{"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":"/dataset/openai-gym","name":"OpenAI Gym","full_name":"OpenAI Gym","description_markdown":"**OpenAI Gym** is a toolkit for developing and comparing reinforcement learning algorithms. It includes environment such as Algorithmic, Atari, Box2D, Classic Control, MuJoCo, Robotics, and Toy Text.\r\n\r\nSource: [https://github.com/openai/gym](https://github.com/openai/gym)\r\nImage Source: [https://medium.com/@tuzzer/cart-pole-balancing-with-q-learning-b54c6068d947](https://medium.com/@tuzzer/cart-pole-balancing-with-q-learning-b54c6068d947)","description_withheld":null,"homepage":"https://gym.openai.com/","introduced_date":"2016-01-01","introduced_date_note":null,"introduced_by":{"paper":"/paper/openai-gym","title":"OpenAI Gym","first_author":"Greg Brockman","url":null},"license":{"name":"MIT","url":"https://github.com/openai/gym/blob/master/LICENSE.md"},"modalities":[{"name":"Environment","url":"/datasets/modality/environment"}],"tasks":[{"name":"Continuous Control","url":"/task/continuous-control","datasets_with_task":"/datasets/task/continuous-control"},{"name":"OpenAI Gym","url":"/task/openai-gym","datasets_with_task":"/datasets/task/openai-gym"}],"languages":[{"name":"Azerbaijani","url":"/datasets/language/azerbaijani"}],"variants":["OpenAI Gym","Cart Pole (OpenAI Gym)","Lunar Lander (OpenAI Gym)","Pendulum-v1"],"data_loaders":[{"repo":"https://github.com/openai/gym","url":"https://github.com/openai/gym/blob/master/docs/environments.md","frameworks":["tf","pytorch","jax"]}],"num_papers_in_archive":1305,"source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28"},"benchmarks":[{"leaderboard":"/sota/continuous-control-on-lunar-lander-openai-gym","task":"Continuous Control","dataset_variant":"Lunar Lander (OpenAI Gym)","rows":5,"metrics":["Score"],"first_row_in_archive_order":{"model":"SAC","paper":"/paper/soft-actor-critic-off-policy-maximum-entropy","metrics":{"Score":"284.59±0.97"},"code_links":[{"title":"ray-project/ray","url":"https://github.com/ray-project/ray/tree/master/rllib"},{"title":"DLR-RM/stable-baselines3","url":"https://github.com/DLR-RM/stable-baselines3"},{"title":"hill-a/stable-baselines","url":"https://github.com/hill-a/stable-baselines"},{"title":"facebookresearch/ReAgent","url":"https://github.com/facebookresearch/ReAgent"},{"title":"opendilab/DI-engine","url":"https://github.com/opendilab/DI-engine/blob/main/ding/policy/sac.py"},{"title":"pytorch/rl","url":"https://github.com/pytorch/rl/tree/main/examples/sac"},{"title":"facebookresearch/rl","url":"https://github.com/facebookresearch/rl/blob/main/examples/sac/sac.py"},{"title":"quantumiracle/Popular-RL-Algorithms","url":"https://github.com/quantumiracle/Popular-RL-Algorithms"},{"title":"haarnoja/sac","url":"https://github.com/haarnoja/sac"},{"title":"MrSyee/pg-is-all-you-need","url":"https://github.com/MrSyee/pg-is-all-you-need"},{"title":"Rafael1s/Deep-Reinforcement-Learning-Udacity","url":"https://github.com/Rafael1s/Deep-Reinforcement-Learning-Udacity"},{"title":"pranz24/pytorch-soft-actor-critic","url":"https://github.com/pranz24/pytorch-soft-actor-critic"},{"title":"toni-sm/skrl","url":"https://github.com/toni-sm/skrl"},{"title":"ikostrikov/jax-rl","url":"https://github.com/ikostrikov/jax-rl"},{"title":"tensorlayer/RLzoo","url":"https://github.com/tensorlayer/RLzoo"},{"title":"marload/DeepRL-TensorFlow2","url":"https://github.com/marload/DeepRL-TensorFlow2"},{"title":"trackmania-rl/tmrl","url":"https://github.com/trackmania-rl/tmrl"},{"title":"Kaixhin/imitation-learning","url":"https://github.com/Kaixhin/imitation-learning"},{"title":"araffin/sbx","url":"https://github.com/araffin/sbx"},{"title":"andrejorsula/drl_grasping","url":"https://github.com/andrejorsula/drl_grasping"},{"title":"BY571/Soft-Actor-Critic-and-Extensions","url":"https://github.com/BY571/Soft-Actor-Critic-and-Extensions