph, not when any sample ran","claim":"Per-sample execution status on synthesized fixtures; not a correctness claim about the paper. Samples come from repositories linked to the paper, official or community; repo_kind says which.","repos":[{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/akterskii/rlpyt","reach":{"status":"ok","spdx":"MIT"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/astooke/rlpyt","reach":{"status":"ok","spdx":"MIT"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/sarahisyoung/rlpyt","reach":{"status":"ok","spdx":"MIT"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/eac-replication/eac-replication","reach":{"status":"ok","spdx":"MIT"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/michael-snower/ppo","reach":null},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/alexsax/testing_rlpyt","reach":{"status":"gone","observed_at":"2026-09-17","how":"tree_404+repo_404"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/RexGLiu/rlpyt_crbp","reach":{"status":"ok","spdx":"MIT"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/astooke/accel_rl","reach":{"status":"ok"}}],"summary":{"ran_draft_wrong":1},"by_repo_kind":{"listed":{"samples":1,"ran":1,"repositories":1}},"repo_kind_vocabulary":{"official":"The archive marks this repository official for the paper","named_in_paper":"The archive records that the paper mentions this repository; it is not marked official","listed":"In the archive's code links for this paper, not marked official and not recorded as mentioned in the paper","found_in_text":"Syntology found this repository in the paper's own text; whether it is the authors' implementation is not asserted","community":"Not in the archive's code links for this paper; a community repository Syntology harvested"},"n_pointer_only_for_licence":1,"samples":[{"code_sha256_prefix":"f173a2c90e83061e","entry":"parse_args","repo":"michael-snower/ppo","repo_kind":"listed","path":"runner.py","file_url":"https://github.com/michael-snower/ppo/blob/HEAD/runner.py","link_basis":"first_harvest_node","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"OUTPUT_MISDECLARED","metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"f173a2c90e83061e"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}