{"about":{"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.","site":"https://codewithpapers.app","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","syntology":{"site":"https://syntology.ai","developers":"https://syntology.ai/developers","mcp":{"server":"https://syntology.ai/mcp","transport":"streamable-http","server_card":"https://syntology.ai/.well-known/mcp/server-card.json","auth":{"type":"trial token, no account","trial_token":"https://syntology.ai/api/oauth/trial/token","method":"POST","docs":"https://syntology.ai/developers"}},"have":"https://syntology.ai/api/graph/have?x=<method, arXiv id or title> (free, answers coverage only)","paper_base":"https://syntology.ai/paper/","atlas_base":"https://app.syntology.ai/?focus="},"machine_readable":[{"url":"https://codewithpapers.app/llms.txt","what":"the machine catalog: every machine-readable file, counted"},{"url":"https://codewithpapers.app/index/manifest.json","what":"paper-to-code index by arXiv id, with Syntology's counts"},{"url":"https://codewithpapers.app/search/manifest.json","what":"site search index (titles, authors) and its files"},{"url":"https://codewithpapers.app/download","what":"bulk files: Syntology's layer, described there"},{"url":"https://codewithpapers.app/build_manifest.json","what":"the build record: inputs, counts, exclusions, probes"}]},"url":"/paper/impala-scalable-distributed-deep-rl-with","title":"IMPALA: Scalable Distributed Deep-RL with Importance Weighted Actor-Learner Architectures","arxiv_id":"1802.01561","date":"2018-02-05","proceeding":"ICML 2018 7","authors":["Lasse Espeholt","Hubert Soyer","Remi Munos","Karen Simonyan","Volodymir Mnih","Tom Ward","Yotam Doron","Vlad Firoiu","Tim Harley","Iain Dunning","Shane Legg","Koray Kavukcuoglu"],"abstract":"In this work we aim to solve a large collection of tasks using a single\nreinforcement learning agent with a single set of parameters. A key challenge\nis to handle the increased amount of data and extended training time. We have\ndeveloped a new distributed agent IMPALA (Importance Weighted Actor-Learner\nArchitecture) that not only uses resources more efficiently in single-machine\ntraining but also scales to thousands of machines without sacrificing data\nefficiency or resource utilisation. We achieve stable learning at high\nthroughput by combining decoupled acting and learning with a novel off-policy\ncorrection method called V-trace. We demonstrate the effectiveness of IMPALA\nfor multi-task reinforcement learning on DMLab-30 (a set of 30 tasks from the\nDeepMind Lab environment (Beattie et al., 2016)) and Atari-57 (all available\nAtari games in Arcade Learning Environment (Bellemare et al., 2013a)). Our\nresults show that IMPALA is able to achieve better performance than previous\nagents with less data, and crucially exhibits positive transfer between tasks\nas a result of its multi-task approach.","url_abs":"http://arxiv.org/abs/1802.01561v3","url_pdf":"http://arxiv.org/pdf/1802.01561v3.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":"impala-scalable-distributed-deep-rl-with","repo_url":"https://github.com/deepmind/scalable_agent","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"tf","reach":{"status":"unanswered"}},{"paper_slug":"impala-scalable-distributed-deep-rl-with","repo_url":"https://github.com/Sheepsody/Batched-Impala-PyTorch","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":null},{"paper_slug":"impala-scalable-distributed-deep-rl-with","repo_url":"https://github.com/crazydonkey200/neural-symbolic-machines","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"tf","reach":{"status":"ok","spdx":"Apache-2.0"}},{"paper_slug":"impala-scalable-distributed-deep-rl-with","repo_url":"https://github.com/deepmind/streetlearn","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"tf","reach":{"status":"ok","spdx":"Apache-2.0"}},{"paper_slug":"impala-scalable-distributed-deep-rl-with","repo_url":"https://github.com/facebookresearch/gala","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":null},{"paper_slug":"impala-scalable-distributed-deep-rl-with","repo_url":"https://github.com/facebookresearch/torchbeast","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":null},{"paper_slug":"impala-scalable-distributed-deep-rl-with","repo_url":"https://github.com/google-deepmind/scalable_agent","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"tf","reach":null},{"paper_slug":"impala-scalable-distributed-deep-rl-with","repo_url":"https://github.com/google-deepmind/streetlearn","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"tf","reach":{"status":"ok","spdx":"Apache-2.0"}},{"paper_slug":"impala-scalable-distributed-deep-rl-with","repo_url":"https://github.com/google-research/valan","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"tf","reach":null},{"paper_slug":"impala-scalable-distributed-deep-rl-with","repo_url":"https://github.com/haje01/impala","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":null},{"paper_slug":"impala-scalable-distributed-deep-rl-with","repo_url":"https://github.com/heiner/scalable_agent","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"tf","reach":{"status":"ok","spdx":"Apache-2.0"}},{"paper_slug":"impala-scalable-distributed-deep-rl-with","repo_url":"https://github.com/jerrodparker20/adaptive-transformers-in-rl","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok"}},{"paper_slug":"impala-scalable-distributed-deep-rl-with","repo_url":"https://github.com/michaelnny/deep_rl_zoo","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":null},{"paper_slug":"impala-scalable-distributed-deep-rl-with","repo_url":"https://github.com/theSparta/neural-symbolic-machines","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"tf","reach":{"status":"ok","spdx":"Apache-2.0"}},{"paper_slug":"impala-scalable-distributed-deep-rl-with","repo_url":"https://github.com/threewisemonkeys-as/torched_impala","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"unanswered"}},{"paper_slug":"impala-scalable-distributed-deep-rl-with","repo_url":"https://github.com/urw7rs/spiralpp","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":null},{"paper_slug":"impala-scalable-distributed-deep-rl-with","repo_url":"https://github.com/villinvic/Georges","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"none","reach":null},{"paper_slug":"impala-scalable-distributed-deep-rl-with","repo_url":"https://github.com/windstrip/DeepMind-StreetLearn","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"tf","reach":{"status":"unanswered"}},{"paper_slug":"impala-scalable-distributed-deep-rl-with","repo_url":"https://github.com/deepmind/haiku","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":0,"framework":"jax","reach":{"status":"unanswered"}},{"paper_slug":"impala-scalable-distributed-deep-rl-with","repo_url":"https://github.com/deepmind/rlax","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":0,"framework":"jax","reach":null},{"paper_slug":"impala-scalable-distributed-deep-rl-with","repo_url":"https://github.com/opendilab/DI-engine/blob/main/ding/policy/impala.py","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":0,"framework":"pytorch","reach":null},{"paper_slug":"impala-scalable-distributed-deep-rl-with","repo_url":"https://github.com/ray-project/ray/tree/master/rllib","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":0,"framework":"none","reach":null},{"paper_slug":"impala-scalable-distributed-deep-rl-with","repo_url":"https://github.com/seolhokim/DistributedRL-Pytorch-Ray","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":0,"framework":"pytorch","reach":null},{"paper_slug":"impala-scalable-distributed-deep-rl-with","repo_url":"https://github.com/seolhokim/SimpleDistributedRL","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":0,"framework":"pytorch","reach":null}],"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":[{"method_slug":"convolution","method_name":"Convolution"},{"method_slug":"entropy-regularization","method_name":"Entropy Regularization"},{"method_slug":"experience-replay","method_name":"Experience Replay"},{"method_slug":"gradient-clipping","method_name":"Gradient Clipping"},{"method_slug":"impala","method_name":"IMPALA"},{"method_slug":"lstm","method_name":"LSTM"},{"method_slug":"max-pooling","method_name":"Max Pooling"},{"method_slug":"rmsprop","method_name":"RMSProp"},{"method_slug":"relu","method_name":"ReLU"},{"method_slug":"residual-connection","method_name":"Residual Connection"},{"method_slug":"sigmoid-activation","method_name":"Sigmoid Activation"},{"method_slug":"tanh-activation","method_name":"Tanh Activation"},{"method_slug":"v-trace","method_name":"V-trace"}],"datasets_introduced":[],"methods_introduced":[{"slug":"impala","name":"IMPALA","full_name":"IMPALA"},{"slug":"v-trace","name":"V-trace","full_name":"V-trace"}],"results":[{"leaderboard":"/sota/atari-games-on-atari-2600-alien","task":"Atari Games","dataset":"Atari 2600 Alien","model":"IMPALA (deep)","rank_in_archive_order":10,"of":49,"metrics":{"Score":"15962.10"},"uses_additional_data":false},{"leaderboard":"/sota/atari-games-on-atari-2600-amidar","task":"Atari Games","dataset":"Atari 2600 Amidar","model":"IMPALA (deep)","rank_in_archive_order":17,"of":48,"metrics":{"Score":"1554.79"},"uses_additional_data":false},{"leaderboard":"/sota/atari-games-on-atari-2600-assault","task":"Atari Games","dataset":"Atari 2600 Assault","model":"IMPALA (deep)","rank_in_archive_order":11,"of":45,"metrics":{"Score":"19148.47"},"uses_additional_data":false},{"leaderboard":"/sota/atari-games-on-atari-2600-asterix","task":"Atari Games","dataset":"Atari 2600 Asterix","model":"IMPALA (deep)","rank_in_archive_order":16,"of":49,"metrics":{"Score":"300732.00"},"uses_additional_data":false},{"leaderboard":"/sota/atari-games-on-atari-2600-asteroids","task":"Atari