{"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/seed-rl-scalable-and-efficient-deep-rl-with-1","title":"SEED RL: Scalable and Efficient Deep-RL with Accelerated Central Inference","arxiv_id":"1910.06591","date":"2019-10-15","proceeding":"ICLR 2020 1","authors":["Lasse Espeholt","Raphaël Marinier","Piotr Stanczyk","Ke Wang","Marcin Michalski"],"abstract":"We present a modern scalable reinforcement learning agent called SEED (Scalable, Efficient Deep-RL). By effectively utilizing modern accelerators, we show that it is not only possible to train on millions of frames per second but also to lower the cost of experiments compared to current methods. We achieve this with a simple architecture that features centralized inference and an optimized communication layer. SEED adopts two state of the art distributed algorithms, IMPALA/V-trace (policy gradients) and R2D2 (Q-learning), and is evaluated on Atari-57, DeepMind Lab and Google Research Football. We improve the state of the art on Football and are able to reach state of the art on Atari-57 three times faster in wall-time. For the scenarios we consider, a 40% to 80% cost reduction for running experiments is achieved. The implementation along with experiments is open-sourced so results can be reproduced and novel ideas tried out.","url_abs":"https://arxiv.org/abs/1910.06591v2","url_pdf":"https://arxiv.org/pdf/1910.06591v2.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":"seed-rl-scalable-and-efficient-deep-rl-with-1","repo_url":"https://github.com/google-research/seed_rl","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"tf","reach":{"status":"ok","spdx":"Apache-2.0"}},{"paper_slug":"seed-rl-scalable-and-efficient-deep-rl-with-1","repo_url":"https://github.com/opendilab/DI-engine","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":0,"framework":"pytorch","reach":null}],"tasks":[{"task_slug":"q-learning","task_name":"Q-Learning"},{"task_slug":"reinforcement-learning","task_name":"Reinforcement Learning"}],"methods":[{"method_slug":"r2d2","method_name":"R2D2"},{"method_slug":"seed-rl","method_name":"SEED RL"}],"datasets_introduced":[],"methods_introduced":[{"slug":"seed-rl","name":"SEED RL","full_name":"SEED RL"}],"results":[],"syntology":{"syntology_url":"https://syntology.ai/paper/1910.06591","atlas_url":"https://app.syntology.ai/?focus=1910.06591","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1910.06591"}},"developers":"https://syntology.ai/developers","read_at":"2026-09-25T09:33:49+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/opendilab/DI-engine","reach":null},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/google-research/seed_rl","reach":{"status":"ok","spdx":"Apache-2.0"}}],"summary":{"unverified":6},"by_repo_kind":{"official":{"samples":6,"ran":0,"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":0,"samples":[{"code_sha256_prefix":"4a1477f42fca643a","entry":"create_mlp","repo":"google-research/seed_rl","repo_kind":"official","path":"agents/sac/networks.py","file_url":"https://github.com/google-research/seed_rl/blob/HEAD/agents/sac/networks.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"4a1477f42fca643a"}},{"code_sha256_prefix":"91ade95e9bacd17d","entry":"create_optimizer","repo":"google-research/seed_rl","repo_kind":"official","path":"atari/r2d2_main.py","file_url":"https://github.com/google-research/seed_rl/blob/HEAD/atari/r2d2_main.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"91ade95e9bacd17d"}},{"code_sha256_prefix":"3e77470c8d768c95","entry":"flatten_and_concatenate_obs","repo":"google-research/seed_rl","repo_kind":"official","path":"common/env_wrappers.py","file_url":"https://github.com/google-research/seed_rl/blob/HEAD/common/env_wrappers.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"3e77470c8d768c95"}},{"code_sha256_prefix":"8de5cad377fd4152","entry":"initial_frame_stacking_state","repo":"google-research/seed_rl","repo_kind":"official","path":"atari/networks.py","file_url":"https://github.com/google-research/seed_rl/blob/HEAD/atari/networks.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"8de5cad377fd4152"}},{"code_sha256_prefix":"f49f61cf5dbd360c","entry":"spec_to_box","repo":"google-research/seed_rl","repo_kind":"official","path":"common/env_wrappers.py","file_url":"https://github.com/google-research/seed_rl/blob/HEAD/common/env_wrappers.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"f49f61cf5dbd360c"}},{"code_sha256_prefix":"bfc70838af9ecd54","entry":"stack_frames","repo":"google-research/seed_rl","repo_kind":"official","path":"atari/networks.py","file_url":"https://github.com/google-research/seed_rl/blob/HEAD/atari/networks.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"bfc70838af9ecd54"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}