{"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/a-distributional-perspective-on-reinforcement","title":"A Distributional Perspective on Reinforcement Learning","arxiv_id":"1707.06887","date":"2017-07-21","proceeding":"ICML 2017 8","authors":["Marc G. Bellemare","Will Dabney","Rémi Munos"],"abstract":"In this paper we argue for the fundamental importance of the value\ndistribution: the distribution of the random return received by a reinforcement\nlearning agent. This is in contrast to the common approach to reinforcement\nlearning which models the expectation of this return, or value. Although there\nis an established body of literature studying the value distribution, thus far\nit has always been used for a specific purpose such as implementing risk-aware\nbehaviour. We begin with theoretical results in both the policy evaluation and\ncontrol settings, exposing a significant distributional instability in the\nlatter. We then use the distributional perspective to design a new algorithm\nwhich applies Bellman's equation to the learning of approximate value\ndistributions. We evaluate our algorithm using the suite of games from the\nArcade Learning Environment. We obtain both state-of-the-art results and\nanecdotal evidence demonstrating the importance of the value distribution in\napproximate reinforcement learning. Finally, we combine theoretical and\nempirical evidence to highlight the ways in which the value distribution\nimpacts learning in the approximate setting.","url_abs":"http://arxiv.org/abs/1707.06887v1","url_pdf":"http://arxiv.org/pdf/1707.06887v1.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":"a-distributional-perspective-on-reinforcement","repo_url":"https://github.com/Abdelhamid-bouzid/Distributional-RL","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok"}},{"paper_slug":"a-distributional-perspective-on-reinforcement","repo_url":"https://github.com/BY571/DQN-Atari-Agents","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":null},{"paper_slug":"a-distributional-perspective-on-reinforcement","repo_url":"https://github.com/Curt-Park/rainbow-is-all-you-need","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"none","reach":{"status":"ok","spdx":"MIT"}},{"paper_slug":"a-distributional-perspective-on-reinforcement","repo_url":"https://github.com/Kchu/DeepRL_CK","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"Apache-2.0"}},{"paper_slug":"a-distributional-perspective-on-reinforcement","repo_url":"https://github.com/NervanaSystems/coach","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"tf","reach":{"status":"unanswered"}},{"paper_slug":"a-distributional-perspective-on-reinforcement","repo_url":"https://github.com/Remtasya/DDPG-Actor-Critic-Reinforcement-Learning-Reacher-Environment","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":null},{"paper_slug":"a-distributional-perspective-on-reinforcement","repo_url":"https://github.com/chainer/chainerrl","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":null},{"paper_slug":"a-distributional-perspective-on-reinforcement","repo_url":"https://github.com/eric-yim/fin_map","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"tf","reach":{"status":"unanswered"}},{"paper_slug":"a-distributional-perspective-on-reinforcement","repo_url":"https://github.com/facebookresearch/Horizon","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"unanswered"}},{"paper_slug":"a-distributional-perspective-on-reinforcement","repo_url":"https://github.com/facebookresearch/ReAgent","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"unanswered"}},{"paper_slug":"a-distributional-perspective-on-reinforcement","repo_url":"https://github.com/guillaumeboniface/bananaland","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":null},{"paper_slug":"a-distributional-perspective-on-reinforcement","repo_url":"https://github.com/kochlisGit/autonomous-vehicles-agent","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"tf","reach":{"status":"ok"}},{"paper_slug":"a-distributional-perspective-on-reinforcement","repo_url":"https://github