Games","dataset":"Atari 2600 Asteroids","model":"IMPALA (deep)","rank_in_archive_order":9,"of":43,"metrics":{"Score":"108590.05"},"uses_additional_data":false},{"leaderboard":"/sota/atari-games-on-atari-2600-atlantis","task":"Atari Games","dataset":"Atari 2600 Atlantis","model":"IMPALA (deep)","rank_in_archive_order":21,"of":42,"metrics":{"Score":"849967.50"},"uses_additional_data":false},{"leaderboard":"/sota/atari-games-on-atari-2600-bank-heist","task":"Atari Games","dataset":"Atari 2600 Bank Heist","model":"IMPALA (deep)","rank_in_archive_order":16,"of":45,"metrics":{"Score":"1223.15"},"uses_additional_data":false},{"leaderboard":"/sota/atari-games-on-atari-2600-battle-zone","task":"Atari Games","dataset":"Atari 2600 Battle Zone","model":"IMPALA (deep)","rank_in_archive_order":36,"of":47,"metrics":{"Score":"20885.00"},"uses_additional_data":false},{"leaderboard":"/sota/atari-games-on-atari-2600-beam-rider","task":"Atari Games","dataset":"Atari 2600 Beam Rider","model":"IMPALA (deep)","rank_in_archive_order":12,"of":49,"metrics":{"Score":"32463.47"},"uses_additional_data":false},{"leaderboard":"/sota/atari-games-on-atari-2600-berzerk","task":"Atari Games","dataset":"Atari 2600 Berzerk","model":"IMPALA (deep)","rank_in_archive_order":18,"of":39,"metrics":{"Score":"1852.70"},"uses_additional_data":false},{"leaderboard":"/sota/atari-games-on-atari-2600-bowling","task":"Atari Games","dataset":"Atari 2600 Bowling","model":"IMPALA (deep)","rank_in_archive_order":25,"of":44,"metrics":{"Score":"59.92"},"uses_additional_data":false},{"leaderboard":"/sota/atari-games-on-atari-2600-boxing","task":"Atari Games","dataset":"Atari 2600 Boxing","model":"IMPALA (deep)","rank_in_archive_order":10,"of":45,"metrics":{"Score":"99.96"},"uses_additional_data":false},{"leaderboard":"/sota/atari-games-on-atari-2600-breakout","task":"Atari Games","dataset":"Atari 2600 Breakout","model":"IMPALA (deep)","rank_in_archive_order":10,"of":58,"metrics":{"Score":"787.34"},"uses_additional_data":false},{"leaderboard":"/sota/atari-games-on-atari-2600-centipede","task":"Atari Games","dataset":"Atari 2600 Centipede","model":"IMPALA (deep)","rank_in_archive_order":18,"of":45,"metrics":{"Score":"11049.75"},"uses_additional_data":false},{"leaderboard":"/sota/atari-games-on-atari-2600-chopper-command","task":"Atari Games","dataset":"Atari 2600 Chopper Command","model":"IMPALA (deep)","rank_in_archive_order":12,"of":45,"metrics":{"Score":"28255.00"},"uses_additional_data":false},{"leaderboard":"/sota/atari-games-on-atari-2600-crazy-climber","task":"Atari Games","dataset":"Atari 2600 Crazy Climber","model":"IMPALA (deep)","rank_in_archive_order":22,"of":49,"metrics":{"Score":"136950.00"},"uses_additional_data":false},{"leaderboard":"/sota/atari-games-on-atari-2600-defender","task":"Atari Games","dataset":"Atari 2600 Defender","model":"IMPALA (deep)","rank_in_archive_order":11,"of":21,"metrics":{"Score":"185203.00"},"uses_additional_data":false},{"leaderboard":"/sota/atari-games-on-atari-2600-demon-attack","task":"Atari Games","dataset":"Atari 2600 Demon Attack","model":"IMPALA (deep)","rank_in_archive_order":10,"of":46,"metrics":{"Score":"132826.98"},"uses_additional_data":false},{"leaderboard":"/sota/atari-games-on-atari-2600-double-dunk","task":"Atari Games","dataset":"Atari 2600 Double Dunk","model":"IMPALA (deep)","rank_in_archive_order":38,"of":43,"metrics":{"Score":"-0.33"},"uses_additional_data":false},{"leaderboard":"/sota/atari-games-on-atari-2600-enduro","task":"Atari Games","dataset":"Atari 2600 Enduro","model":"IMPALA (deep)","rank_in_archive_order":45,"of":48,"metrics":{"Score":"0.00"},"uses_additional_data":false},{"leaderboard":"/sota/atari-games-on-atari-2600-fishing-derby","task":"Atari Games","dataset":"Atari 2600 Fishing Derby","model":"IMPALA (deep)","rank_in_archive_order":15,"of":44,"metrics":{"Score":"44.85"},"uses_additional_data":false},{"leaderboard":"/sota/atari-games-on-atari-2600-freeway","task":"Atari Games","dataset":"Atari 2600 Freeway","model":"IMPALA (deep)","rank_in_archive_order":59,"of":59,"metrics":{"Score":"0.00"},"uses_additional_data":false},{"leaderboard":"/sota/atari-games-on-atari-2600-frostbite","task":"Atari Games","dataset":"Atari 2600 Frostbite","model":"IMPALA (deep)","rank_in_archive_order":44,"of":53,"metrics":{"Score":"317.75"},"uses_additional_data":false},{"leaderboard":"/sota/atari-games-on-atari-2600-gopher","task":"Atari Games","dataset":"Atari 2600 Gopher","model":"IMPALA (deep)","rank_in_archive_order":15,"of":43,"metrics":{"Score":"66782.30"},"uses_additional_data":false},{"leaderboard":"/sota/atari-games-on-atari-2600-gravitar","task":"Atari Games","dataset":"Atari 2600 Gravitar","model":"IMPALA (deep)","rank_in_archive_order":40,"of":53,"metrics":{"Score":"359.50"},"uses_additional_data":false},{"leaderboard":"/sota/atari-games-on-atari-2600-hero","task":"Atari Games","dataset":"Atari 2600 HERO","model":"IMPALA (deep)","rank_in_archive_order":9,"of":44,"metrics":{"Score":"33730.55"},"uses_additional_data":false},{"leaderboard":"/sota/atari-games-on-atari-2600-ice-hockey","task":"Atari Games","dataset":"Atari 2600 Ice Hockey","model":"IMPALA (deep)","rank_in_archive_order":14,"of":43,"metrics":{"Score":"3.48"},"uses_additional_data":false},{"leaderboard":"/sota/atari-games-on-atari-2600-james-bond","task":"Atari Games","dataset":"Atari 2600 James Bond","model":"IMPALA (deep)","rank_in_archive_order":31,"of":45,"metrics":{"Score":"601.50"},"uses_additional_data":false},{"leaderboard":"/sota/atari-games-on-atari-2600-kangaroo","task":"Atari Games","dataset":"Atari 2600 Kangaroo","model":"IMPALA (deep)","rank_in_archive_order":35,"of":47,"metrics":{"Score":"1632.00"},"uses_additional_data":false},{"leaderboard":"/sota/atari-games-on-atari-2600-krull","task":"Atari Games","dataset":"Atari 2600 Krull","model":"IMPALA (deep)","rank_in_archive_order":28,"of":45,"metrics":{"Score":"8147.40"},"uses_additional_data":false},{"leaderboard":"/sota/atari-games-on-atari-2600-kung-fu-master","task":"Atari Games","dataset":"Atari 2600 Kung-Fu Master","model":"IMPALA (deep)","rank_in_archive_order":19,"of":43,"metrics":{"Score":"43375.50"},"uses_additional_data":false},{"leaderboard":"/sota/atari-games-on-atari-2600-montezumas-revenge","task":"Atari Games","dataset":"Atari 2600 Montezuma's Revenge","model":"IMPALA (deep)","rank_in_archive_order":44,"of":50,"metrics":{"Score":"0.00"},"uses_additional_data":false},{"leaderboard":"/sota/atari-games-on-atari-2600-ms-pacman","task":"Atari Games","dataset":"Atari 2600 Ms. Pacman","model":"IMPALA (deep)","rank_in_archive_order":12,"of":47,"metrics":{"Score":"7342.32"},"uses_additional_data":false},{"leaderboard":"/sota/atari-games-on-atari-2600-name-this-game","task":"Atari Games","dataset":"Atari 2600 Name This Game","model":"IMPALA (deep)","rank_in_archive_order":11,"of":43,"metrics":{"Score":"21537.20"},"uses_additional_data":false},{"leaderboard":"/sota/atari-games-on-atari-2600-phoenix","task":"Atari Games","dataset":"Atari 2600 Phoenix","model":"IMPALA (deep)","rank_in_archive_order":10,"of":21,"metrics":{"Score":"210996.45"},"uses_additional_data":false},{"leaderboard":"/sota/atari-games-on-atari-2600-pitfall","task":"Atari Games","dataset":"Atari 2600 Pitfall!","model":"IMPALA (deep)","rank_in_archive_order":22,"of":23,"metrics":{"Score":"-1.66"},"uses_additional_data":false},{"leaderboard":"/sota/atari-games-on-atari-2600-pong","task":"Atari Games","dataset":"Atari 2600 Pong","model":"IMPALA (deep)","rank_in_archive_order":15,"of":52,"metrics":{"Score":"20.98"},"uses_additional_data":false},{"leaderboard":"/sota/atari-games-on-atari-2600-private-eye","task":"Atari Games","dataset":"Atari 2600 Private Eye","model":"IMPALA (deep)","rank_in_archive_order":48,"of":52,"metrics":{"Score":"98.50"},"uses_additional_data":false},{"leaderboard":"/sota/atari-games-on-atari-2600-qbert","task":"Atari Games","dataset":"Atari 2600 Q*Bert","model":"IMPALA (deep)","rank_in_archive_order":4,"of":57,"metrics":{"Score":"351200.12"},"uses_additional_data":false},{"leaderboard":"/sota/atari-games-on-atari-2600-river-raid","task":"Atari Games","dataset":"Atari 2600 River Raid","model":"IMPALA (deep)","rank_in_archive_order":6,"of":41,"metrics":{"Score":"29608.05"},"uses_additional_data":false},{"leaderboard":"/sota/atari-games-on-atari-2600-road-runner","task":"Atari Games","dataset":"Atari 2600 Road Runner","model":"IMPALA (deep)","rank_in_archive_order":19,"of":44,"metrics":{"Score":"57121.00"},"uses_additional_data":false},{"leaderboard":"/sota/atari-games-on-atari-2600-robotank","task":"Atari Games","dataset":"Atari 2600 Robotank","model":"IMPALA (deep)","rank_in_archive_order":36,"of":42,"metrics":{"Score":"12.96"},"uses_additional_data":false},{"leaderboard":"/sota/atari-games-on-atari-2600-seaquest","task":"Atari Games","dataset":"Atari 2600 Seaquest","model":"IMPALA (deep)","rank_in_archive_order":41,"of":57,"metrics":{"Score":"1753.20"},"uses_additional_data":false},{"leaderboard":"/sota/atari-games-on-atari-2600-skiing","task":"Atari Games","dataset":"Atari 2600 Skiing","model":"IMPALA (deep)","rank_in_archive_order":6,"of":23,"metrics":{"Score":"-10180.38"},"uses_additional_data":true},{"leaderboard":"/sota/atari-games-on-atari-2600-solaris","task":"Atari Games","dataset":"Atari 2600 Solaris","model":"IMPALA (deep)","rank_in_archive_order":19,"of":23,"metrics":{"Score":"2365.00"},"uses_additional_data":false},{"leaderboard":"/sota/atari-games-on-atari-2600-space-invaders","task":"Atari Games","dataset":"Atari 2600 Space Invaders","model":"IMPALA (deep)","rank_in_archive_order":9,"of":55,"metrics":{"Score":"43595.78"},"uses_additional_data":false},{"leaderboard":"/sota/atari-games-on-atari-2600-star-gunner","task":"Atari