"},{"title":"ShawK91/Evolutionary-Reinforcement-Learning","url":"https://github.com/ShawK91/Evolutionary-Reinforcement-Learning"},{"title":"ShawK91/erl_paper_nips18","url":"https://github.com/ShawK91/erl_paper_nips18"},{"title":"ku2482/gail-airl-ppo.pytorch","url":"https://github.com/ku2482/gail-airl-ppo.pytorch"},{"title":"learn-to-race/l2r","url":"https://github.com/learn-to-race/l2r"},{"title":"dasgringuen/assetto_corsa_gym","url":"https://github.com/dasgringuen/assetto_corsa_gym"},{"title":"polixir/NeoRL","url":"https://github.com/polixir/NeoRL"},{"title":"toshikwa/soft-actor-critic.pytorch","url":"https://github.com/toshikwa/soft-actor-critic.pytorch"},{"title":"ku2482/soft-actor-critic.pytorch","url":"https://github.com/ku2482/soft-actor-critic.pytorch"},{"title":"ku2482/rljax","url":"https://github.com/ku2482/rljax"},{"title":"jakegrigsby/deep_control","url":"https://github.com/jakegrigsby/deep_control/blob/master/deep_control/sac.py"},{"title":"ac-93/soft-actor-critic","url":"https://github.com/ac-93/soft-actor-critic"},{"title":"RLAgent/state-marginal-matching","url":"https://github.com/RLAgent/state-marginal-matching"},{"title":"dfki-ric-underactuated-lab/torque_limited_simple_pendulum","url":"https://github.com/dfki-ric-underactuated-lab/torque_limited_simple_pendulum"},{"title":"FOCAL-ICLR/FOCAL-ICLR","url":"https://github.com/FOCAL-ICLR/FOCAL-ICLR"},{"title":"lanqingli1993/focal-iclr","url":"https://github.com/lanqingli1993/focal-iclr"},{"title":"toshikwa/discor.pytorch","url":"https://github.com/toshikwa/discor.pytorch"},{"title":"ku2482/discor.pytorch","url":"https://github.com/ku2482/discor.pytorch"},{"title":"tilkb/thermoai","url":"https://github.com/tilkb/thermoai"},{"title":"kdally/fault-tolerant-flight-control-drl","url":"https://github.com/kdally/fault-tolerant-flight-control-drl"},{"title":"kairproject/kair_algorithms_draft","url":"https://github.com/kairproject/kair_algorithms_draft"},{"title":"fdcl-gwu/gym-rotor","url":"https://github.com/fdcl-gwu/gym-rotor"},{"title":"roythuly/obac","url":"https://github.com/roythuly/obac"},{"title":"kushagra06/SAC","url":"https://github.com/kushagra06/SAC"},{"title":"yining043/SAC-discrete","url":"https://github.com/yining043/SAC-discrete"},{"title":"MatthieuSarkis/Portfolio-Optimization-and-Goal-Based-Investment-with-Reinforcement-Learning","url":"https://github.com/MatthieuSarkis/Portfolio-Optimization-and-Goal-Based-Investment-with-Reinforcement-Learning"},{"title":"AutumnWu/Streamlined-Off-Policy-Learning","url":"https://github.com/AutumnWu/Streamlined-Off-Policy-Learning"},{"title":"core-robotics-lab/icct","url":"https://github.com/core-robotics-lab/icct"},{"title":"xiuyu0000/new_papers_codes","url":"https://github.com/xiuyu0000/new_papers_codes/tree/main/sac"},{"title":"ku2482/rltorch","url":"https://github.com/ku2482/rltorch"},{"title":"baturaysaglam/la3p","url":"https://github.com/baturaysaglam/la3p"},{"title":"seungju-k1m/sac-td3-td7","url":"https://github.com/seungju-k1m/sac-td3-td7"},{"title":"X3N4/car_racer","url":"https://github.com/X3N4/car_racer"},{"title":"timoklein/car_racer","url":"https://github.com/timoklein/car_racer"},{"title":"moreanp/csro","url":"https://github.com/moreanp/csro"},{"title":"ajaysub110/rl-pytorch","url":"https://github.com/ajaysub110/rl-pytorch"},{"title":"watchernyu/spinningup-drl-prototyping","url":"https://github.com/watchernyu/spinningup-drl-prototyping"},{"title":"tliu1997/rnac","url":"https://github.com/tliu1997/rnac"},{"title":"thomashirtz/pytorch-soft-actor-critic","url":"https://github.com/thomashirtz/pytorch-soft-actor-critic"},{"title":"thomashirtz/soft-actor-critic","url":"https://github.com/thomashirtz/soft-actor-critic"},{"title":"ccolas/rl_stats","url":"https://github.com/ccolas/rl_stats"},{"title":"nagisazj/idaq_public","url":"https://github.com/nagisazj/idaq_public"},{"title":"Ipsedo/EvoMotion","url":