{"url":"/sota/continuous-control-on-pybullet-ant","task":{"name":"Continuous Control","url":"/task/continuous-control","note":null},"dataset":{"name":"PyBullet Ant","url":"/dataset/pybullet"},"category":"Computer Vision","categories":["Computer Vision","Playing Games","Robots"],"category_note":null,"description":"Continuous control in the context of playing games, especially within artificial intelligence (AI) and machine learning (ML), refers to the ability to make a series of smooth, ongoing adjustments or actions to control a game or a simulation. This is in contrast to discrete control, where the actions are limited to a set of specific, distinct choices. Continuous control is crucial in environments where precision, timing, and the magnitude of actions matter, such as driving a car in a racing game, controlling a character in a simulation, or managing the flight of an aircraft in a flight simulator.","description_from":"task","source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28","rank":"the archive's row order at snapshot; not re-ranked","rows_end_at":"2025-07-28","rows_withheld_as_spam":0,"metric_values":"the archive's strings, untouched"},"metrics":["Return"],"metric_direction":{"note":"inferred from the metric name only (the archive records no direction); null = not inferred, chart draws points only","by_metric":{"Return":null}},"counts":{"rows":8,"rows_with_code":8,"rows_with_paper_page":8,"rows_dated":8,"rows_using_additional_data":0},"rows":[{"rank_in_archive_order":1,"model":"SAC gSDE","metrics":{"Return":"3459"},"uses_additional_data":false,"paper_date":"2020-05-12","paper":"/paper/generalized-state-dependent-exploration-for","paper_url":"https://arxiv.org/abs/2005.05719v2","paper_title":"Smooth Exploration for Robotic Reinforcement Learning","code":"https://github.com/DLR-RM/stable-baselines3","n_code_links":4,"syntology":{"n_ran":0,"n_unverified":1,"n_samples":1,"n_pointer_only_licence":0}},{"rank_in_archive_order":2,"model":"TD3 gSDE","metrics":{"Return":"3267"},"uses_additional_data":false,"paper_date":"2020-05-12","paper":"/paper/generalized-state-dependent-exploration-for","paper_url":"https://arxiv.org/abs/2005.05719v2","paper_title":"Smooth Exploration for Robotic Reinforcement Learning","code":"https://github.com/DLR-RM/stable-baselines3","n_code_links":4,"syntology":{"n_ran":0,"n_unverified":1,"n_samples":1,"n_pointer_only_licence":0}},{"rank_in_archive_order":3,"model":"TD3","metrics":{"Return":"2865"},"uses_additional_data":false,"paper_date":"2020-05-12","paper":"/paper/generalized-state-dependent-exploration-for","paper_url":"https://arxiv.org/abs/2005.05719v2","paper_title":"Smooth Exploration for Robotic Reinforcement Learning","code":"https://github.com/DLR-RM/stable-baselines3","n_code_links":4,"syntology":{"n_ran":0,"n_unverified":1,"n_samples":1,"n_pointer_only_licence":0}},{"rank_in_archive_order":4,"model":"SAC","metrics":{"Return":"2859"},"uses_additional_data":false,"paper_date":"2020-05-12","paper":"/paper/generalized-state-dependent-exploration-for","paper_url":"https://arxiv.org/abs/2005.05719v2","paper_title":"Smooth Exploration for Robotic Reinforcement Learning","code":"https://github.com/DLR-RM/stable-baselines3","n_code_links":4,"syntology":{"n_ran":0,"n_unverified":1,"n_samples":1,"n_pointer_only_licence":0}},{"rank_in_archive_order":5,"model":"PPO gSDE","metrics":{"Return":"2587"},"uses_additional_data":false,"paper_date":"2020-05-12","paper":"/paper/generalized-state-dependent-exploration-for","paper_url":"https://arxiv.org/abs/2005.05719v2","paper_title":"Smooth Exploration for Robotic Reinforcement Learning","code":"https://github.com/DLR-RM/stable-baselines3","n_code_links":4,"syntology":{"n_ran":0,"n_unverified":1,"n_samples":1,"n_pointer_only_licence":0}},{"rank_in_archive_order":6,"model":"A2C gSDE","metrics":{"Return":"2560"},"uses_additional_data":false,"paper_date":"2020-05-12","paper":"/paper/generalized-state-dependent-exploration-for","paper_url":"https://arxiv.org/abs/2005.05719v2","paper_title":"Smooth Exploration for Robotic Reinforcement Learning","code":"https://github.com/DLR-RM/stable-baselines3","n_code_links":4,"syntology":{"n_ran":0,"n_unverified":1,"n_samples":1,"n_pointer_only_licence":0}},{"rank_in_archive_order":7,"model":"PPO","metrics":{"Return":"2160"},"uses_additional_data":false,"paper_date":"2020-05-12","paper":"/paper/generalized-state-dependent-exploration-for","paper_url":"https://arxiv.org/abs/2005.05719v2","paper_title":"Smooth Exploration for Robotic Reinforcement Learning","code":"https://github.com/DLR-RM/stable-baselines3","n_code_links":4,"syntology":{"n_ran":0,"n_unverified":1,"n_samples":1,"n_pointer_only_licence":0}},{"rank_in_archive_order":8,"model":"A2C","metrics":{"Return":"1967"},"uses_additional_data":false,"paper_date":"2020-05-12","paper":"/paper/generalized-state-dependent-exploration-for","paper_url":"https://arxiv.org/abs/2005.05719v2","paper_title":"Smooth Exploration for Robotic Reinforcement Learning","code":"https://github.com/DLR-RM/stable-baselines3","n_code_links":4,"syntology":{"n_ran":0,"n_unverified":1,"n_samples":1,"n_pointer_only_licence":0}}],"since_archive":{"present":false,"note":"No Syntology-extracted rows are published in this build."},"syntology":{"read_at":"2026-09-24T18:15:14+00:00","claim":"Per row: N of M harvested code samples from that row's paper executed on a synthesized fixture; the other M-N are unverified. Not a reproduction of the row's number; not a correctness claim. n_pointer_only_licence counts samples the site points at rather than redistributes (a licence axis, independent of ran/unverified).","rows_with_graph_line":8,"rows_with_any_sample_ran":0,"distinct_papers_with_graph_line":1,"distinct_papers_with_any_sample_ran":0,"samples_over_distinct_papers":{"n_ran":0,"n_unverified":1,"n_samples":1,"n_pointer_only_licence":0,"note":"each paper (arXiv id) counted once, however many rows it is behind; this is the page-level figure"},"samples_row_weighted":{"n_ran":0,"n_unverified":8,"n_samples":8,"n_pointer_only_licence":0,"note":"row-weighted: a paper behind several rows is counted once per row; inflated relative to samples_over_distinct_papers by design, kept for readers summing the per-row syntology blocks"}}}