Games","dataset":"Atari 2600 Star Gunner","model":"IMPALA (deep)","rank_in_archive_order":8,"of":43,"metrics":{"Score":"200625.00"},"uses_additional_data":false},{"leaderboard":"/sota/atari-games-on-atari-2600-surround","task":"Atari Games","dataset":"Atari 2600 Surround","model":"IMPALA (deep)","rank_in_archive_order":8,"of":15,"metrics":{"Score":"7.56"},"uses_additional_data":false},{"leaderboard":"/sota/atari-games-on-atari-2600-tennis","task":"Atari Games","dataset":"Atari 2600 Tennis","model":"IMPALA (deep)","rank_in_archive_order":19,"of":43,"metrics":{"Score":"0.55"},"uses_additional_data":false},{"leaderboard":"/sota/atari-games-on-atari-2600-time-pilot","task":"Atari Games","dataset":"Atari 2600 Time Pilot","model":"IMPALA (deep)","rank_in_archive_order":10,"of":44,"metrics":{"Score":"48481.50"},"uses_additional_data":false},{"leaderboard":"/sota/atari-games-on-atari-2600-tutankham","task":"Atari Games","dataset":"Atari 2600 Tutankham","model":"IMPALA (deep)","rank_in_archive_order":11,"of":44,"metrics":{"Score":"292.11"},"uses_additional_data":false},{"leaderboard":"/sota/atari-games-on-atari-2600-up-and-down","task":"Atari Games","dataset":"Atari 2600 Up and Down","model":"IMPALA (deep)","rank_in_archive_order":11,"of":44,"metrics":{"Score":"332546.75"},"uses_additional_data":false},{"leaderboard":"/sota/atari-games-on-atari-2600-venture","task":"Atari Games","dataset":"Atari 2600 Venture","model":"IMPALA (deep)","rank_in_archive_order":52,"of":55,"metrics":{"Score":"0.00"},"uses_additional_data":false},{"leaderboard":"/sota/atari-games-on-atari-2600-video-pinball","task":"Atari Games","dataset":"Atari 2600 Video Pinball","model":"IMPALA (deep)","rank_in_archive_order":13,"of":42,"metrics":{"Score":"572898.27"},"uses_additional_data":false},{"leaderboard":"/sota/atari-games-on-atari-2600-wizard-of-wor","task":"Atari Games","dataset":"Atari 2600 Wizard of Wor","model":"IMPALA (deep)","rank_in_archive_order":22,"of":41,"metrics":{"Score":"9157.50"},"uses_additional_data":false},{"leaderboard":"/sota/atari-games-on-atari-2600-yars-revenge","task":"Atari Games","dataset":"Atari 2600 Yars Revenge","model":"IMPALA (deep)","rank_in_archive_order":11,"of":17,"metrics":{"Score":"84231.14"},"uses_additional_data":false},{"leaderboard":"/sota/atari-games-on-atari-2600-zaxxon","task":"Atari Games","dataset":"Atari 2600 Zaxxon","model":"IMPALA (deep)","rank_in_archive_order":9,"of":41,"metrics":{"Score":"32935.50"},"uses_additional_data":false},{"leaderboard":"/sota/atari-games-on-atari-games","task":"Atari Games","dataset":"Atari games","model":"IMPALA, deep","rank_in_archive_order":9,"of":12,"metrics":{"Mean Human Normalized Score":"957.34%"},"uses_additional_data":false},{"leaderboard":"/sota/atari-games-on-atari-57","task":"Atari Games","dataset":"Atari-57","model":"IMPALA, deep","rank_in_archive_order":8,"of":11,"metrics":{"Human World Record Breakthrough":"3","Mean Human Normalized Score":"957.34%"},"uses_additional_data":false}],"syntology":{"syntology_url":"https://syntology.ai/paper/1802.01561","atlas_url":"https://app.syntology.ai/?focus=1802.01561","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1802.01561"},"calls":[{"tool":"get_harvested_code_for_paper","arguments":{"arxiv_id":"1802.01561"},"returns":"the samples harvested from this paper, each with its run record; it does not verify the paper"},{"tool":"get_code","arguments_in":"samples[].code_sha256","returns":"one stored sample by its code_sha256; not shown on this site"}]},"developers":"https://syntology.ai/developers","held":true,"reason":"in_graph_layer","checked_against":null,"agent_calls":[{"tool":"get_harvested_code_for_paper","arguments":{"arxiv_id":"1802.01561"},"call":"get_harvested_code_for_paper(arxiv_id=\"1802.01561\")"},{"tool":"get_code","arguments_in":{"code_sha256":"syntology.samples[].code_sha256"},"call":"get_code(code_sha256=\"…\")"},{"tool":"get_citation_path","arguments":{"paper_1":"1802.01561"},"arguments_in":{"paper_2":"another paper's arXiv id or title"},"call":"get_citation_path(paper_1=\"1802.01561\", paper_2=\"…\")"},{"tool":"get_concepts_for_paper","arguments":{"arxiv_id":"1802.01561"},"call":"get_concepts_for_paper(arxiv_id=\"1802.01561\")"}],"by_repo":[{"repo":"deepmind/scalable_agent","kind":"official","samples":0,"ran":0,"instrument":0,"unverified":0},{"repo":"Sheepsody/Batched-Impala-PyTorch","kind":"listed","samples":2,"ran":1,"instrument":0,"unverified":1},{"repo":"crazydonkey200/neural-symbolic-machines","kind":"listed","samples":0,"ran":0,"instrument":0,"unverified":0,"harvested_for_other_papers":1,"harvested_for":["1807.02322"],"harvested_for_calls":[{"arxiv_id":"1807.02322","tool":"get_harvested_code_for_paper","arguments":{"arxiv_id":"1807.02322"},"call":"get_harvested_code_for_paper(arxiv_id=\"1807.02322\")"}]},{"repo":"deepmind/streetlearn","kind":"listed","samples":0,"ran":0,"instrument":0,"unverified":0,"harvested_for_other_papers":1,"harvested_for":["1903.01292"],"harvested_for_calls":[{"arxiv_id":"1903.01292","tool":"get_harvested_code_for_paper","arguments":{"arxiv_id":"1903.01292"},"call":"get_harvested_code_for_paper(arxiv_id=\"1903.01292\")"}]},{"repo":"facebookresearch/gala","kind":"listed","samples":1,"ran":1,"instrument":0,"unverified":0},{"repo":"facebookresearch/torchbeast","kind":"listed","samples":3,"ran":3,"instrument":3,"unverified":0},{"repo":"google-deepmind/scalable_agent","kind":"listed","samples":3,"ran":1,"instrument":1,"unverified":2},{"repo":"google-deepmind/streetlearn","kind":"listed","samples":0,"ran":0,"instrument":0,"unverified":0},{"repo":"google-research/valan","kind":"listed","samples":3,"ran":1,"instrument":1,"unverified":2},{"repo":"haje01/impala","kind":"listed","samples":1,"ran":0,"instrument":0,"unverified":1},{"repo":"heiner/scalable_agent","kind":"listed","samples":0,"ran":0,"instrument":0,"unverified":0,"harvested_for_other_papers":1,"harvested_for":["1910.03552"],"harvested_for_calls":[{"arxiv_id":"1910.03552","tool":"get_harvested_code_for_paper","arguments":{"arxiv_id":"1910.03552"},"call":"get_harvested_code_for_paper(arxiv_id=\"1910.03552\")"}]},{"repo":"jerrodparker20/adaptive-transformers-in-rl","kind":"listed","samples":0,"ran":0,"instrument":0,"unverified":0},{"repo":"michaelnny/deep_rl_zoo","kind":"listed","samples":0,"ran":0,"instrument":0,"unverified":0,"harvested_for_other_papers":2,"harvested_for":["1312.5602","2002.06038"],"harvested_for_calls":[{"arxiv_id":"1312.5602","tool":"get_harvested_code_for_paper","arguments":{"arxiv_id":"1312.5602"},"call":"get_harvested_code_for_paper(arxiv_id=\"1312.5602\")"},{"arxiv_id":"2002.06038","tool":"get_harvested_code_for_paper","arguments":{"arxiv_id":"2002.06038"},"call":"get_harvested_code_for_paper(arxiv_id=\"2002.06038\")"}]},{"repo":"theSparta/neural-symbolic-machines","kind":"listed","samples":0,"ran":0,"instrument":0,"unverified":0,"harvested_for_other_papers":1,"harvested_for":["1807.02322"],"harvested_for_calls":[{"arxiv_id":"1807.02322","tool":"get_harvested_code_for_paper","arguments":{"arxiv_id":"1807.02322"},"call":"get_harvested_code_for_paper(arxiv_id=\"1807.02322\")"}]},{"repo":"threewisemonkeys-as/torched_impala","kind":"listed","samples":0,"ran":0,"instrument":0,"unverified":0},{"repo":"urw7rs/spiralpp","kind":"listed","samples":2,"ran":0,"instrument":0,"unverified":2},{"repo":"villinvic/Georges","kind":"listed","samples":14,"ran":7,"instrument":0,"unverified":7},{"repo":"windstrip/DeepMind-StreetLearn","kind":"listed","samples":0,"ran":0,"instrument":0,"unverified":0},{"repo":"deepmind/haiku","kind":"listed","samples":0,"ran":0,"instrument":0,"unverified":0},{"repo":"deepmind/rlax","kind":"listed","samples":1,"ran":1,"instrument":1,"unverified":0},{"repo":"opendilab/DI-engine","kind":"listed","samples":0,"ran":0,"instrument":0,"unverified":0,"harvested_for_other_papers":4,"harvested_for":["1707.01495","1901.02860","2106.01345","2304.12824"],"harvested_for_calls":[{"arxiv_id":"1707.01495","tool":"get_harvested_code_for_paper","arguments":{"arxiv_id":"1707.01495"},"call":"get_harvested_code_for_paper(arxiv_id=\"1707.01495\")"},{"arxiv_id":"1901.02860","tool":"get_harvested_code_for_paper","arguments":{"arxiv_id":"1901.02860"},"call":"get_harvested_code_for_paper(arxiv_id=\"1901.02860\")"},{"arxiv_id":"2106.01345","tool":"get_harvested_code_for_paper","arguments":{"arxiv_id":"2106.01345"},"call":"get_harvested_code_for_paper(arxiv_id=\"2106.01345\")"},{"arxiv_id":"2304.12824","tool":"get_harvested_code_for_paper","arguments":{"arxiv_id":"2304.12824"},"call":"get_harvested_code_for_paper(arxiv_id=\"2304.12824\")"}]},{"repo":"ray-project/ray","kind":"listed","samples":0,"ran":0,"instrument":0,"unverified":0},{"repo":"seolhokim/DistributedRL-Pytorch-Ray","kind":"listed","samples":2,"ran":1,"instrument":0,"unverified":1},{"repo":"seolhokim/SimpleDistributedRL","kind":"listed","samples":2,"ran":0,"instrument":0,"unverified":2},{"repo":"deepmind/lab","kind":"found_in_text","samples":0,"ran":0,"instrument":0,"unverified":0}],"by_repo_harvested_for_is":"harvested_for: the arXiv ids (as Syntology's graph holds them) of every paper whose samples Syntology's graph links to this repository, in arXiv-id order, complete; the page names the first 3 and says how many more. A link only: it does not say the papers are the same work, that one copied the other, or that the code implements this paper's method; harvested_for_calls gives the get_harvested_code_for_paper call for each arXiv-shaped id among them","by_repo_is":"one row per repository in the archive's code links, Syntology's graph links or the samples; samples 0 means no sample is linked to this paper, a statement about Syntology's coverage, not about the repository: with harvested_for_other_papers present, Syntology harvested the