.com/marload/DistRL-TensorFlow2","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"tf","reach":{"status":"ok","spdx":"Apache-2.0"}},{"paper_slug":"a-distributional-perspective-on-reinforcement","repo_url":"https://github.com/marload/dist-rl-tf2","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"tf","reach":{"status":"ok","spdx":"Apache-2.0"}},{"paper_slug":"a-distributional-perspective-on-reinforcement","repo_url":"https://github.com/mindspore-courses/Rainbow-MindSpore","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"mindspore","reach":null},{"paper_slug":"a-distributional-perspective-on-reinforcement","repo_url":"https://github.com/parilo/gym_bipedal_walker_v2_solution","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"tf","reach":{"status":"unanswered"}},{"paper_slug":"a-distributional-perspective-on-reinforcement","repo_url":"https://github.com/pihey1995/DistributionalRL","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok"}},{"paper_slug":"a-distributional-perspective-on-reinforcement","repo_url":"https://github.com/shuli0808/DQN","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"unanswered"}},{"paper_slug":"a-distributional-perspective-on-reinforcement","repo_url":"https://github.com/Stable-Baselines-Team/stable-baselines3-contrib","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":0,"framework":"pytorch","reach":{"status":"ok","spdx":"MIT"}},{"paper_slug":"a-distributional-perspective-on-reinforcement","repo_url":"https://github.com/chandar-lab/RLHive","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":0,"framework":"pytorch","reach":null},{"paper_slug":"a-distributional-perspective-on-reinforcement","repo_url":"https://github.com/opendilab/DI-engine/blob/main/ding/policy/c51.py","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":0,"framework":"pytorch","reach":null},{"paper_slug":"a-distributional-perspective-on-reinforcement","repo_url":"https://github.com/qgallouedec/deep_rl","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":0,"framework":"pytorch","reach":{"status":"unanswered"}}],"tasks":[{"task_slug":"atari-games","task_name":"Atari Games"},{"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":[{"leaderboard":"/sota/atari-games-on-atari-2600-alien","task":"Atari Games","dataset":"Atari 2600 Alien","model":"C51 noop","rank_in_archive_order":26,"of":49,"metrics":{"Score":"3166.0"},"uses_additional_data":false},{"leaderboard":"/sota/atari-games-on-atari-2600-amidar","task":"Atari Games","dataset":"Atari 2600 Amidar","model":"C51 noop","rank_in_archive_order":14,"of":48,"metrics":{"Score":"1735.0"},"uses_additional_data":false},{"leaderboard":"/sota/atari-games-on-atari-2600-assault","task":"Atari Games","dataset":"Atari 2600 Assault","model":"C51 noop","rank_in_archive_order":23,"of":45,"metrics":{"Score":"7203.0"},"uses_additional_data":false},{"leaderboard":"/sota/atari-games-on-atari-2600-asterix","task":"Atari Games","dataset":"Atari 2600 Asterix","model":"C51 noop","rank_in_archive_order":9,"of":49,"metrics":{"Score":"406211"},"uses_additional_data":false},{"leaderboard":"/sota/atari-games-on-atari-2600-asteroids","task":"Atari Games","dataset":"Atari 2600 Asteroids","model":"C51 noop","rank_in_archive_order":33,"of":43,"metrics":{"Score":"1516.0"},"uses_additional_data":false},{"leaderboard":"/sota/atari-games-on-atari-2600-atlantis","task":"Atari Games","dataset":"Atari 2600 Atlantis","model":"C51 noop","rank_in_archive_order":22,"of":42,"metrics":{"Score":"841075.0"},"uses_additional_data":false},{"leaderboard":"/sota/atari-games-on-atari-2600-bank-heist","task":"Atari Games","dataset":"Atari 2600 Bank Heist","model":"C51 noop","rank_in_archive_order":26,"of":45,"metrics":{"Score":"976.0"},"uses_additional_data":false},{"leaderboard":"/sota/atari-games-on-atari-2600-battle-zone","task":"Atari Games","dataset":"Atari 2600 Battle Zone","model":"C51 noop","rank_in_archive_order":28,"of":47,"metrics":{"Score":"28742.0"},"uses_additional_data":false},{"leaderboard":"/sota/atari-games-on-atari-2600-beam-rider","task":"Atari Games","dataset":"Atari 2600 Beam Rider","model":"C51 noop","rank_in_archive_order":26,"of":49,"metrics":{"Score":"14074.0"},"uses_additional_data":false},{"leaderboard":"/sota/atari-games-on-atari-2600-berzerk","task":"Atari Games","dataset":"Atari 2600 Berzerk","model":"C51 noop","rank_in_archive_order":19,"of":39,"metrics":{"Score":"1645.0"},"uses_additional_data":false},{"leaderboard":"/sota/atari-games-on-atari-2600-bowling","task":"Atari Games","dataset":"Atari 2600 Bowling","model":"C51 noop","rank_in_archive_order":15,"of":44,"metrics":{"Score":"81.8"},"uses_additional_data":false},{"leaderboard":"/sota/atari-games-on-atari-2600-boxing","task":"Atari Games","dataset":"Atari 2600 Boxing","model":"C51 noop","rank_in_archive_order":22,"of":45,"metrics":{"Score":"97.8"},"uses_additional_data":false},{"leaderboard":"/sota/atari-games-on-atari-2600-breakout","task":"Atari Games","dataset":"Atari 2600 Breakout","model":"C51 noop","rank_in_archive_order":13,"of":58,"metrics":{"Score":"748.0"},"uses_additional_data":false},{"leaderboard":"/sota/atari-games-on-atari-2600-centipede","task":"Atari Games","dataset":"Atari 2600 Centipede","model":"C51 noop","rank_in_archive_order":19,"of":45,"metrics":{"Score":"9646.0"},"uses_additional_data":false},{"leaderboard":"/sota/atari-games-on-atari-2600-chopper-command","task":"Atari Games","dataset":"Atari 2600 Chopper Command","model":"C51 noop","rank_in_archive_order":14,"of":45,"metrics":{"Score":"15600.0"},"uses_additional_data":false},{"leaderboard":"/sota/atari-games-on-atari-2600-crazy-climber","task":"Atari Games","dataset":"Atari 2600 Crazy Climber","model":"C51 noop","rank_in_archive_order":10,"of":49,"metrics":{"Score":"179877.0"},"uses_additional_data":false},{"leaderboard":"/sota/atari-games-on-atari-2600-demon-attack","task":"Atari Games","dataset":"Atari 2600 Demon Attack","model":"C51 noop","rank_in_archive_order":11,"of":46,"metrics":{"Score":"130955.0"},"uses_additional_data":false},{"leaderboard":"/sota/atari-games-on-atari-2600-double-dunk","task":"Atari Games","dataset":"Atari 2600 Double Dunk","model":"C51 noop","rank_in_archive_order":18,"of":43,"metrics":{"Score":"2.5"},"uses_additional_data":false},{"leaderboard":"/sota/atari-games-on-atari-2600-enduro","task":"Atari Games","dataset":"Atari 2600 Enduro","model":"C51 noop","rank_in_archive_order":4,"of":48,"metrics":{"Score":"3454.0"},"uses_additional_data":false},{"leaderboard":"/sota/atari-games-on-atari-2600-fishing-derby","task":"Atari Games","dataset":"Atari 2600 Fishing Derby","model":"C51 noop","rank_in_archive_order":33,"of":44,"metrics":{"Score":"8.9"},"uses_additional_data":false},{"leaderboard":"/sota/atari-games-on-atari-2600-freeway","task":"Atari Games","dataset":"Atari 2600 Freeway","model":"C51 noop","rank_in_archive_order":10,"of":59,"metrics":{"Score":"33.9"},"uses_additional_data":false},{"leaderboard":"/sota/atari-games-on-atari-2600-frostbite","task":"Atari Games","dataset":"Atari 2600 Frostbite","model":"C51 noop","rank_in_archive_order":21,"of":53,"metrics":{"Score":"3965.0"},"uses_additional_data":false},{"leaderboard":"/sota/atari-games-on-atari-2600-gopher","task":"Atari Games","dataset":"Atari 2600 Gopher","model":"C51 noop","rank_in_archive_order":19,"of":43,"metrics":{"Score":"33641.0"},"uses_additional_data":false},{"leaderboard":"/sota/atari-games-on-atari-2600-gravitar","task":"Atari Games","dataset":"Atari 2600 Gravitar","model":"C51 noop","rank_in_archive_order":35,"of":53,"metrics":{"Score":"440.0"},"uses_additional_data":false},{"leaderboard":"/sota/atari-games-on-atari-2600-hero","task":"Atari Games","dataset":"Atari 2600 HERO","model":"C51 noop","rank_in_archive_order":4,"of":44,"metrics":{"Score":"38874"},"uses_additional_data":false},{"leaderboard":"/sota/atari-games-on-atari-2600-ice-hockey","task":"Atari Games","dataset":"Atari 2600 Ice Hockey","model":"C51 noop","rank_in_archive_order":35,"of":43,"metrics":{"Score":"-3.5"},"uses_additional_data":false},{"leaderboard":"/sota/atari-games-on-atari-2600-james-bond","task":"Atari Games","dataset":"Atari 2600 James