{"about":{"site":"https://codewithpapers.app","non_affiliation":"Code with Papers and Syntology are not affiliated with, endorsed by, or sponsored by Papers with Code, Meta, or the pwc-archive mirror.","licence":"CC BY-SA 4.0","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","attribution":"https://codewithpapers.app/attribution","modified":"archive material modified by Syntology; see the attribution page"},"url":"/paper/addressing-function-approximation-error-in","title":"Addressing Function Approximation Error in Actor-Critic Methods","arxiv_id":"1802.09477","date":"2018-02-26","proceeding":"ICML 2018 7","authors":["Scott Fujimoto","Herke van Hoof","David Meger"],"abstract":"In value-based reinforcement learning methods such as deep Q-learning,\nfunction approximation errors are known to lead to overestimated value\nestimates and suboptimal policies. We show that this problem persists in an\nactor-critic setting and propose novel mechanisms to minimize its effects on\nboth the actor and the critic. Our algorithm builds on Double Q-learning, by\ntaking the minimum value between a pair of critics to limit overestimation. We\ndraw the connection between target networks and overestimation bias, and\nsuggest delaying policy updates to reduce per-update error and further improve\nperformance. We evaluate our method on the suite of OpenAI gym tasks,\noutperforming the state of the art in every environment tested.","url_abs":"http://arxiv.org/abs/1802.09477v3","url_pdf":"http://arxiv.org/pdf/1802.09477v3.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":"addressing-function-approximation-error-in","repo_url":"https://github.com/sfujim/TD3","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":null},{"paper_slug":"addressing-function-approximation-error-in","repo_url":"https://github.com/CharlotteMorrison/Baxter-Research","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":null},{"paper_slug":"addressing-function-approximation-error-in","repo_url":"https://github.com/CharlotteMorrison/Baxter-VREP","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":null},{"paper_slug":"addressing-function-approximation-error-in","repo_url":"https://github.com/CharlotteMorrison/Baxter-VREP-Version-2","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":null},{"paper_slug":"addressing-function-approximation-error-in","repo_url":"https://github.com/DanielTakeshi/DCUR","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"MIT"}},{"paper_slug":"addressing-function-approximation-error-in","repo_url":"https://github.com/GauravPatel89/Car-Navigation-Simulation-using-TD3","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok"}},{"paper_slug":"addressing-function-approximation-error-in","repo_url":"https://github.com/GhadaSokar/Dynamic-Sparse-Training-for-Deep-Reinforcement-Learning","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"MIT"}},{"paper_slug":"addressing-function-approximation-error-in","repo_url":"https://github.com/JohannesAck/MATD3implementation","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"tf","reach":{"status":"ok"}},{"paper_slug":"addressing-function-approximation-error-in","repo_url":"https://github.com/MrSyee/pg-is-all-you-need","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"none","reach":{"status":"ok","spdx":"MIT"}},{"paper_slug":"addressing-function-approximation-error-in","repo_url":"https://github.com/Rafael1s/Deep-Reinforcement-Learning-Udacity","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":null},{"paper_slug":"addressing-function-approximation-error-in","repo_url":"https://github.com/SaminYeasar/off_policy_ac","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":null},{"paper_slug":"addressing-function-approximation-error-in","repo_url":"https://github.com/SeungeonBaek/continuous-agents-test","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"tf","reach":null},{"paper_slug":"addressing-function-approximation-error-in","repo_url":"https://github.com/VasaKiDD/TD3-deep-rl-research","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":null},{"paper_slug":"addressing-function-approximation-error-in","repo_url":"https://github.com/Zartris/TD3_continuous_control","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok"}},{"paper_slug":"addressing-function-approximation-error-in","repo_url":"https://github.com/adaptive-intelligent-robotics/pga-map-elites","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok"}},{"paper_slug":"addressing-function-approximation-error-in","repo_url":"https://github.com/andreidi/AC_DDPG_walker","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"tf","reach":null},{"paper_slug":"addressing-function-approximation-error-in","repo_url":"https://github.com/andrejorsula/drl_grasping","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"BSD-3-Clause"}},{"paper_slug":"addressing-function-approximation-error-in","repo_url":"https://github.com/araffin/sbx","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"jax","reach":null},{"paper_slug":"addressing-function-approximation-error-in","repo_url":"https://github.com/arrival-ltd/catalyst-rl-tutorial","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"MIT"}},{"paper_slug":"addressing-function-approximation-error-in","repo_url":"https://github.com/ashaaher/Reinforcement-Learning-Project","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok"}},{"paper_slug":"addressing-function-approximation-error-in","repo_url":"https://github.com/b06b01073/Twin-Delayed-DDPG","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok"}},{"paper_slug":"addressing-function-approximation-error-in","repo_url":"https://github.com/baturaysaglam/ac-off-poc","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":null},{"paper_slug":"addressing-function-approximation-error-in","repo_url":"https://github.com/baturaysaglam/dase","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"gone","observed_at":"2026-09-17","how":"tree_404+repo_404"}},{"paper_slug":"addressing-function-approximation-error-in","repo_url":"https://github.com/baturaysaglam/la3p","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":null},{"paper_slug":"addressing-function-approximation-error-in","repo_url":"https://github.com/ccolas/rl_stats","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"none","reach":null},{"paper_slug":"addressing-function-approximation-error-in","repo_url":"https://github.com/chainer/chainerrl","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":null},{"paper_slug":"addressing-function-approximation-error-in","repo_url":"https://github.com/claudeHifly/BipedalWalker-v3","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":null},{"paper_slug":"addressing-function-approximation-error-in","repo_url":"https://github.com/core-robotics-lab/icct","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"MIT"}},{"paper_slug":"addressing-function-approximation-error-in","repo_url":"https://github.com/coreylowman/rl_simply","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok"}},{"paper_slug":"addressing-function-approximation-error-in","repo_url":"https://github.com/crazyleg/TD3-reacher","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"MIT"}},{"paper_slug":"addressing-function-approximation-error-in","repo_url":"https://github.com/facebookresearch/ReAgent","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"unanswered"}},{"paper_slug":"addressing-function-approximation-error-in","repo_url":"https://github.com/fdcl-gwu/gym-rotor","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"MIT"}},{"paper_slug":"addressing-function-approximation-error-in","repo_url":"https://github.com/fiorenza2/OffCon3","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"unanswered"}},{"paper_slug":"addressing-function-approximation-error-in","repo_url":"https://github.com/flowersteam/rl_stats","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"none","reach":{"status":"ok"}},{"paper_slug":"addressing-function-approximation-error-in","repo_url":"https://github.com/georgesung/TD3","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok"}},{"paper_slug":"addressing-function-approximation-error-in","repo_url":"https://github.com/gwthomas/gtml","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"tf","reach":{"status":"ok"}},{"paper_slug":"addressing-function-approximation-error-in","repo_url":"https://github.com/intelligent-environments-lab/CityLearn","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