repository for that many other papers, and without it, Syntology harvested nothing from it; placed_by_identical_code counts samples whose link records no repository, placed here because identical code was harvested from this repository for another paper; ran counts executions on a synthesized input and instrument counts failures of Syntology's instrument, not of the code","assemblies":[{"assembly_sha256":"0107a796900a3774","source_kind":"harvested","method_name":"IMPALA","realizes_method":"IMPALA","graph_method":"IMPALA","realizes_severed":false,"claim":"The code implements IMPALA, a scalable distributed deep reinforcement learning agent with importance weighted actor-learner architectures.","centrality":"contribution","entry":"Impala","entry_sha256":"cd20ae279ac1aa9f","n_bricks":2,"bricks":[{"entry":"Impala","code_sha256":"cd20ae279ac1aa9f","role":"entry","order":0,"level":0,"status":"unverified"},{"entry":"VTrace","code_sha256":"a7ffabde1fe6a3c9","role":"loss","order":1,"level":1,"status":"ran"}],"ran_individually":1,"ran_individually_constructed":1,"ran_individually_by_status":{"ran":1},"end_to_end":{"ran":false,"level":0},"level_lowered":null,"claim_match":"IMPLEMENTS","claim_match_rule":"single_judge","claim_match_basis":"judge:global.anthropic.claude-sonnet-4-5-20250929-v1:0","claim_match_judges":["global.anthropic.claude-sonnet-4-5-20250929-v1:0"],"label_verdict":"matches","label_verdict_judged":true,"suggested_method":null,"batch_at":"2026-09-09T22:44:46+00:00","sibling_group":"cf99aec1c87f","n_siblings":10,"retention":"keep","provenance":"assembly:harvest_method_v6","attached_at":"2026-09-09T22:44:46+00:00","attached_provenance":"assembly:harvest_method_v6"},{"assembly_sha256":"091c7bf6bdeabc01","source_kind":"harvested","method_name":"IMPALA","realizes_method":"IMPALA","graph_method":"IMPALA","realizes_severed":false,"claim":"This code implements the IMPALA algorithm's core off-policy correction using V-trace importance weighting to adjust actor-learners' trajectories for scalable distributed deep reinforcement learning.","centrality":"contribution","entry":"from_logits","entry_sha256":"c0ca8087e51d7e1d","n_bricks":3,"bricks":[{"entry":"from_logits","code_sha256":"c0ca8087e51d7e1d","role":"entry","order":0,"level":0,"status":"unverified"},{"entry":"from_importance_weights","code_sha256":"86f7ee994e64dc88","role":"helper","order":1,"level":0,"status":"unverified"},{"entry":"log_probs_from_logits_and_actions","code_sha256":"a872fa719c5242ff","role":"helper","order":2,"level":1,"status":"ran_fixture"}],"ran_individually":1,"ran_individually_constructed":0,"ran_individually_by_status":{"ran_fixture":1},"end_to_end":{"ran":false,"level":0},"level_lowered":null,"claim_match":"IMPLEMENTS","claim_match_rule":"single_judge","claim_match_basis":"judge:global.anthropic.claude-sonnet-4-5-20250929-v1:0","claim_match_judges":["global.anthropic.claude-sonnet-4-5-20250929-v1:0"],"label_verdict":"matches","label_verdict_judged":true,"suggested_method":null,"batch_at":"2026-09-09T22:44:46+00:00","sibling_group":"cf99aec1c87f","n_siblings":10,"retention":"keep","provenance":"assembly:harvest_method_v6","attached_at":"2026-09-09T22:44:46+00:00","attached_provenance":"assembly:harvest_method_v6"},{"assembly_sha256":"10c5b0ac18e3f50f","source_kind":"harvested","method_name":"IMPALA","realizes_method":"IMPALA","graph_method":"IMPALA","realizes_severed":false,"claim":"IMPALA is a distributed deep reinforcement learning agent using importance weighted actor-learner architectures to handle large-scale training across multiple tasks","centrality":"contribution","entry":"AC","entry_sha256":"f34df61f30b311d5","n_bricks":14,"bricks":[{"entry":"AC","code_sha256":"f34df61f30b311d5","role":"entry","order":0,"level":0,"status":"unverified"},{"entry":"ActionStateProbs","code_sha256":"103308756a178abe","role":"helper","order":1,"level":0,"status":"unverified"},{"entry":"CategoricalActor","code_sha256":"e05eecb1a5750a6c","role":"helper","order":2,"level":1,"status":"ran"},{"entry":"Default","code_sha256":"ceddd134b3dd01f7","role":"helper","order":3,"level":0,"status":"unverified"},{"entry":"PlayerState","code_sha256":"cbb6758024239ec3","role":"helper","order":4,"level":0,"status":"unverified"},{"entry":"V","code_sha256":"7d75b7a3afdfddc6","role":"model","order":5,"level":1,"status":"ran"},{"entry":"nn_crossover","code_sha256":"e1569fbaca09c124","role":"helper","order":6,"level":0,"status":"unverified"},{"entry":"Categorical","code_sha256":"89ed626ce6f952a2","role":"helper","order":7,"level":1,"status":"ran"},{"entry":"ConfigLoader","code_sha256":"4d9828f13202e523","role":"helper","order":8,"level":1,"status":"ran"},{"entry":"layer_crossover","code_sha256":"a22618d583e622fe","role":"helper","order":9,"level":0,"status":"unverified"},{"entry":"pairwise_cross_corr","code_sha256":"ba92bb44edd2ada6","role":"helper","order":10,"level":1,"status":"ran_honours"},{"entry":"safe_crossover","code_sha256":"d9e1fb4c37c2e728","role":"helper","order":11,"level":1,"status":"ran_violates"},{"entry":"Distribution","code_sha256":"6490dcf1e1570c31","role":"helper","order":12,"level":1,"status":"ran"},{"entry":"corr_matrix","code_sha256":"9f5db323eec0eeba","role":"helper","order":13,"level":0,"status":"unverified"}],"ran_individually":7,"ran_individually_constructed":3,"ran_individually_by_status":{"ran":5,"ran_honours":1,"ran_violates":1},"end_to_end":{"ran":false,"level":0},"level_lowered":null,"claim_match":"COMPONENT","claim_match_rule":"single_judge","claim_match_basis":"judge:global.anthropic.claude-sonnet-4-5-20250929-v1:0","claim_match_judges":["global.anthropic.claude-sonnet-4-5-20250929-v1:0"],"label_verdict":"cannot_tell","label_verdict_judged":true,"suggested_method":null,"batch_at":"2026-09-09T22:44:46+00:00","sibling_group":"cf99aec1c87f","n_siblings":10,"retention":"defer","provenance":"assembly:harvest_method_v6","attached_at":"2026-09-09T22:44:46+00:00","attached_provenance":"assembly:harvest_method_v6"},{"assembly_sha256":"48ba37512cd9010c","source_kind":"harvested","method_name":"IMPALA","realizes_method":"IMPALA","graph_method":"IMPALA","realizes_severed":false,"claim":"This code implements the V-trace off-policy actor-critic algorithm, which is the core method proposed in IMPALA for handling distributed training with importance weighting.","centrality":"contribution","entry":"from_logits","entry_sha256":"715b439b8761ea76","n_bricks":3,"bricks":[{"entry":"from_logits","code_sha256":"715b439b8761ea76","role":"entry","order":0,"level":1,"status":"ran_fixture"},{"entry":"action_log_probs","code_sha256":"815b225c5ab9f314","role":"helper","order":1,"level":1,"status":"ran_draft_wrong"},{"entry":"from_importance_weights","code_sha256":"123172de8a1bc477","role":"helper","order":2,"level":1,"status":"ran_draft_wrong"}],"ran_individually":3,"ran_individually_constructed":0,"ran_individually_by_status":{"ran_draft_wrong":2,"ran_fixture":1},"end_to_end":{"ran":false,"level":0},"level_lowered":null,"claim_match":"IMPLEMENTS","claim_match_rule":"single_judge","claim_match_basis":"judge:global.anthropic.claude-sonnet-4-5-20250929-v1:0","claim_match_judges":["global.anthropic.claude-sonnet-4-5-20250929-v1:0"],"label_verdict":"matches","label_verdict_judged":true,"suggested_method":null,"batch_at":"2026-09-09T22:44:46+00:00","sibling_group":"cf99aec1c87f","n_siblings":10,"retention":"keep","provenance":"assembly:harvest_method_v6","attached_at":"2026-09-09T22:44:46+00:00","attached_provenance":"assembly:harvest_method_v6"},{"assembly_sha256":"77056a81045f76b6","source_kind":"harvested","method_name":"IMPALA","realizes_method":"IMPALA","graph_method":"IMPALA","realizes_severed":false,"claim":"This code implements the IMPALA distributed reinforcement learning algorithm with importance-weighted actor-learner architectures for scalable training.","centrality":"contribution","entry":"GALA_A2C","entry_sha256":"aad00ea22af3c855","n_bricks":1,"bricks":[{"entry":"GALA_A2C","code_sha256":"aad00ea22af3c855","role":"entry","order":0,"level":1,"status":"ran"}],"ran_individually":1,"ran_individually_constructed":1,"ran_individually_by_status":{"ran":1},"end_to_end":{"ran":false,"level":0},"level_lowered":null,"claim_match":"IMPLEMENTS","claim_match_rule":"single_judge","claim_match_basis":"judge:global.anthropic.claude-sonnet-4-5-20250929-v1:0","claim_match_judges":["global.anthropic.claude-sonnet-4-5-20250929-v1:0"],"label_verdict":"matches","label_verdict_judged":true,"suggested_method":null,"batch_at":"2026-09-09T22:44:46+00:00","sibling_group":"cf99aec1c87f","n_siblings":10,"retention":"keep","provenance":"assembly:harvest_method_v6","attached_at":"2026-09-09T22:44:46+00:00","attached_provenance":"assembly:harvest_method_v6"},{"assembly_sha256":"7ae296120fb836e2","source_kind":"harvested","method_name":"IMPALA","realizes_method":"IMPALA","graph_method":"IMPALA","realizes_severed":false,"claim":"This code implements the IMPALA method's loss calculation and backpropagation using V-trace for off-policy correction and policy gradient updates.","centrality":"contribution","entry":"calc_loss_and_backprop","entry_sha256":"cb89e31851cc2931","n_bricks":1,"bricks":[{"entry":"calc_loss_and_backprop","code_sha256":"cb89e31851cc2931","role":"entry","order":0,"level":0,"status":"unverified"}],"ran_individually":0,"ran_individually_constructed":0,"ran_individually_by_status":{},"end_to_end":{"ran":false,"level":0},"level_lowered":null,"claim_match":"IMPLEMENTS","claim_match_rule":"single_judge","claim_match_basis":"judge:global.anthropic.claude-sonnet-4-5-20250929-v1:0","claim_match_judges":["global.anthropic.claude-sonnet-4-5-20250929-v1:0"],"label_verdict":"matches","label_verdict_judged":true,"suggested_method":null,"batch_at":"2026-09-09T22:44:46+00:00","sibling_group":"cf99aec1c87f","n_siblings":10,"retention":"keep","provenance":"assembly:harvest_method_v6","attached_at":"2026-09-09T22:44:46+00:00","attached_provenance":"assembly:harvest_method_v6"},{"assembly_sha256":"80355a363df49649","source_kind":"harvested","method_name":"IMPALA","realizes_method":"IMPALA","graph_method":"IMPALA","realizes_severed":false,"claim":"This