"https://github.com/Ipsedo/EvoMotion"},{"title":"lucadellalib/sac-beta","url":"https://github.com/lucadellalib/sac-beta"},{"title":"h-aboutalebi/SparceReward","url":"https://github.com/h-aboutalebi/SparceReward"},{"title":"garyzyr001/rethinking-airl","url":"https://github.com/garyzyr001/rethinking-airl"},{"title":"flowersteam/rl_stats","url":"https://github.com/flowersteam/rl_stats"},{"title":"gijskoning/ReproducingCURL","url":"https://github.com/gijskoning/ReproducingCURL"},{"title":"yimingpeng/sac-master","url":"https://github.com/yimingpeng/sac-master"},{"title":"MarsEleven/car_racer_RL","url":"https://github.com/MarsEleven/car_racer_RL"},{"title":"yhisaki/average-reward-drl","url":"https://github.com/yhisaki/average-reward-drl"},{"title":"AmmarFayad/Behavioral-Actor-Critic","url":"https://github.com/AmmarFayad/Behavioral-Actor-Critic"},{"title":"autumnwu/aggressive-q-learning-with-ensembles","url":"https://github.com/autumnwu/aggressive-q-learning-with-ensembles"},{"title":"tarod13/SAC","url":"https://github.com/tarod13/SAC"},{"title":"Steinheilig/Imbiss","url":"https://github.com/Steinheilig/Imbiss"},{"title":"tmjeong1103/RL_with_RAY","url":"https://github.com/tmjeong1103/RL_with_RAY"},{"title":"QuentinVacher-rl/SoftActorCritic-in-Cpp-using-LibTorch","url":"https://github.com/QuentinVacher-rl/SoftActorCritic-in-Cpp-using-LibTorch"},{"title":"SaminYeasar/off_policy_ac","url":"https://github.com/SaminYeasar/off_policy_ac"},{"title":"lollcat/Soft-Actor-Critic","url":"https://github.com/lollcat/Soft-Actor-Critic"},{"title":"donamin/llc","url":"https://github.com/donamin/llc"},{"title":"susan-amin/SparseBaseline1","url":"https://github.com/susan-amin/SparseBaseline1"},{"title":"hyunin-lee/ForecasterSAC","url":"https://github.com/hyunin-lee/ForecasterSAC"},{"title":"cindycia/Atari-SAC-Discrete","url":"https://github.com/cindycia/Atari-SAC-Discrete"},{"title":"mxblr/DeepRLHockey","url":"https://github.com/mxblr/DeepRLHockey"},{"title":"rk1998/robot-sac","url":"https://github.com/rk1998/robot-sac"},{"title":"sunfex/weighted-sac","url":"https://github.com/sunfex/weighted-sac"}]},"note":"rows are the archive's own order at snapshot; nothing here re-ranks them"},{"leaderboard":"/sota/openai-gym-on-pendulum-v1","task":"OpenAI Gym","dataset_variant":"Pendulum-v1","rows":2,"metrics":["Mean Reward","Average Decisions","Action Repetition"],"first_row_in_archive_order":{"model":"TLA with Hierarchical Reward Functions","paper":"/paper/creating-hierarchical-dispositions-of-needs","metrics":{"Action Repetition":".8073","Average Decisions":"38.6","Mean Reward":"-125.02"},"code_links":[{"title":"TofaraMoyo/Heirachical-Reward-Functions","url":"https://github.com/TofaraMoyo/Heirachical-Reward-Functions"}]},"note":"rows are the archive's own order at snapshot; nothing here re-ranks them"},{"leaderboard":"/sota/continuous-control-on-cart-pole-openai-gym","task":"Continuous Control","dataset_variant":"Cart Pole (OpenAI Gym)","rows":1,"metrics":["Score"],"first_row_in_archive_order":{"model":"MAC","paper":"/paper/mean-actor-critic","metrics":{"Score":"178.3"},"code_links":[{"title":"kavosh8/MAC","url":"https://github.com/kavosh8/MAC"},{"title":"camall3n/atari-MAC","url":"https://github.com/camall3n/atari-MAC"}]},"note":"rows are the archive's own order at snapshot; nothing here re-ranks them"}],"papers":{"order":"date (newest first), then slug","population":"every paper with a leaderboard row on this dataset's benchmarks (the benchmark-backed subset): the archive's own papers-using-this-dataset list was never published, so this is not that list; num_papers_in_archive is the archive's own count","page":1,"pages_in_order":1,"rows_per_page":100,"shown":7,"of":7,"counts":{"papers_with_a_benchmark_row":7,"with_a_code_link":7,"where_syntology_ran_a_sample":4,"not_listed_spam_title":0,"listed":7,"listed_where_code_ran":4,"where_syntology_ran_a_sample_split":{"with_a_run_with_no_instrument_failure":4,"every_run_a_failure_of_syntologys_instrument":0,"listed_with_a_run_with_no_instrument_failure":4,"listed_every_run_a_failure_of_syntologys_instrument":0,"filter":{"states":["a