"tf","reach":{"status":"unanswered"}},{"paper_slug":"addressing-function-approximation-error-in","repo_url":"https://github.com/jaem-seo/AI_tokamak_control","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"none","reach":{"status":"ok","spdx":"MIT"}},{"paper_slug":"addressing-function-approximation-error-in","repo_url":"https://github.com/jyqhahah/rl_maddpg_matd3","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":null},{"paper_slug":"addressing-function-approximation-error-in","repo_url":"https://github.com/kairproject/kair_algorithms_draft","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok"}},{"paper_slug":"addressing-function-approximation-error-in","repo_url":"https://github.com/markub3327/rl-agent","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"tf","reach":{"status":"ok","spdx":"MIT"}},{"paper_slug":"addressing-function-approximation-error-in","repo_url":"https://github.com/markub3327/rl-baselines","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"tf","reach":{"status":"ok","spdx":"MIT"}},{"paper_slug":"addressing-function-approximation-error-in","repo_url":"https://github.com/markub3327/rl-toolkit","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"tf","reach":{"status":"ok","spdx":"MIT"}},{"paper_slug":"addressing-function-approximation-error-in","repo_url":"https://github.com/marload/DeepRL-TensorFlow2","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"tf","reach":null},{"paper_slug":"addressing-function-approximation-error-in","repo_url":"https://github.com/mindspore-courses/Deep-Reinforcement-Learning-Algorithms-with-MindSpore","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"mindspore","reach":{"status":"ok"}},{"paper_slug":"addressing-function-approximation-error-in","repo_url":"https://github.com/nikhilbarhate99/TD3-PyTorch-BipedalWalker-v2","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"MIT"}},{"paper_slug":"addressing-function-approximation-error-in","repo_url":"https://github.com/ollenilsson19/MAP-Elites-GAPG","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"MIT"}},{"paper_slug":"addressing-function-approximation-error-in","repo_url":"https://github.com/ollenilsson19/PGA-MAP-Elites","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"MIT"}},{"paper_slug":"addressing-function-approximation-error-in","repo_url":"https://github.com/patrickhart/jaxdl","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"jax","reach":{"status":"ok","spdx":"MIT"}},{"paper_slug":"addressing-function-approximation-error-in","repo_url":"https://github.com/pkasala/ContinuesControl","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok"}},{"paper_slug":"addressing-function-approximation-error-in","repo_url":"https://github.com/quantumiracle/Popular-RL-Algorithms","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":null},{"paper_slug":"addressing-function-approximation-error-in","repo_url":"https://github.com/reiniscimurs/TD3_Separate_Action","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok"}},{"paper_slug":"addressing-function-approximation-error-in","repo_url":"https://github.com/robintyh1/icml2021-pengqlambda","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"tf","reach":{"status":"ok","spdx":"MIT"}},{"paper_slug":"addressing-function-approximation-error-in","repo_url":"https://github.com/rshnn/battleship","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"none","reach":{"status":"ok"}},{"paper_slug":"addressing-function-approximation-error-in","repo_url":"https://github.com/soumik12345/Twin-Delayed-DDPG","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok"}},{"paper_slug":"addressing-function-approximation-error-in","repo_url":"https://github.com/tensorlayer/RLzoo","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"tf","reach":null},{"paper_slug":"addressing-function-approximation-error-in","repo_url":"https://github.com/tomaszsmaruj25/Twin-Delayed-DDPG-Implementation","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"none","reach":{"status":"ok"}},{"paper_slug":"addressing-function-approximation-error-in","repo_url":"https://github.com/yifan12wu/td3-jax","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"jax","reach":{"status":"ok","