code implements the IMPALA algorithm's learner component, which computes gradients using importance-weighted actor-learner architectures for scalable distributed deep reinforcement learning.","centrality":"contribution","entry":"ImpalaLearner","entry_sha256":"b3a1158468bd53aa","n_bricks":2,"bricks":[{"entry":"ImpalaLearner","code_sha256":"b3a1158468bd53aa","role":"entry","order":0,"level":0,"status":"unverified"},{"entry":"Learner","code_sha256":"3fdd0c84f214c2bb","role":"helper","order":1,"level":1,"status":"ran"}],"ran_individually":1,"ran_individually_constructed":1,"ran_individually_by_status":{"ran":1},"end_to_end":{"ran":false,"level":0},"level_lowered":null,"claim_match":"IMPLEMENTS","claim_match_rule":"single_judge","claim_match_basis":"judge:global.anthropic.claude-sonnet-4-5-20250929-v1:0","claim_match_judges":["global.anthropic.claude-sonnet-4-5-20250929-v1:0"],"label_verdict":"matches","label_verdict_judged":true,"suggested_method":null,"batch_at":"2026-09-09T22:44:46+00:00","sibling_group":"cf99aec1c87f","n_siblings":10,"retention":"keep","provenance":"assembly:harvest_method_v6","attached_at":"2026-09-09T22:44:46+00:00","attached_provenance":"assembly:harvest_method_v6"},{"assembly_sha256":"978afc124d357fa8","source_kind":"harvested","method_name":"IMPALA","realizes_method":"IMPALA","graph_method":"IMPALA","realizes_severed":false,"claim":"Implements the V-trace off-policy actor-critic algorithm with importance weighting for distributed deep reinforcement learning.","centrality":"contribution","entry":"from_logits","entry_sha256":"e26d17c678348c08","n_bricks":3,"bricks":[{"entry":"from_logits","code_sha256":"e26d17c678348c08","role":"entry","order":0,"level":0,"status":"unverified"},{"entry":"action_log_probs","code_sha256":"bc2ac55256ed974b","role":"helper","order":1,"level":0,"status":"unverified"},{"entry":"from_importance_weights","code_sha256":"123172de8a1bc477","role":"helper","order":2,"level":1,"status":"ran_draft_wrong"}],"ran_individually":1,"ran_individually_constructed":0,"ran_individually_by_status":{"ran_draft_wrong":1},"end_to_end":{"ran":false,"level":0},"level_lowered":null,"claim_match":"IMPLEMENTS","claim_match_rule":"single_judge","claim_match_basis":"judge:global.anthropic.claude-sonnet-4-5-20250929-v1:0","claim_match_judges":["global.anthropic.claude-sonnet-4-5-20250929-v1:0"],"label_verdict":"matches","label_verdict_judged":true,"suggested_method":null,"batch_at":"2026-09-09T22:44:46+00:00","sibling_group":"cf99aec1c87f","n_siblings":10,"retention":"keep","provenance":"assembly:harvest_method_v6","attached_at":"2026-09-09T22:44:46+00:00","attached_provenance":"assembly:harvest_method_v6"},{"assembly_sha256":"be82921a5a79d6a3","source_kind":"harvested","method_name":"IMPALA","realizes_method":"IMPALA","graph_method":"IMPALA","realizes_severed":false,"claim":"The paper claims this code implements the IMPALA algorithm, a scalable distributed deep reinforcement learning method using importance-weighted actor-learner architectures.","centrality":"contribution","entry":"train","entry_sha256":"01b62761de35ed90","n_bricks":2,"bricks":[{"entry":"train","code_sha256":"01b62761de35ed90","role":"entry","order":0,"level":0,"status":"unverified"},{"entry":"get_vtrace_and_advantages","code_sha256":"b1527fc2ce13e346","role":"loss","order":1,"level":0,"status":"unverified"}],"ran_individually":0,"ran_individually_constructed":0,"ran_individually_by_status":{},"end_to_end":{"ran":false,"level":0},"level_lowered":null,"claim_match":"IMPLEMENTS","claim_match_rule":"single_judge","claim_match_basis":"judge:global.anthropic.claude-sonnet-4-5-20250929-v1:0","claim_match_judges":["global.anthropic.claude-sonnet-4-5-20250929-v1:0"],"label_verdict":"matches","label_verdict_judged":true,"suggested_method":null,"batch_at":"2026-09-09T22:44:46+00:00","sibling_group":"cf99aec1c87f","n_siblings":10,"retention":"keep","provenance":"assembly:harvest_method_v6","attached_at":"2026-09-09T22:44:46+00:00","attached_provenance":"assembly:harvest_method_v6"},{"assembly_sha256":"d4d62036f650d684","source_kind":"harvested","method_name":"IMPALA","realizes_method":"IMPALA","graph_method":"IMPALA","realizes_severed":false,"claim":"The code implements the V-trace off-policy actor-critic algorithm, which is the core method proposed in IMPALA for scalable distributed deep reinforcement learning.","centrality":"contribution","entry":"vtrace","entry_sha256":"e565e1e08272948c","n_bricks":1,"bricks":[{"entry":"vtrace","code_sha256":"e565e1e08272948c","role":"entry","order":0,"level":1,"status":"ran_fixture"}],"ran_individually":1,"ran_individually_constructed":0,"ran_individually_by_status":{"ran_fixture":1},"end_to_end":{"ran":false,"level":0},"level_lowered":null,"claim_match":"IMPLEMENTS","claim_match_rule":"single_judge","claim_match_basis":"judge:global.anthropic.claude-sonnet-4-5-20250929-v1:0","claim_match_judges":["global.anthropic.claude-sonnet-4-5-20250929-v1:0"],"label_verdict":"matches","label_verdict_judged":true,"suggested_method":null,"batch_at":"2026-09-09T22:44:46+00:00","sibling_group":"cf99aec1c87f","n_siblings":10,"retention":"keep","provenance":"assembly:harvest_method_v6","attached_at":"2026-09-09T22:44:46+00:00","attached_provenance":"assembly:harvest_method_v6"},{"assembly_sha256":"e3065d54eaeb335a","source_kind":"harvested","method_name":"IMPALA","realizes_method":"IMPALA","graph_method":"IMPALA","realizes_severed":false,"claim":"The paper claims this code implements the V-trace algorithm for off-policy correction in the IMPALA distributed deep reinforcement learning architecture.","centrality":"contribution","entry":"from_logits","entry_sha256":"2b5d90526b4ad312","n_bricks":3,"bricks":[{"entry":"from_logits","code_sha256":"2b5d90526b4ad312","role":"entry","order":0,"level":0,"status":"unverified"},{"entry":"from_importance_weights","code_sha256":"e11ee068514828e6","role":"helper","order":1,"level":0,"status":"unverified"},{"entry":"log_probs_from_logits_and_actions","code_sha256":"a75de4dc4c61d7dc","role":"helper","order":2,"level":1,"status":"ran_fixture"}],"ran_individually":1,"ran_individually_constructed":0,"ran_individually_by_status":{"ran_fixture":1},"end_to_end":{"ran":false,"level":0},"level_lowered":null,"claim_match":"IMPLEMENTS","claim_match_rule":"single_judge","claim_match_basis":"judge:global.anthropic.claude-sonnet-4-5-20250929-v1:0","claim_match_judges":["global.anthropic.claude-sonnet-4-5-20250929-v1:0"],"label_verdict":"matches","label_verdict_judged":true,"suggested_method":null,"batch_at":"2026-09-09T22:44:46+00:00","sibling_group":"cf99aec1c87f","n_siblings":10,"retention":"keep","provenance":"assembly:harvest_method_v6","attached_at":"2026-09-09T22:44:46+00:00","attached_provenance":"assembly:harvest_method_v6"}],"assembly_sibling_groups":[{"group":"cf99aec1c87f","realizes_method":"IMPALA","source_kind":"harvested","batch_at":"2026-09-09T22:44:46+00:00","members":["0107a796900a3774","091c7bf6bdeabc01","10c5b0ac18e3f50f","48ba37512cd9010c","77056a81045f76b6","7ae296120fb836e2","80355a363df49649","978afc124d357fa8","be82921a5a79d6a3","d4d62036f650d684","e3065d54eaeb335a"]}],"assemblies_is":{"about":"What Syntology's graph records as this paper's claimed method, lifted into code: each assembly names its bricks (functions and classes), each with its own role and its own verification level. An assembly is not a check that the code implements the method correctly or reproduces the paper's results.","harvested":"assembled from code harvested from a repository linked to the paper","generated":"generated from the paper text, not the repository's code","end_to_end":"for a harvested assembly, the assembly has not been run end-to-end; for a generated one, end_to_end.level is the assembly's own level and against_independent_peer says whether it ran against a peer: an independent peer is a second implementation generated separately from the same paper text; neither implementation read the authors' code. At level 2 the two agreed numerically on the fixture's inputs; level 3 is recorded when property tests derived from the paper also passed on both, and each level 3 card prints how many its report lists","bricks_level":"each brick's own verification level in Syntology's graph (level 0: no recorded run), listed brick by brick and never combined into one level","ran_individually":"a COUNT of bricks that ran on their own on a fixture (split by status in ran_individually_by_status), not a level; instrument statuses are failures of Syntology's instrument, not of the code","siblings":"assemblies lifted from this paper in the same batch for the same method: alternative readings kept side by side; none replaces or supersedes another","judged":"Where a model read the code against the paper's claim, each assembly's label verdict is one model's judgement, kept in this page's JSON twin; it is not calibrated, so no card prints it. A generated assembly's label was set when its code was generated for the method, and no model judged it; its card prints it as \"by construction\" or \"not judged by a model\"","level_lowered":"a generated assembly whose level Syntology's graph lowered, with the level it had, the recorded reason and when","retention":"Syntology's spending triage for further verification, not a verdict","claim_match":"the claim_match vote: IMPLEMENTS, COMPONENT or UNCLEAR. Where claim_match_basis is \"judge:<model>\", it