run with no instrument failure","any run, instrument failures included"],"default":"a run with no instrument failure","note":"on the 'only where code ran' pages the default hides, in the browser, the rows where every run was a failure of Syntology's instrument; the second state shows them again. Rows are hidden, never re-ordered; these twins list every row"}},"definition":"distinct papers with at least one leaderboard row on this dataset's benchmarks; 'where Syntology ran a sample' counts papers with at least one harvested sample that ran, which is not a correctness claim"},"items":[{"paper":"/paper/creating-hierarchical-dispositions-of-needs","slug":"creating-hierarchical-dispositions-of-needs","title":"Creating Hierarchical Dispositions of Needs in an Agent","date":"2024-11-23","arxiv_id":"2412.00044","rows_on_this_dataset":1,"code_links":1,"syntology":null},{"paper":"/paper/temporally-layered-architecture-for-efficient","slug":"temporally-layered-architecture-for-efficient","title":"Optimizing Attention and Cognitive Control Costs Using Temporally-Layered Architectures","date":"2023-05-30","arxiv_id":"2305.18701","rows_on_this_dataset":1,"code_links":1,"syntology":null},{"paper":"/paper/addressing-function-approximation-error-in","slug":"addressing-function-approximation-error-in","title":"Addressing Function Approximation Error in Actor-Critic Methods","date":"2018-02-26","arxiv_id":"1802.09477","rows_on_this_dataset":1,"code_links":67,"syntology":{"read_at":"2026-10-05T00:36:11+00:00","samples_harvested":36,"samples_ran":26,"samples_constructed":0,"samples_ran_checked":20,"samples_ran_instrument_failed":6,"samples_unverified":10,"pointer_only_for_licence":21,"official":{"repos":["sfujim/TD3"],"state":"community repositories only","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["listed"]},"claim":"Per-sample execution on synthesized fixtures; not a correctness claim.","sample_list":"/paper/addressing-function-approximation-error-in#ran","syntology_url":"https://syntology.ai/paper/1802.09477","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1802.09477"}}}},{"paper":"/paper/soft-actor-critic-off-policy-maximum-entropy","slug":"soft-actor-critic-off-policy-maximum-entropy","title":"Soft Actor-Critic: Off-Policy Maximum Entropy Deep Reinforcement Learning with a Stochastic Actor","date":"2018-01-04","arxiv_id":"1801.01290","rows_on_this_dataset":1,"code_links":86,"syntology":{"read_at":"2026-10-05T00:36:11+00:00","samples_harvested":148,"samples_ran":91,"samples_constructed":61,"samples_ran_checked":73,"samples_ran_instrument_failed":18,"samples_unverified":57,"pointer_only_for_licence":66,"official":{"repos":["haarnoja/sac"],"state":"community repositories only","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["listed"]},"claim":"Per-sample execution on synthesized fixtures; not a correctness claim.","sample_list":"/paper/soft-actor-critic-off-policy-maximum-entropy#ran","syntology_url":"https://syntology.ai/paper/1801.01290","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1801.01290"}}}},{"paper":"/paper/mean-actor-critic","slug":"mean-actor-critic","title":"Mean Actor Critic","date":"2017-09-01","arxiv_id":"1709.00503","rows_on_this_dataset":2,"code_links":2,"syntology":null},{"paper":"/paper/proximal-policy-optimization-algorithms","slug":"proximal-policy-optimization-algorithms","title":"Proximal Policy Optimization Algorithms","date":"2017-07-20","arxiv_id":"1707.06347","rows_on_this_dataset":1,"code_links":188,"syntology":{"read_at":"2026-10-05T00:36:11+00:00","samples_harvested":176,"samples_ran":99,"samples_constructed":53,"samples_ran_checked":71,"samples_ran_instrument_failed":28,"samples_unverified":77,"pointer_only_for_licence":94,"official":null,"claim":"Per-sample