spdx":"MIT"}},{"paper_slug":"addressing-function-approximation-error-in","repo_url":"https://github.com/yydsok/oparl","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"MIT"}},{"paper_slug":"addressing-function-approximation-error-in","repo_url":"https://github.com/BIT-aerial-robotics/AquaML/blob/2.1.11/AquaML/rlalgo/TD3Agent.py","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":0,"framework":"tf","reach":null},{"paper_slug":"addressing-function-approximation-error-in","repo_url":"https://github.com/DLR-RM/stable-baselines3","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":0,"framework":"pytorch","reach":null},{"paper_slug":"addressing-function-approximation-error-in","repo_url":"https://github.com/hill-a/stable-baselines","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":0,"framework":"tf","reach":null},{"paper_slug":"addressing-function-approximation-error-in","repo_url":"https://github.com/jakegrigsby/deep_control/blob/master/deep_control/td3.py","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":0,"framework":"pytorch","reach":null},{"paper_slug":"addressing-function-approximation-error-in","repo_url":"https://github.com/opendilab/DI-engine/blob/main/ding/policy/td3.py","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":0,"framework":"pytorch","reach":null},{"paper_slug":"addressing-function-approximation-error-in","repo_url":"https://github.com/pytorch/rl/tree/main/examples/td3","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":0,"framework":"jax","reach":null},{"paper_slug":"addressing-function-approximation-error-in","repo_url":"https://github.com/seungju-k1m/sac-td3-td7","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":0,"framework":"pytorch","reach":{"status":"ok"}},{"paper_slug":"addressing-function-approximation-error-in","repo_url":"https://github.com/toni-sm/skrl","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":0,"framework":"jax","reach":{"status":"ok","spdx":"MIT"}}],"tasks":[{"task_slug":"continuous-control","task_name":"Continuous Control"},{"task_slug":"openai-gym","task_name":"OpenAI Gym"},{"task_slug":"q-learning","task_name":"Q-Learning"},{"task_slug":"reinforcement-learning","task_name":"Reinforcement Learning"},{"task_slug":"reinforcement-learning-1","task_name":"Reinforcement Learning (RL)"},{"task_slug":"reinforcement-learning-2","task_name":"reinforcement-learning"}],"methods":[{"method_slug":"adam","method_name":"Adam"},{"method_slug":"clipped-double-q-learning","method_name":"Clipped Double Q-learning"},{"method_slug":"dense-connections","method_name":"Dense Connections"},{"method_slug":"double-q-learning","method_name":"Double Q-learning"},{"method_slug":"experience-replay","method_name":"Experience Replay"},{"method_slug":"relu","method_name":"ReLU"},{"method_slug":"td3","method_name":"TD3"},{"method_slug":"target-policy-smoothing","method_name":"Target Policy Smoothing"}],"datasets_introduced":[],"methods_introduced":[{"slug":"td3","name":"TD3","full_name":"Twin Delayed Deep Deterministic"},{"slug":"target-policy-smoothing","name":"Target Policy Smoothing","full_name":"Target Policy Smoothing"}],"results":[{"leaderboard":"/sota/continuous-control-on-lunar-lander-openai-gym","task":"Continuous Control","dataset":"Lunar Lander (OpenAI Gym)","model":"TD3","rank_in_archive_order":2,"of":5,"metrics":{"Score":"277.26±4.17"},"uses_additional_data":false},{"leaderboard":"/sota/openai-gym-on-ant-v4","task":"OpenAI Gym","dataset":"Ant-v4","model":"TD3","rank_in_archive_order":2,"of":5,"metrics":{"Average Return":"5942.55"},"uses_additional_data":false},{"leaderboard":"/sota/openai-gym-on-halfcheetah-v4","task":"OpenAI Gym","dataset":"HalfCheetah-v4","model":"TD3","rank_in_archive_order":3,"of":5,"metrics":{"Average Return":"12026.73"},"uses_additional_data":false},{"leaderboard":"/sota/openai-gym-on-hopper-v4","task":"OpenAI Gym","dataset":"Hopper-v4","model":"TD3","rank_in_archive_order":2,"of":5,"metrics":{"Average Return":"3319.98"},"uses_additional_data":false},{"leaderboard":"/sota/openai-gym-on-humanoid-v4","task":"OpenAI Gym","dataset":"Humanoid-v4","model":"TD3","rank_in_archive_order":4,"of":5,"metrics":{"Average