is one model's judgement of the assembly's label against the paper's claim (claim_match_rule single_judge, the model in claim_match_judges): not a verification and not a run. Where it is \"construction\", the value was set when the code was generated for this method and no model judged it, whatever claim_match_rule says. The page prints no claim match for any assembly","label_verdict":"whether the assembly's code is the method it is labelled with: matches, cannot_tell, mislabelled (suggested_method names what it looks like instead) or not_the_method; label_verdict_judged is true only when a model read the code (claim_match_basis \"judge:<model>\")","label_verdict_judged":"where true (claim_match_basis \"judge:<model>\"), label_verdict is a single model's judgement; not calibrated; not printed on the page; where false, it was set by construction, and the page prints it unless the node is shared with another paper (node_properties_written_for)","claim":"the claim text stored on the assembly node: for a harvested assembly, what the paper claims the code implements, as the lifting model wrote it; for a generated one, the specification the code was generated from. Not verified text","centrality":"how central the lifted method is to the paper, as the lifting step recorded it: contribution, component or incidental","v3_tests_passed_both_sides":"end_to_end.v3_tests_passed_both_sides: the number of property tests derived from the paper that passed on both implementations, as the attached report lists them; a level 3 card with 0 says its report lists none","ran_individually_constructed":"ran_individually_constructed: of the bricks counted in ran_individually, how many constructed an object rather than computing a result (Syntology's RAN record's rule, read from the graph-layer sample with the brick's code_sha256); a part of ran_individually, never subtracted from it and never a failure; null where a brick that ran has no sample in the graph layer this build read, so the figure was not counted"},"assemblies_call":{"tool":"assembly","arguments":{"arxiv_id":"1802.01561"},"call":"assembly(arxiv_id=\"1802.01561\")"},"read_at":"2026-10-05T00:36:11+00:00","read_at_is":"when the build read Syntology's graph, not when any sample ran","ran_record":{"url":"https://syntology.ai/api/ran/1802.01561.json","schema":"syntology.ran_record/1","counts_crosswalk":{"n_samples":"syntology.counts.lifted","n_ran":"syntology.counts.executed","n_ran_checked":"syntology.counts.checked","n_instrument":"syntology.counts.instrument_failures","n_unverified":"syntology.counts.no_recorded_run"},"note":"live record, measured at request time; may be newer than this page's graph read","badge":"https://syntology.ai/api/ran/1802.01561.svg"},"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/seolhokim/SimpleDistributedRL","reach":null},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/deepmind/rlax","reach":null},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/ray-project/ray/tree/master/rllib","reach":null},{"provenance":"deterministic:regex_extraction","url":"https://github.com/deepmind/lab","reach":{"status":"ok","spdx":"NOASSERTION"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/google-deepmind/streetlearn","reach":{"status":"ok","spdx":"Apache-2.0"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/crazydonkey200/neural-symbolic-machines","reach":{"status":"ok","spdx":"Apache-2.0"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/deepmind/streetlearn","reach":{"status":"ok","spdx":"Apache-2.0"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/deepmind/haiku","reach":{"status":"unanswered"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/jerrodparker20/adaptive-transformers-in-rl","reach":{"status":"ok"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/facebookresearch/torchbeast","reach":null},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/deepmind/scalable_agent","reach":{"status":"unanswered"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/villinvic/Georges","reach":null},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/windstrip/DeepMind-StreetLearn","reach":{"status":"unanswered"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/Sheepsody/Batched-Impala-PyTorch","reach":null},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/heiner/scalable_agent","reach":{"status":"ok","spdx":"Apache-2.0"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/google-research/valan","reach":null},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/theSparta/neural-symbolic-machines","reach":{"status":"ok","spdx":"Apache-2.0"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/facebookresearch/gala","reach":null},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/michaelnny/deep_rl_zoo","reach":null},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/seolhokim/DistributedRL-Pytorch-Ray","reach":null},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/google-deepmind/scalable_agent","reach":null},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/haje01/impala","reach":null},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/threewisemonkeys-as/torched_impala","reach":{"status":"unanswered"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/opendilab/DI-engine/blob/main/ding/policy/impala.py","reach":null},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/urw7rs/spiralpp","reach":null}],"summary":{"ran":8,"ran_draft_wrong":2,"ran_fixture":4,"ran_honours":1,"ran_violates":1,"unverified":18},"n_samples":34,"n_ran":16,"n_constructed":6,"n_ran_checked":10,"n_instrument":6,"n_unverified":18,"n_instrument_is":"failures of Syntology's instrument, not of the code","every_run_is_an_instrument_failure":false,"key_notes":{"n_ran_checked":"legacy name, kept unchanged so existing readers do not break: it counts the samples that ran with no instrument failure (honoured, violated, and ran with no contract checked); it does not mean a contract was checked, and the pages print it as 'K with no instrument failure', not 'K checked'","n_constructed":"a sub-count of the samples that ran, never subtracted from them and never a failure: an executed sample whose run returned an instance of its own class (fixture_out_type equals the entry name): the run built an object and did not compute a result (Syntology's RAN record, counts.constructed)"},"by_repo_kind":{"listed":{"samples":34,"ran":16,"n_ran_checked":10,"n_instrument":6,"repositories":11}},"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"},"official_not_harvested":{"repositories":["deepmind/scalable_agent"],"harvested_for_other_papers":[0],"samples_from_other_repositories":34,"other_repositories":11,"samples_unlocated":0},"n_pointer_only_for_licence":3,"inline_ok_is":"inline_ok is true only when both licence gates allow Syntology to serve this code's text: this paper's link (inline_ok_link, from the licence of this paper's copy) and the stored copy of the same code that Syntology serves, which may have been first harvested from another repository. withheld_clause is Syntology's own wording of which gate keeps the text a pointer and why, and is null when inline_ok is true. This site shows no code text either way; n_pointer_only_for_licence counts samples with inline_ok false (both gates), n_pointer_only_link_allows those of them whose inline_ok_link is true","n_pointer_only_link_allows":0,"fixture_fields_is":{"signature_and_fixture_out_type":"the arguments Syntology's fixture called the sample with, each as name:type/rank/element kind (? where none was recorded), and the type of what the fixture's run returned, exactly as the harness recorded them; the arguments and the returned type were recorded by two separate runs of the same fixture. No output value is shown, and a returned type says nothing about whether the output was right","level_recorded_at":"when Syntology's graph wrote the sample's verification level, not when the code executed; absent where the level was written before the date was kept, and never filled in with the build date","present_on":"samples that ran only; a key is absent, never empty, where the graph records nothing"},"n_ran_with_level_date":16,"n_ran_without_level_date":0,"n_ran_signature_not_shown":0,"levels_written_between":{"first":"2026-09-22","last":"2026-09-24","is":"the first and last UTC dates on which Syntology's graph wrote a verification level for a sample on this page that ran, not when the code executed"},"code_page_min_papers":5,"code_page_is":"a page for the entry name across every paper's harvested code; the name is a string, not an identity","samples":[{"code_sha256":"89ed626ce6f952a2","code_sha256_prefix":"89ed626ce6f952a2","entry":"Categorical","repo":"villinvic/Georges","repo_kind":"listed","path":"training/RL.py","file_url":"https://github.com/villinvic/Georges/blob/HEAD/training/RL.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"signature":"x:EagerTensor/2/float, param:dict/0/?","fixture_out_type":"EagerTensor","level_recorded_at":"2026-09-24T15:16:18.137819+00:00","code_page":"/code/categorical","census":null,"licence":"MIT","inline_ok":true,"inline_ok_link":true,"withheld_clause":null,"mcp_get_code":{"code_sha256":"89ed626ce6f952a2"}},{"code_sha256":"e05eecb1a5750a6c","code_sha256_prefix":"e05eecb1a5750a6c","entry":"CategoricalActor","repo":"villinvic/Georges","repo_kind":"listed","path":"training/RL.py","file_url":"https://github.com/villinvic/Georges/blob/HEAD/training/RL.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":"deterministic","behaviour_fingerprint":false,"fixture_out_type":"CategoricalActor","level_recorded_at":"2026-09-22T14:31:46.068493+00:00","code_page":null,"census":null,"licence":"MIT","inline_ok":true,"inline_ok_link":true,"withheld_clause":null,"mcp_get_code":{"code_sha256":"e05eecb1a5750a6c"}},{"code_sha256":"4d9828f13202e523","code_sha256_prefix":"4d9828f13202e523","entry":"ConfigLoader","repo":"villinvic/Georges","repo_kind":"listed","path":"training/RL.py","file_url":"https://github.com/villinvic/Georges/blob/HEAD/training/RL.