Bond","model":"C51 noop","rank_in_archive_order":18,"of":45,"metrics":{"Score":"1909.0"},"uses_additional_data":false},{"leaderboard":"/sota/atari-games-on-atari-2600-kangaroo","task":"Atari Games","dataset":"Atari 2600 Kangaroo","model":"C51 noop","rank_in_archive_order":19,"of":47,"metrics":{"Score":"12853.0"},"uses_additional_data":false},{"leaderboard":"/sota/atari-games-on-atari-2600-krull","task":"Atari Games","dataset":"Atari 2600 Krull","model":"C51 noop","rank_in_archive_order":20,"of":45,"metrics":{"Score":"9735.0"},"uses_additional_data":false},{"leaderboard":"/sota/atari-games-on-atari-2600-kung-fu-master","task":"Atari Games","dataset":"Atari 2600 Kung-Fu Master","model":"C51 noop","rank_in_archive_order":18,"of":43,"metrics":{"Score":"48192.0"},"uses_additional_data":false},{"leaderboard":"/sota/atari-games-on-atari-2600-ms-pacman","task":"Atari Games","dataset":"Atari 2600 Ms. Pacman","model":"C51 noop","rank_in_archive_order":25,"of":47,"metrics":{"Score":"3415.0"},"uses_additional_data":false},{"leaderboard":"/sota/atari-games-on-atari-2600-name-this-game","task":"Atari Games","dataset":"Atari 2600 Name This Game","model":"C51 noop","rank_in_archive_order":20,"of":43,"metrics":{"Score":"12542.0"},"uses_additional_data":false},{"leaderboard":"/sota/atari-games-on-atari-2600-pong","task":"Atari Games","dataset":"Atari 2600 Pong","model":"C51 noop","rank_in_archive_order":19,"of":52,"metrics":{"Score":"20.9"},"uses_additional_data":false},{"leaderboard":"/sota/atari-games-on-atari-2600-private-eye","task":"Atari Games","dataset":"Atari 2600 Private Eye","model":"C51 noop","rank_in_archive_order":8,"of":52,"metrics":{"Score":"15095.0"},"uses_additional_data":false},{"leaderboard":"/sota/atari-games-on-atari-2600-qbert","task":"Atari Games","dataset":"Atari 2600 Q*Bert","model":"C51 noop","rank_in_archive_order":18,"of":57,"metrics":{"Score":"23784"},"uses_additional_data":false},{"leaderboard":"/sota/atari-games-on-atari-2600-river-raid","task":"Atari Games","dataset":"Atari 2600 River Raid","model":"C51 noop","rank_in_archive_order":15,"of":41,"metrics":{"Score":"17322.0"},"uses_additional_data":false},{"leaderboard":"/sota/atari-games-on-atari-2600-road-runner","task":"Atari Games","dataset":"Atari 2600 Road Runner","model":"C51 noop","rank_in_archive_order":22,"of":44,"metrics":{"Score":"55839.0"},"uses_additional_data":false},{"leaderboard":"/sota/atari-games-on-atari-2600-robotank","task":"Atari Games","dataset":"Atari 2600 Robotank","model":"C51 noop","rank_in_archive_order":28,"of":42,"metrics":{"Score":"52.3"},"uses_additional_data":false},{"leaderboard":"/sota/atari-games-on-atari-2600-seaquest","task":"Atari Games","dataset":"Atari 2600 Seaquest","model":"C51 noop","rank_in_archive_order":10,"of":57,"metrics":{"Score":"266434.0"},"uses_additional_data":false},{"leaderboard":"/sota/atari-games-on-atari-2600-space-invaders","task":"Atari Games","dataset":"Atari 2600 Space Invaders","model":"C51 noop","rank_in_archive_order":22,"of":55,"metrics":{"Score":"5747.0"},"uses_additional_data":false},{"leaderboard":"/sota/atari-games-on-atari-2600-star-gunner","task":"Atari Games","dataset":"Atari 2600 Star Gunner","model":"C51 noop","rank_in_archive_order":33,"of":43,"metrics":{"Score":"49095.0"},"uses_additional_data":false},{"leaderboard":"/sota/atari-games-on-atari-2600-tennis","task":"Atari Games","dataset":"Atari 2600 Tennis","model":"C51 noop","rank_in_archive_order":8,"of":43,"metrics":{"Score":"23.1"},"uses_additional_data":false},{"leaderboard":"/sota/atari-games-on-atari-2600-time-pilot","task":"Atari Games","dataset":"Atari 2600 Time Pilot","model":"C51 noop","rank_in_archive_order":28,"of":44,"metrics":{"Score":"8329.0"},"uses_additional_data":false},{"leaderboard":"/sota/atari-games-on-atari-2600-tutankham","task":"Atari Games","dataset":"Atari 2600 Tutankham","model":"C51 noop","rank_in_archive_order":12,"of":44,"metrics":{"Score":"280.0"},"uses_additional_data":false},{"leaderboard":"/sota/atari-games-on-atari-2600-up-and-down","task":"Atari Games","dataset":"Atari 2600 Up and