Return":"198.44"},"uses_additional_data":false},{"leaderboard":"/sota/openai-gym-on-walker2d-v4","task":"OpenAI Gym","dataset":"Walker2d-v4","model":"TD3","rank_in_archive_order":5,"of":5,"metrics":{"Average Return":"2612.74"},"uses_additional_data":false}],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=1802.09477","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1802.09477"}},"developers":"https://syntology.ai/developers","read_at":"2026-09-24T18:15:14+00:00","read_at_is":"when the build read Syntology's graph, not when any sample ran","claim":"Per-sample execution status on synthesized fixtures; not a correctness claim about the paper. Samples come from repositories linked to the paper, official or community; repo_kind says which.","repos":[{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/sfujim/TD3","reach":null},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/hill-a/stable-baselines","reach":null},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/DLR-RM/stable-baselines3","reach":null},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/arrival-ltd/catalyst-rl-tutorial","reach":{"status":"ok","spdx":"MIT"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/baturaysaglam/la3p","reach":null},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/quantumiracle/Popular-RL-Algorithms","reach":null},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/CharlotteMorrison/Baxter-Research","reach":null},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/jyqhahah/rl_maddpg_matd3","reach":null},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/gwthomas/gtml","reach":{"status":"ok"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/SaminYeasar/off_policy_ac","reach":null},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/kairproject/kair_algorithms_draft","reach":{"status":"ok"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/opendilab/DI-engine/blob/main/ding/policy/td3.py","reach":null},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/toni-sm/skrl","reach":{"status":"ok","spdx":"MIT"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/markub3327/rl-agent","reach":{"status":"ok","spdx":"MIT"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/VasaKiDD/TD3-deep-rl-research","reach":null},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/MrSyee/pg-is-all-you-need","reach":{"status":"ok","spdx":"MIT"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/Rafael1s/Deep-Reinforcement-Learning-Udacity","reach":null},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/core-robotics-lab/icct","reach":{"status":"ok","spdx":"MIT"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/b06b01073/Twin-Delayed-DDPG","reach":{"status":"ok"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/flowersteam/rl_stats","reach":{"status":"ok"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/DanielTakeshi/DCUR","reach":{"status":"ok","spdx":"MIT"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/mindspore-courses/Deep-Reinforcement-Learning-Algorithms-with-MindSpore","reach":{"status":"ok"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/ollenilsson19/MAP-Elites-GAPG","reach":{"status":"ok","spdx":"MIT"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/ollenilsson19/PGA-MAP-Elites","reach":{"status":"ok","spdx":"MIT"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/chainer/chainerrl","reach":null}],"summary":{"ran":6,"ran_draft_wrong":1,"ran_honours":1,"ran_violates":1,"unverified":27},"by_repo_kind":{"listed":{"samples":36,"ran":9,"repositories":8}},"repo_kind_vocabulary":{"official":"The archive marks this repository official for the paper","named_in_paper":"The archive records that the paper mentions this repository; it is not marked official","listed":"In the archive's code links for this paper, not marked official and not recorded as mentioned in the paper","found_in_text":"Syntology found this repository in the paper's own text; whether it is the authors' implementation is not asserted","community":"Not in the archive's code links for this paper; a community repository Syntology