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"signature":"config_file:str/0/str","fixture_out_type":"ConfigParser","level_recorded_at":"2026-09-24T15:16:18.137819+00:00","code_page":null,"census":null,"licence":"MIT","inline_ok":true,"inline_ok_link":true,"withheld_clause":null,"mcp_get_code":{"code_sha256":"4d9828f13202e523"}},{"code_sha256":"6490dcf1e1570c31","code_sha256_prefix":"6490dcf1e1570c31","entry":"Distribution","repo":"villinvic/Georges","repo_kind":"listed","path":"training/RL.py","file_url":"https://github.com/villinvic/Georges/blob/HEAD/training/RL.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"fixture_out_type":"Distribution","level_recorded_at":"2026-09-22T14:31:46.068493+00:00","code_page":"/code/distribution","census":null,"licence":"MIT","inline_ok":true,"inline_ok_link":true,"withheld_clause":null,"mcp_get_code":{"code_sha256":"6490dcf1e1570c31"}},{"code_sha256":"aad00ea22af3c855","code_sha256_prefix":"aad00ea22af3c855","entry":"GALA_A2C","repo":"facebookresearch/gala","repo_kind":"listed","path":"gala/gala_a2c.py","file_url":"https://github.com/facebookresearch/gala/blob/HEAD/gala/gala_a2c.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"fixture_out_type":"GALA_A2C","level_recorded_at":"2026-09-22T14:31:46.068493+00:00","code_page":null,"census":null,"licence":"NOASSERTION","inline_ok":false,"inline_ok_link":false,"withheld_clause":"GitHub could not classify the licence of this paper's repository, facebookresearch/gala (NOASSERTION)","mcp_get_code":{"code_sha256":"aad00ea22af3c855"}},{"code_sha256":"3fdd0c84f214c2bb","code_sha256_prefix":"3fdd0c84f214c2bb","entry":"Learner","repo":"seolhokim/DistributedRL-Pytorch-Ray","repo_kind":"listed","path":"agents/runners/learners/impala_learner.py","file_url":"https://github.com/seolhokim/DistributedRL-Pytorch-Ray/blob/HEAD/agents/runners/learners/impala_learner.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"fixture_out_type":"Learner","level_recorded_at":"2026-09-22T14:31:46.068493+00:00","code_page":"/code/learner","census":null,"licence":"MIT","inline_ok":true,"inline_ok_link":true,"withheld_clause":null,"mcp_get_code":{"code_sha256":"3fdd0c84f214c2bb"}},{"code_sha256":"7d75b7a3afdfddc6","code_sha256_prefix":"7d75b7a3afdfddc6","entry":"V","repo":"villinvic/Georges","repo_kind":"listed","path":"training/RL.py","file_url":"https://github.com/villinvic/Georges/blob/HEAD/training/RL.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":"deterministic","behaviour_fingerprint":false,"fixture_out_type":"V","level_recorded_at":"2026-09-22T14:31:46.068493+00:00","code_page":null,"census":null,"licence":"MIT","inline_ok":true,"inline_ok_link":true,"withheld_clause":null,"mcp_get_code":{"code_sha256":"7d75b7a3afdfddc6"}},{"code_sha256":"a7ffabde1fe6a3c9","code_sha256_prefix":"a7ffabde1fe6a3c9","entry":"VTrace","repo":"Sheepsody/Batched-Impala-PyTorch","repo_kind":"listed","path":"src/IMPALA.py","file_url":"https://github.com/Sheepsody/Batched-Impala-PyTorch/blob/HEAD/src/IMPALA.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":"deterministic","behaviour_fingerprint":false,"fixture_out_type":"VTrace","level_recorded_at":"2026-09-22T14:31:46.068493+00:00","code_page":null,"census":null,"licence":"NONE","inline_ok":false,"inline_ok_link":false,"withheld_clause":"GitHub detected no licence in this paper's repository, Sheepsody/Batched-Impala-PyTorch when it was checked","mcp_get_code":{"code_sha256":"a7ffabde1fe6a3c9"}},{"code_sha256":"815b225c5ab9f314","code_sha256_prefix":"815b225c5ab9f314","entry":"action_log_probs","repo":"facebookresearch/torchbeast","repo_kind":"listed","path":"torchbeast/core/vtrace.py","file_url":"https://github.com/facebookresearch/torchbeast/blob/HEAD/torchbeast/core/vtrace.py","link_basis":"first_harvest_node","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"MISDECLARED","metamorphic_tier":null,"behaviour_fingerprint":false,"signature":"policy_logits:Tensor/3/float, actions:Tensor/2/int","fixture_out_type":"Tensor","level_recorded_at":"2026-09-22T14:31:46.068493+00:00","code_page":null,"census":null,"licence":"Apache-2.0","inline_ok":true,"inline_ok_link":true,"withheld_clause":null,"mcp_get_code":{"code_sha256":"815b225c5ab9f314"}},{"code_sha256":"123172de8a1bc477","code_sha256_prefix":"123172de8a1bc477","entry":"from_importance_weights","repo":"facebookresearch/torchbeast","repo_kind":"listed","path":"torchbeast/core/vtrace.py","file_url":"https://github.com/facebookresearch/torchbeast/blob/HEAD/torchbeast/core/vtrace.py","link_basis":"first_harvest_node","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"MISDECLARED","metamorphic_tier":null,"behaviour_fingerprint":false,"signature":"log_rhos:Tensor/2/float, discounts:Tensor/2/float, rewards:Tensor/2/float, values:Tensor/2/float, bootstrap_value:Tensor/1/float, clip_rho_threshold:float/0/float, clip_pg_rho_threshold:float/0/float","fixture_out_type":"VTraceReturns","level_recorded_at":"2026-09-22T14:31:46.068493+00:00","code_page":null,"census":null,"licence":"Apache-2.0","inline_ok":true,"inline_ok_link":true,"withheld_clause":null,"mcp_get_code":{"code_sha256":"123172de8a1bc477"}},{"code_sha256":"715b439b8761ea76","code_sha256_prefix":"715b439b8761ea76","entry":"from_logits","repo":"facebookresearch/torchbeast","repo_kind":"listed","path":"torchbeast/core/vtrace.py","file_url":"https://github.com/facebookresearch/torchbeast/blob/HEAD/torchbeast/core/vtrace.py","link_basis":"first_harvest_node","language":"python","status":"ran_fixture","verification_level":1,"contract_check":"RAISES","metamorphic_tier":null,"behaviour_fingerprint":false,"signature":"behavior_policy_logits:Tensor/3/float, target_policy_logits:Tensor/3/float, actions:Tensor/2/int, discounts:Tensor/2/float, rewards:Tensor/2/float, values:Tensor/2/float, bootstrap_value:Tensor/1/float, clip_rho_threshold:float/0/float, clip_pg_rho_threshold:float/0/float","fixture_out_type":"VTraceFromLogitsReturns","level_recorded_at":"2026-09-22T14:31:46.068493+00:00","code_page":null,"census":null,"licence":"Apache-2.0","inline_ok":true,"inline_ok_link":true,"withheld_clause":null,"mcp_get_code":{"code_sha256":"715b439b8761ea76"}},{"code_sha256":"a872fa719c5242ff","code_sha256_prefix":"a872fa719c5242ff","entry":"log_probs_from_logits_and_actions","repo":"google-research/valan","repo_kind":"listed","path":"framework/vtrace.py","file_url":"https://github.com/google-research/valan/blob/HEAD/framework/vtrace.py","link_basis":"first_harvest_node","language":"python","status":"ran_fixture","verification_level":1,"contract_check":"RAISES","metamorphic_tier":"invariant","behaviour_fingerprint":false,"signature":"policy_logits:EagerTensor/3/float, actions:EagerTensor/2/int","fixture_out_type":"EagerTensor","level_recorded_at":"2026-09-22T14:31:46.068493+00:00","code_page":null,"census":null,"licence":"Apache-2.0","inline_ok":true,"inline_ok_link":true,"withheld_clause":null,"mcp_get_code":{"code_sha256":"a872fa719c5242ff"}},{"code_sha256":"a75de4dc4c61d7dc","code_sha256_prefix":"a75de4dc4c61d7dc","entry":"log_probs_from_logits_and_actions","repo":"google-deepmind/scalable_agent","repo_kind":"listed","path":"vtrace.py","file_url":"https://github.com/google-deepmind/scalable_agent/blob/HEAD/vtrace.py","link_basis":"first_harvest_node","language":"python","status":"ran_fixture","verification_level":1,"contract_check":"RAISES","metamorphic_tier":null,"behaviour_fingerprint":false,"signature":"policy_logits:EagerTensor/3/float, actions:EagerTensor/2/int","fixture_out_type":"EagerTensor","level_recorded_at":"2026-09-22T14:31:46.068493+00:00","code_page":null,"census":null,"licence":"Apache-2.0","inline_ok":true,"inline_ok_link":true,"withheld_clause":null,"mcp_get_code":{"code_sha256":"a75de4dc4c61d7dc"}},{"code_sha256":"ba92bb44edd2ada6","code_sha256_prefix":"ba92bb44edd2ada6","entry":"pairwise_cross_corr","repo":"villinvic/Georges","repo_kind":"listed","path":"training/RL.py","file_url":"https://github.com/villinvic/Georges/blob/HEAD/training/RL.py","link_basis":"first_harvest_node","language":"python","status":"ran_honours","verification_level":1,"contract_check":"HONOURS","metamorphic_tier":"invariant","behaviour_fingerprint":true,"signature":"La:ndarray/2/float, Lb:ndarray/2/float","fixture_out_type":"ndarray","level_recorded_at":"2026-09-22T14:31:46.068493+00:00","retrieve_with":{"tool":"get_code","code_sha256":"ba92bb44edd2ada6"},"code_page":null,"census":null,"licence":"MIT","inline_ok":true,"inline_ok_link":true,"withheld_clause":null,"mcp_get_code":{"code_sha256":"ba92bb44edd2ada6"}},{"code_sha256":"d9e1fb4c37c2e728","code_sha256_prefix":"d9e1fb4c37c2e728","entry":"safe_crossover","repo":"villinvic/Georges","repo_kind":"listed","path":"training/RL.py","file_url":"https://github.com/villinvic/Georges/blob/HEAD/training/RL.py","link_basis":"first_harvest_node","language":"python","status":"ran_violates","verification_level":1,"contract_check":"VIOLATES","metamorphic_tier":"invariant","behaviour_fingerprint":true,"signature":"ax:ndarray/1/float, bx:ndarray/1/float","fixture_out_type":"ndarray","level_recorded_at":"2026-09-22T14:31:46.068493+00:00","retrieve_with":{"tool":"get_code","code_sha256":"d9e1fb4c37c2e728"},"code_page":null,"census":null,"licence":"MIT","inline_ok":true,"inline_ok_link":true,"withheld_clause":null,"mcp_get_code":{"code_sha256":"d9e1fb4c37c2e728"}},{"code_sha256":"e565e1e08272948c","code_sha256_prefix":"e565e1e08272948c","entry":"vtrace","repo":"deepmind/rlax","repo_kind":"listed","path":"rlax/_src/vtrace.py","file_url":"https://github.com/deepmind/rlax/blob/HEAD/rlax/_src/vtrace.py","link_basis":"first_harvest_node","language":"python","status":"ran_fixture","verification_level":1,"contract_check":"RAISES","metamorphic_tier":null,"behaviour_fingerprint":false,"signature":"v_tm1:ArrayImpl/1/float, v_t:ArrayImpl/1/float, r_t:ArrayImpl/1/float, discount_t:ArrayImpl/1/float, rho_tm1:ArrayImpl/1/float, lambda_:float/0/float, clip_rho_threshold:float/0/float, stop_target_gradients:bool/0/bool, sample_mask:ArrayImpl/1/bool","fixture_out_type":"ArrayImpl","level_recorded_at":"2026-09-22T14:31:46.068493+00:00","code_page":null,"census":null,"licence":"Apache-2.0","inline_ok":true,"inline_ok_link":true,"withheld_clause":null,"mcp_get_code":{"code_sha256":"e565e1e08272948c"}},{"code_sha256":"f34df61f30b311d5","code_sha256_prefix":"f34df61f30b311d5","entry":"AC","repo":"villinvic/Georges","repo_kind":"listed","path":"training/RL.py","file_url":"https://github.com/villinvic/Georges/blob/HEAD/training/RL.