Down","model":"C51 noop","rank_in_archive_order":33,"of":44,"metrics":{"Score":"15612.0"},"uses_additional_data":false},{"leaderboard":"/sota/atari-games-on-atari-2600-venture","task":"Atari Games","dataset":"Atari 2600 Venture","model":"C51 noop","rank_in_archive_order":13,"of":55,"metrics":{"Score":"1520.0"},"uses_additional_data":false},{"leaderboard":"/sota/atari-games-on-atari-2600-video-pinball","task":"Atari Games","dataset":"Atari 2600 Video Pinball","model":"C51 noop","rank_in_archive_order":5,"of":42,"metrics":{"Score":"949604.0"},"uses_additional_data":false},{"leaderboard":"/sota/atari-games-on-atari-2600-wizard-of-wor","task":"Atari Games","dataset":"Atari 2600 Wizard of Wor","model":"C51 noop","rank_in_archive_order":21,"of":41,"metrics":{"Score":"9300.0"},"uses_additional_data":false},{"leaderboard":"/sota/atari-games-on-atari-2600-zaxxon","task":"Atari Games","dataset":"Atari 2600 Zaxxon","model":"C51 noop","rank_in_archive_order":24,"of":41,"metrics":{"Score":"10513.0"},"uses_additional_data":false}],"syntology":{"syntology_url":"https://syntology.ai/paper/1707.06887","atlas_url":"https://app.syntology.ai/?focus=1707.06887","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1707.06887"}},"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/qgallouedec/deep_rl","reach":{"status":"unanswered"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/facebookresearch/Horizon","reach":{"status":"unanswered"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/eric-yim/fin_map","reach":{"status":"unanswered"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/pihey1995/DistributionalRL","reach":{"status":"ok"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/marload/dist-rl-tf2","reach":{"status":"ok","spdx":"Apache-2.0"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/guillaumeboniface/bananaland","reach":null},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/chainer/chainerrl","reach":null},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/parilo/gym_bipedal_walker_v2_solution","reach":{"status":"unanswered"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/opendilab/DI-engine/blob/main/ding/policy/c51.py","reach":null},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/Remtasya/DDPG-Actor-Critic-Reinforcement-Learning-Reacher-Environment","reach":null},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/Abdelhamid-bouzid/Distributional-RL","reach":{"status":"ok"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/shuli0808/DQN","reach":{"status":"unanswered"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/BY571/DQN-Atari-Agents","reach":null},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/Stable-Baselines-Team/stable-baselines3-contrib","reach":{"status":"ok","spdx":"MIT"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/kochlisGit/autonomous-vehicles-agent","reach":{"status":"ok"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/mindspore-courses/Rainbow-MindSpore","reach":null},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/Curt-Park/rainbow-is-all-you-need","reach":{"status":"ok","spdx":"MIT"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/NervanaSystems/coach","reach":{"status":"unanswered"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/facebookresearch/ReAgent","reach":{"status":"unanswered"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/Kchu/DeepRL_CK","reach":{"status":"ok","spdx":"Apache-2.0"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/chandar-lab/RLHive","reach":null},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/marload/DistRL-TensorFlow2","reach":{"status":"ok","spdx":"Apache-2.0"}}],"summary":{"unverified":1},"by_repo_kind":{},"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":"34182f569fae27fe","entry":"run","repo":null,"repo_kind":null,"path":null,"file_url":null,"link_basis":"identical_code_first_harvested_elsewhere","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":null,"inline_ok":false,"mcp_get_code":{"code_sha256":"34182f569fae27fe"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}