harvested"},"n_pointer_only_for_licence":20,"samples":[{"code_sha256_prefix":"2103e65a90ce7a04","entry":"all_bools","repo":"robintyh1/icml2021-pengqlambda","repo_kind":"listed","path":"spinup/utils/run_utils.py","file_url":"https://github.com/robintyh1/icml2021-pengqlambda/blob/HEAD/spinup/utils/run_utils.py","link_basis":"harvester_set","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":false,"mcp_get_code":{"code_sha256":"2103e65a90ce7a04"}},{"code_sha256_prefix":"7e36f1c357c4618d","entry":"colorize","repo":"robintyh1/icml2021-pengqlambda","repo_kind":"listed","path":"spinup/utils/logx.py","file_url":"https://github.com/robintyh1/icml2021-pengqlambda/blob/HEAD/spinup/utils/logx.py","link_basis":"harvester_set","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":false,"mcp_get_code":{"code_sha256":"7e36f1c357c4618d"}},{"code_sha256_prefix":"fbc505a5dac82646","entry":"convert_json","repo":"robintyh1/icml2021-pengqlambda","repo_kind":"listed","path":"spinup/utils/serialization_utils.py","file_url":"https://github.com/robintyh1/icml2021-pengqlambda/blob/HEAD/spinup/utils/serialization_utils.py","link_basis":"harvester_set","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"OUTPUT_MISDECLARED","metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":false,"mcp_get_code":{"code_sha256":"fbc505a5dac82646"}},{"code_sha256_prefix":"b0a2d4b21b2d48e6","entry":"evaluate_policy","repo":"VasaKiDD/TD3-deep-rl-research","repo_kind":"listed","path":"train/main_faimemory.py","file_url":"https://github.com/VasaKiDD/TD3-deep-rl-research/blob/HEAD/train/main_faimemory.py","link_basis":"first_harvest_node","language":"python","status":"ran_honours","verification_level":1,"contract_check":"HONOURS","metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"b0a2d4b21b2d48e6"}},{"code_sha256_prefix":"62314e3b8ca6edfc","entry":"get_all_datasets","repo":"robintyh1/icml2021-pengqlambda","repo_kind":"listed","path":"spinup/utils/plot.py","file_url":"https://github.com/robintyh1/icml2021-pengqlambda/blob/HEAD/spinup/utils/plot.py","link_basis":"harvester_set","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":false,"mcp_get_code":{"code_sha256":"62314e3b8ca6edfc"}},{"code_sha256_prefix":"e642bb98eca55069","entry":"get_datasets","repo":"robintyh1/icml2021-pengqlambda","repo_kind":"listed","path":"spinup/utils/plot.py","file_url":"https://github.com/robintyh1/icml2021-pengqlambda/blob/HEAD/spinup/utils/plot.py","link_basis":"harvester_set","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":false,"mcp_get_code":{"code_sha256":"e642bb98eca55069"}},{"code_sha256_prefix":"9ca8b8e45f7fbebf","entry":"is_json_serializable","repo":"robintyh1/icml2021-pengqlambda","repo_kind":"listed","path":"spinup/utils/serialization_utils.py","file_url":"https://github.com/robintyh1/icml2021-pengqlambda/blob/HEAD/spinup/utils/serialization_utils.py","link_basis":"harvester_set","language":"python","status":"ran_violates","verification_level":1,"contract_check":"VIOLATES","metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":false,"mcp_get_code":{"code_sha256":"9ca8b8e45f7fbebf"}},{"code_sha256_prefix":"c17b6915065d3722","entry":"make_hashable","repo":"ollenilsson19/MAP-Elites-GAPG","repo_kind":"listed","path":"utils.py","file_url":"https://github.com/ollenilsson19/MAP-Elites-GAPG/blob/HEAD/utils.py","link_basis":"harvester_set","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"c17b6915065d3722"}},{"code_sha256_prefix":"c6bdd181afa1fdf7","entry":"valid_str","repo":"robintyh1/icml2021-pengqlambda","repo_kind":"listed","path":"spinup/utils/run_utils.py","file_url":"https://github.com/robintyh1/icml2021-pengqlambda/blob/HEAD/spinup/utils/run_utils.py","link_basis":"harvester_set","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"MIT","inline_ok":false,"mcp_get_code":{"code_sha256":"c6bdd181afa1fdf7"}},{"code_sha256_prefix":"b798db60af40d446","entry":"actv","repo":"jaem-seo/AI_tokamak_control","repo_kind":"listed","path":"common/model_structure.py","file_url":"https://github.com/jaem-seo/AI_tokamak_control/blob/HEAD/common/model_structure.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"b798db60af40d446"}},{"code_sha256_prefix":"c005d4991ad325bd","entry":"add_to_archive","repo":"ollenilsson19/MAP-Elites-GAPG","repo_kind":"listed","path":"utils.py","file_url":"https://github.com/ollenilsson19/MAP-Elites-GAPG/blob/HEAD/utils.