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"code_page":null,"census":null,"licence":"MIT","inline_ok":true,"inline_ok_link":true,"withheld_clause":null,"mcp_get_code":{"code_sha256":"f34df61f30b311d5"}},{"code_sha256":"103308756a178abe","code_sha256_prefix":"103308756a178abe","entry":"ActionStateProbs","repo":"villinvic/Georges","repo_kind":"listed","path":"training/RL.py","file_url":"https://github.com/villinvic/Georges/blob/HEAD/training/RL.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"code_page":null,"census":null,"licence":"MIT","inline_ok":true,"inline_ok_link":true,"withheld_clause":null,"mcp_get_code":{"code_sha256":"103308756a178abe"}},{"code_sha256":"ceddd134b3dd01f7","code_sha256_prefix":"ceddd134b3dd01f7","entry":"Default","repo":"villinvic/Georges","repo_kind":"listed","path":"training/RL.py","file_url":"https://github.com/villinvic/Georges/blob/HEAD/training/RL.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"code_page":null,"census":null,"licence":"MIT","inline_ok":true,"inline_ok_link":true,"withheld_clause":null,"mcp_get_code":{"code_sha256":"ceddd134b3dd01f7"}},{"code_sha256":"cd20ae279ac1aa9f","code_sha256_prefix":"cd20ae279ac1aa9f","entry":"Impala","repo":"Sheepsody/Batched-Impala-PyTorch","repo_kind":"listed","path":"src/IMPALA.py","file_url":"https://github.com/Sheepsody/Batched-Impala-PyTorch/blob/HEAD/src/IMPALA.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"code_page":null,"census":null,"licence":"NONE","inline_ok":false,"inline_ok_link":false,"withheld_clause":"GitHub detected no licence in this paper's repository, Sheepsody/Batched-Impala-PyTorch when it was checked","mcp_get_code":{"code_sha256":"cd20ae279ac1aa9f"}},{"code_sha256":"b3a1158468bd53aa","code_sha256_prefix":"b3a1158468bd53aa","entry":"ImpalaLearner","repo":"seolhokim/DistributedRL-Pytorch-Ray","repo_kind":"listed","path":"agents/runners/learners/impala_learner.py","file_url":"https://github.com/seolhokim/DistributedRL-Pytorch-Ray/blob/HEAD/agents/runners/learners/impala_learner.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"code_page":null,"census":null,"licence":"MIT","inline_ok":true,"inline_ok_link":true,"withheld_clause":null,"mcp_get_code":{"code_sha256":"b3a1158468bd53aa"}},{"code_sha256":"cbb6758024239ec3","code_sha256_prefix":"cbb6758024239ec3","entry":"PlayerState","repo":"villinvic/Georges","repo_kind":"listed","path":"training/RL.py","file_url":"https://github.com/villinvic/Georges/blob/HEAD/training/RL.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"code_page":null,"census":null,"licence":"MIT","inline_ok":true,"inline_ok_link":true,"withheld_clause":null,"mcp_get_code":{"code_sha256":"cbb6758024239ec3"}},{"code_sha256":"bc2ac55256ed974b","code_sha256_prefix":"bc2ac55256ed974b","entry":"action_log_probs","repo":"urw7rs/spiralpp","repo_kind":"listed","path":"torchbeast/core/vtrace.py","file_url":"https://github.com/urw7rs/spiralpp/blob/HEAD/torchbeast/core/vtrace.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"code_page":null,"census":null,"licence":"Apache-2.0","inline_ok":true,"inline_ok_link":true,"withheld_clause":null,"mcp_get_code":{"code_sha256":"bc2ac55256ed974b"}},{"code_sha256":"cb89e31851cc2931","code_sha256_prefix":"cb89e31851cc2931","entry":"calc_loss_and_backprop","repo":"haje01/impala","repo_kind":"listed","path":"learner.py","file_url":"https://github.com/haje01/impala/blob/HEAD/learner.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"code_page":null,"census":null,"licence":"MIT","inline_ok":true,"inline_ok_link":true,"withheld_clause":null,"mcp_get_code":{"code_sha256":"cb89e31851cc2931"}},{"code_sha256":"9f5db323eec0eeba","code_sha256_prefix":"9f5db323eec0eeba","entry":"corr_matrix","repo":"villinvic/Georges","repo_kind":"listed","path":"training/RL.py","file_url":"https://github.com/villinvic/Georges/blob/HEAD/training/RL.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"code_page":null,"census":null,"licence":"MIT","inline_ok":true,"inline_ok_link":true,"withheld_clause":null,"mcp_get_code":{"code_sha256":"9f5db323eec0eeba"}},{"code_sha256":"86f7ee994e64dc88","code_sha256_prefix":"86f7ee994e64dc88","entry":"from_importance_weights","repo":"google-research/valan","repo_kind":"listed","path":"framework/vtrace.py","file_url":"https://github.com/google-research/valan/blob/HEAD/framework/vtrace.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"code_page":null,"census":null,"licence":"Apache-2.0","inline_ok":true,"inline_ok_link":true,"withheld_clause":null,"mcp_get_code":{"code_sha256":"86f7ee994e64dc88"}},{"code_sha256":"e11ee068514828e6","code_sha256_prefix":"e11ee068514828e6","entry":"from_importance_weights","repo":"google-deepmind/scalable_agent","repo_kind":"listed","path":"vtrace.py","file_url":"https://github.com/google-deepmind/scalable_agent/blob/HEAD/vtrace.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"code_page":null,"census":null,"licence":"Apache-2.0","inline_ok":true,"inline_ok_link":true,"withheld_clause":null,"mcp_get_code":{"code_sha256":"e11ee068514828e6"}},{"code_sha256":"c0ca8087e51d7e1d","code_sha256_prefix":"c0ca8087e51d7e1d","entry":"from_logits","repo":"google-research/valan","repo_kind":"listed","path":"framework/vtrace.py","file_url":"https://github.com/google-research/valan/blob/HEAD/framework/vtrace.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"code_page":null,"census":null,"licence":"Apache-2.0","inline_ok":true,"inline_ok_link":true,"withheld_clause":null,"mcp_get_code":{"code_sha256":"c0ca8087e51d7e1d"}},{"code_sha256":"e26d17c678348c08","code_sha256_prefix":"e26d17c678348c08","entry":"from_logits","repo":"urw7rs/spiralpp","repo_kind":"listed","path":"torchbeast/core/vtrace.py","file_url":"https://github.com/urw7rs/spiralpp/blob/HEAD/torchbeast/core/vtrace.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"code_page":null,"census":null,"licence":"Apache-2.0","inline_ok":true,"inline_ok_link":true,"withheld_clause":null,"mcp_get_code":{"code_sha256":"e26d17c678348c08"}},{"code_sha256":"2b5d90526b4ad312","code_sha256_prefix":"2b5d90526b4ad312","entry":"from_logits","repo":"google-deepmind/scalable_agent","repo_kind":"listed","path":"vtrace.py","file_url":"https://github.com/google-deepmind/scalable_agent/blob/HEAD/vtrace.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"code_page":null,"census":null,"licence":"Apache-2.0","inline_ok":true,"inline_ok_link":true,"withheld_clause":null,"mcp_get_code":{"code_sha256":"2b5d90526b4ad312"}},{"code_sha256":"b1527fc2ce13e346","code_sha256_prefix":"b1527fc2ce13e346","entry":"get_vtrace_and_advantages","repo":"seolhokim/SimpleDistributedRL","repo_kind":"listed","path":"distributed_reinforcement_learning/algorithms/impala.py","file_url":"https://github.com/seolhokim/SimpleDistributedRL/blob/HEAD/distributed_reinforcement_learning/algorithms/impala.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"code_page":null,"census":null,"licence":"MIT","inline_ok":true,"inline_ok_link":true,"withheld_clause":null,"mcp_get_code":{"code_sha256":"b1527fc2ce13e346"}},{"code_sha256":"a22618d583e622fe","code_sha256_prefix":"a22618d583e622fe","entry":"layer_crossover","repo":"villinvic/Georges","repo_kind":"listed","path":"training/RL.py","file_url":"https://github.com/villinvic/Georges/blob/HEAD/training/RL.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"code_page":null,"census":null,"licence":"MIT","inline_ok":true,"inline_ok_link":true,"withheld_clause":null,"mcp_get_code":{"code_sha256":"a22618d583e622fe"}},{"code_sha256":"e1569fbaca09c124","code_sha256_prefix":"e1569fbaca09c124","entry":"nn_crossover","repo":"villinvic/Georges","repo_kind":"listed","path":"training/RL.py","file_url":"https://github.com/villinvic/Georges/blob/HEAD/training/RL.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"code_page":null,"census":null,"licence":"MIT","inline_ok":true,"inline_ok_link":true,"withheld_clause":null,"mcp_get_code":{"code_sha256":"e1569fbaca09c124"}},{"code_sha256":"01b62761de35ed90","code_sha256_prefix":"01b62761de35ed90","entry":"train","repo":"seolhokim/SimpleDistributedRL","repo_kind":"listed","path":"distributed_reinforcement_learning/algorithms/impala.py","file_url":"https://github.com/seolhokim/SimpleDistributedRL/blob/HEAD/distributed_reinforcement_learning/algorithms/impala.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"code_page":"/code/train","census":null,"licence":"MIT","inline_ok":true,"inline_ok_link":true,"withheld_clause":null,"mcp_get_code":{"code_sha256":"01b62761de35ed90"}}]},"code_links_note":null,"arxiv_metadata":null,"syntology_extracted_results":null,"record_sha256":"17dce2c5cdc64a92f3c40f41d7b59b8a18382c9f3fabdfae8183807931beb9a3","record_changed_at":"2026-09-28","record_changed_at_basis":"first_hashed"}