execution on synthesized fixtures; not a correctness claim.","sample_list":"/paper/proximal-policy-optimization-algorithms#ran","syntology_url":"https://syntology.ai/paper/1707.06347","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1707.06347"}}}},{"paper":"/paper/continuous-control-with-deep-reinforcement","slug":"continuous-control-with-deep-reinforcement","title":"Continuous control with deep reinforcement learning","date":"2015-09-09","arxiv_id":"1509.02971","rows_on_this_dataset":1,"code_links":161,"syntology":{"read_at":"2026-10-05T00:36:11+00:00","samples_harvested":306,"samples_ran":163,"samples_constructed":126,"samples_ran_checked":152,"samples_ran_instrument_failed":11,"samples_unverified":143,"pointer_only_for_licence":163,"official":null,"claim":"Per-sample execution on synthesized fixtures; not a correctness claim.","sample_list":"/paper/continuous-control-with-deep-reinforcement#ran","syntology_url":"https://syntology.ai/paper/1509.02971","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1509.02971"}}}}],"full_list":"papers_with_a_benchmark_row: every listed paper, in this order"},"papers_with_a_benchmark_row":[{"paper":"/paper/creating-hierarchical-dispositions-of-needs","slug":"creating-hierarchical-dispositions-of-needs","title":"Creating Hierarchical Dispositions of Needs in an Agent","date":"2024-11-23","arxiv_id":"2412.00044","rows_on_this_dataset":1,"code_links":1,"syntology":null},{"paper":"/paper/temporally-layered-architecture-for-efficient","slug":"temporally-layered-architecture-for-efficient","title":"Optimizing Attention and Cognitive Control Costs Using Temporally-Layered Architectures","date":"2023-05-30","arxiv_id":"2305.18701","rows_on_this_dataset":1,"code_links":1,"syntology":null},{"paper":"/paper/addressing-function-approximation-error-in","slug":"addressing-function-approximation-error-in","title":"Addressing Function Approximation Error in Actor-Critic Methods","date":"2018-02-26","arxiv_id":"1802.09477","rows_on_this_dataset":1,"code_links":67,"syntology":{"read_at":"2026-10-05T00:36:11+00:00","samples_harvested":36,"samples_ran":26,"samples_constructed":0,"samples_ran_checked":20,"samples_ran_instrument_failed":6,"samples_unverified":10,"pointer_only_for_licence":21,"official":{"repos":["sfujim/TD3"],"state":"community repositories only","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["listed"]},"claim":"Per-sample execution on synthesized fixtures; not a correctness claim.","sample_list":"/paper/addressing-function-approximation-error-in#ran","syntology_url":"https://syntology.ai/paper/1802.09477","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1802.09477"}}}},{"paper":"/paper/soft-actor-critic-off-policy-maximum-entropy","slug":"soft-actor-critic-off-policy-maximum-entropy","title":"Soft Actor-Critic: Off-Policy Maximum Entropy Deep Reinforcement Learning with a Stochastic Actor","date":"2018-01-04","arxiv_id":"1801.01290","rows_on_this_dataset":1,"code_links":86,"syntology":{"read_at":"2026-10-05T00:36:11+00:00","samples_harvested":148,"samples_ran":91,"samples_constructed":61,"samples_ran_checked":73,"samples_ran_instrument_failed":18,"samples_unverified":57,"pointer_only_for_licence":66,"official":{"repos":["haarnoja/sac"],"state":"community repositories only","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["listed"]},"claim":"Per-sample execution on synthesized fixtures; not a correctness claim.","sample_list":"/paper/soft-actor-critic-off-policy-maximum-entropy#ran","syntology_url":"https://syntology.ai/paper/1801.01290","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1801.01290"}}}},{"paper":"/paper/mean-actor-critic","slug":"mean-actor-critic","title":"Mean Actor