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"c005d4991ad325bd"}},{"code_sha256_prefix":"38aa9c2f06df49b7","entry":"cosine_schedule","repo":"markub3327/rl-agent","repo_kind":"listed","path":"rl_toolkit/networks/callbacks/lr.py","file_url":"https://github.com/markub3327/rl-agent/blob/HEAD/rl_toolkit/networks/callbacks/lr.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"38aa9c2f06df49b7"}},{"code_sha256_prefix":"b97fcec4203f4736","entry":"cvt","repo":"ollenilsson19/MAP-Elites-GAPG","repo_kind":"listed","path":"utils.py","file_url":"https://github.com/ollenilsson19/MAP-Elites-GAPG/blob/HEAD/utils.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"b97fcec4203f4736"}},{"code_sha256_prefix":"e0f9ede3192984c6","entry":"density_scatter","repo":"DanielTakeshi/DCUR","repo_kind":"listed","path":"spinup/teaching/inspect_policy.py","file_url":"https://github.com/DanielTakeshi/DCUR/blob/HEAD/spinup/teaching/inspect_policy.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":false,"mcp_get_code":{"code_sha256":"e0f9ede3192984c6"}},{"code_sha256_prefix":"ff2f8ee596f45c07","entry":"f2i","repo":"jaem-seo/AI_tokamak_control","repo_kind":"listed","path":"ai_control_v0.py","file_url":"https://github.com/jaem-seo/AI_tokamak_control/blob/HEAD/ai_control_v0.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"ff2f8ee596f45c07"}},{"code_sha256_prefix":"df403533c9480409","entry":"generate_grid_configs","repo":"ollenilsson19/MAP-Elites-GAPG","repo_kind":"listed","path":"configure_experiment/generate_configs.py","file_url":"https://github.com/ollenilsson19/MAP-Elites-GAPG/blob/HEAD/configure_experiment/generate_configs.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"df403533c9480409"}},{"code_sha256_prefix":"87cf4755f4594737","entry":"get_base_conf","repo":"ollenilsson19/MAP-Elites-GAPG","repo_kind":"listed","path":"configure_experiment/generate_configs.py","file_url":"https://github.com/ollenilsson19/MAP-Elites-GAPG/blob/HEAD/configure_experiment/generate_configs.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"87cf4755f4594737"}},{"code_sha256_prefix":"bd6be7742940fb51","entry":"get_revised_reward","repo":"DanielTakeshi/DCUR","repo_kind":"listed","path":"spinup/teaching/offline_utils.py","file_url":"https://github.com/DanielTakeshi/DCUR/blob/HEAD/spinup/teaching/offline_utils.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":false,"mcp_get_code":{"code_sha256":"bd6be7742940fb51"}},{"code_sha256_prefix":"a2580d7c4a763348","entry":"get_vars","repo":"robintyh1/icml2021-pengqlambda","repo_kind":"listed","path":"spinup/algos/tf1/td3_peng/core.py","file_url":"https://github.com/robintyh1/icml2021-pengqlambda/blob/HEAD/spinup/algos/tf1/td3_peng/core.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":false,"mcp_get_code":{"code_sha256":"a2580d7c4a763348"}},{"code_sha256_prefix":"5fa1289490ba5c13","entry":"i2f","repo":"jaem-seo/AI_tokamak_control","repo_kind":"listed","path":"ai_control_v0.py","file_url":"https://github.com/jaem-seo/AI_tokamak_control/blob/HEAD/ai_control_v0.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"5fa1289490ba5c13"}},{"code_sha256_prefix":"2d2a11f97ea11eec","entry":"load_custom_model","repo":"jaem-seo/AI_tokamak_control","repo_kind":"listed","path":"common/model_structure.py","file_url":"https://github.com/jaem-seo/AI_tokamak_control/blob/HEAD/common/model_structure.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"2d2a11f97ea11eec"}},{"code_sha256_prefix":"a921320c1a9ef680","entry":"load_policy_and_env","repo":"DanielTakeshi/DCUR","repo_kind":"listed","path":"spinup/teaching/load_policy.py","file_url":"https://github.com/DanielTakeshi/DCUR/blob/HEAD/spinup/teaching/load_policy.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":false,"mcp_get_code":{"code_sha256":"a921320c1a9ef680"}},{"code_sha256_prefix":"de91c09e463e0669","entry":"load_policy_model","repo":"DanielTakeshi/DCUR","repo_kind":"listed","path":"spinup/teaching/inspect_actions.py","file_url":"https://github.com/DanielTakeshi/DCUR/blob/HEAD/spinup/teaching/inspect_actions.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":false,"mcp_get_code":{"code_sha256":"de91c09e463e0669"}},{"code_sha256_prefix":"e50af51bd256e662","entry":"load_pytorch_policy","repo":"DanielTakeshi/DCUR","repo_kind":"listed","path":"spinup/teaching/load_policy.py","file_url":"https://github.com/DanielTakeshi/DCUR/blob/HEAD/spinup/teaching/load_policy.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":false,"mcp_get_code":{"code_sha256":"e50af51bd256e662"}},{"code_sha256_prefix":"e68b07bcdded00fa","entry":"mlp","repo":"robintyh1/icml2021-pengqlambda","repo_kind":"listed","path":"spinup/algos/tf1/td3_peng/core.py","file_url":"https://github.com/robintyh1/icml2021-pengqlambda/blob/HEAD/spinup/algos/tf1/td3_peng/core.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":false,"mcp_get_code":{"code_sha256":"e68b07bcdded00fa"}},{"code_sha256_prefix":"17b03c462ce92576","entry":"placeholder","repo":"robintyh1/icml2021-pengqlambda","repo_kind":"listed","path":"spinup/algos/tf1/td3_peng/core.py","file_url":"https://github.com/robintyh1/icml2021-pengqlambda/blob/HEAD/spinup/algos/tf1/td3_peng/core.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":false,"mcp_get_code":{"code_sha256":"17b03c462ce92576"}},{"code_sha256_prefix":"986b521c8e695d46","entry":"plot_fill","repo":"yifan12wu/td3-jax","repo_kind":"listed","path":"plot.py","file_url":"https://github.com/yifan12wu/td3-jax/blob/HEAD/plot.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"986b521c8e695d46"}},{"code_sha256_prefix":"f7d8b73059cc19fc","entry":"r2_k","repo":"jaem-seo/AI_tokamak_control","repo_kind":"listed","path":"old/model_structure.py","file_url":"https://github.com/jaem-seo/AI_tokamak_control/blob/HEAD/old/model_structure.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"f7d8b73059cc19fc"}},{"code_sha256_prefix":"8a70bbd1276e274c","entry":"restore_tf_graph","repo":"robintyh1/icml2021-pengqlambda","repo_kind":"listed","path":"spinup/utils/logx.py","file_url":"https://github.com/robintyh1/icml2021-pengqlambda/blob/HEAD/spinup/utils/logx.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":false,"mcp_get_code":{"code_sha256":"8a70bbd1276e274c"}},{"code_sha256_prefix":"7a6fd6ea6db8460a","entry":"sample_combo_batch","repo":"DanielTakeshi/DCUR","repo_kind":"listed","path":"spinup/teaching/online_rl.py","file_url":"https://github.com/DanielTakeshi/DCUR/blob/HEAD/spinup/teaching/online_rl.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":false,"mcp_get_code":{"code_sha256":"7a6fd6ea6db8460a"}},{"code_sha256_prefix":"1b7cc1754bd06854","entry":"sample_std","repo":"DanielTakeshi/DCUR","repo_kind":"listed","path":"spinup/teaching/load_policy.py","file_url":"https://github.com/DanielTakeshi/DCUR/blob/HEAD/spinup/teaching/load_policy.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":false,"mcp_get_code":{"code_sha256":"1b7cc1754bd06854"}},{"code_sha256_prefix":"fb3b17a4bd91d20a","entry":"should_we_end_early","repo":"DanielTakeshi/DCUR","repo_kind":"listed","path":"spinup/teaching/offline_utils.py","file_url":"https://github.com/DanielTakeshi/DCUR/blob/HEAD/spinup/teaching/offline_utils.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":false,"mcp_get_code":{"code_sha256":"fb3b17a4bd91d20a"}},{"code_sha256_prefix":"c9672c271269cb9d","entry":"smooth","repo":"DanielTakeshi/DCUR","repo_kind":"listed","path":"spinup/teaching/inspect_actions.py","file_url":"https://github.com/DanielTakeshi/DCUR/blob/HEAD/spinup/teaching/inspect_actions.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":false,"mcp_get_code":{"code_sha256":"c9672c271269cb9d"}},{"code_sha256_prefix":"1dcf318473b1f057","entry":"split_list","repo":"yydsok/oparl","repo_kind":"listed","path":"parell.py","file_url":"https://github.com/yydsok/oparl/blob/HEAD/parell.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"1dcf318473b1f057"}},{"code_sha256_prefix":"052527002e0be3dc","entry":"tensormax","repo":"yydsok/oparl","repo_kind":"listed","path":"TD3.py","file_url":"https://github.com/yydsok/oparl/blob/HEAD/TD3.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"052527002e0be3dc"}},{"code_sha256_prefix":"a8d4fda0f5e30ac7","entry":"tensormin","repo":"yydsok/oparl","repo_kind":"listed","path":"TD3.py","file_url":"https://github.com/yydsok/oparl/blob/HEAD/TD3.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"a8d4fda0f5e30ac7"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}