Critic","date":"2017-09-01","arxiv_id":"1709.00503","rows_on_this_dataset":2,"code_links":2,"syntology":null},{"paper":"/paper/proximal-policy-optimization-algorithms","slug":"proximal-policy-optimization-algorithms","title":"Proximal Policy Optimization Algorithms","date":"2017-07-20","arxiv_id":"1707.06347","rows_on_this_dataset":1,"code_links":188,"syntology":{"read_at":"2026-10-05T00:36:11+00:00","samples_harvested":176,"samples_ran":99,"samples_constructed":53,"samples_ran_checked":71,"samples_ran_instrument_failed":28,"samples_unverified":77,"pointer_only_for_licence":94,"official":null,"claim":"Per-sample execution on synthesized fixtures; not a correctness claim.","sample_list":"/paper/proximal-policy-optimization-algorithms#ran","syntology_url":"https://syntology.ai/paper/1707.06347","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1707.06347"}}}},{"paper":"/paper/continuous-control-with-deep-reinforcement","slug":"continuous-control-with-deep-reinforcement","title":"Continuous control with deep reinforcement learning","date":"2015-09-09","arxiv_id":"1509.02971","rows_on_this_dataset":1,"code_links":161,"syntology":{"read_at":"2026-10-05T00:36:11+00:00","samples_harvested":306,"samples_ran":163,"samples_constructed":126,"samples_ran_checked":152,"samples_ran_instrument_failed":11,"samples_unverified":143,"pointer_only_for_licence":163,"official":null,"claim":"Per-sample execution on synthesized fixtures; not a correctness claim.","sample_list":"/paper/continuous-control-with-deep-reinforcement#ran","syntology_url":"https://syntology.ai/paper/1509.02971","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1509.02971"}}}}],"papers_where_code_ran":4,"papers_where_code_ran_first_page":"/dataset/openai-gym/papers/ran/1","papers_where_code_ran_caption":"We ran code from the paper's repository; we did not run it on this dataset or check it against this dataset's benchmarks.","pages":[{"order":"ran","page":1,"of":1,"url":"/dataset/openai-gym/papers/ran/1","json":"/dataset/openai-gym/papers/ran/1.json","rows":4}],"row_route":"each paper's syntology object carries sample_list (this site's paper page, #ran), syntology_url (syntology.ai's page for the paper, only when that route probed live) and mcp (the agent call that lists the paper's harvested samples; not a verdict on the paper)","developers":"https://syntology.ai/developers","syntology_totals":{"read_at":"2026-10-05T00:36:11+00:00","papers_with_samples":4,"samples_harvested":666,"samples_ran":379,"samples_constructed":240,"samples_ran_checked":316,"samples_ran_instrument_failed":63,"samples_unverified":287,"pointer_only_for_licence":344,"papers_with_no_sample_that_ran":0,"papers_with_a_sample_that_ran":4,"papers_with_a_run_with_no_instrument_failure":4,"papers_where_every_run_was_an_instrument_failure":0,"note":"the per-paper counts of every listed paper (all pages), summed; not a rate"},"key_notes":{"samples_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'","samples_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)"},"since_archive_judged":{"papers":0,"papers_placed":0,"judged_by":{"model":"a model","models_as_recorded":[],"from":"lb_rows_run_verified.jsonl: each record's `model` field (the extractor's call that wrote decisions[])"},"note":"a model's judgement from the paper's own tables that they report on this leaderboard, not a result: no value from a paper that was not placed is printed or carried here; papers counts each paper once over these leaderboards","backfill":"8,886 of 18,637 newer papers checked so far (733 more had nothing to place; 41 could not be read)","backfill_complete":false,"leaderboards":[]},"papers_note":"The archive never published its papers-using-dataset list; these are papers with a leaderboard row on this dataset's benchmarks.","record_sha256":"4dac482fddb031ffe0d056ee189675fa66d8781390545b01624534492060f3a1","record_changed_at":"2026-10-05","record_changed_at_basis":"changed"}