{"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/generalized-state-dependent-exploration-for","title":"Smooth Exploration for Robotic Reinforcement Learning","arxiv_id":"2005.05719","date":"2020-05-12","proceeding":null,"authors":["Antonin Raffin","Jens Kober","Freek Stulp"],"abstract":"Reinforcement learning (RL) enables robots to learn skills from interactions with the real world. In practice, the unstructured step-based exploration used in Deep RL -- often very successful in simulation -- leads to jerky motion patterns on real robots. Consequences of the resulting shaky behavior are poor exploration, or even damage to the robot. We address these issues by adapting state-dependent exploration (SDE) to current Deep RL algorithms. To enable this adaptation, we propose two extensions to the original SDE, using more general features and re-sampling the noise periodically, which leads to a new exploration method generalized state-dependent exploration (gSDE). We evaluate gSDE both in simulation, on PyBullet continuous control tasks, and directly on three different real robots: a tendon-driven elastic robot, a quadruped and an RC car. The noise sampling interval of gSDE permits to have a compromise between performance and smoothness, which allows training directly on the real robots without loss of performance. The code is available at https://github.com/DLR-RM/stable-baselines3.","url_abs":"https://arxiv.org/abs/2005.05719v2","url_pdf":"https://arxiv.org/pdf/2005.05719v2.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":"generalized-state-dependent-exploration-for","repo_url":"https://github.com/DLR-RM/stable-baselines3","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":0,"framework":"pytorch","reach":null},{"paper_slug":"generalized-state-dependent-exploration-for","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":"generalized-state-dependent-exploration-for","repo_url":"https://github.com/araffin/sbx","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":0,"framework":"jax","reach":null},{"paper_slug":"generalized-state-dependent-exploration-for","repo_url":"https://github.com/facebookresearch/rl","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":"reinforcement-learning","task_name":"Reinforcement Learning"},{"task_slug":"reinforcement-learning-1","task_name":"Reinforcement Learning (RL)"},{"task_slug":"continuous-control","task_name":"continuous-control"},{"task_slug":"reinforcement-learning-2","task_name":"reinforcement-learning"}],"methods":[{"method_slug":"a2c","method_name":"A2C"},{"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":"entropy-regularization","method_name":"Entropy Regularization"},{"method_slug":"experience-replay","method_name":"Experience Replay"},{"method_slug":"ppo","method_name":"PPO"},{"method_slug":"relu","method_name":"ReLU"},{"method_slug":"soft-actor-critic","method_name":"Soft Actor Critic"},{"method_slug":"td3","method_name":"TD3"},{"method_slug":"target-policy-smoothing","method_name":"Target Policy Smoothing"},{"method_slug":"gsde","method_name":"gSDE"}],"datasets_introduced":[],"methods_introduced":[{"slug":"gsde","name":"gSDE","full_name":"Generalized State-Dependent Exploration"}],"results":[{"leaderboard":"/sota/continuous-control-on-pybullet-ant","task":"Continuous Control","dataset":"PyBullet Ant","model":"SAC gSDE","rank_in_archive_order":1,"of":8,"metrics":{"Return":"3459"},"uses_additional_data":false},{"leaderboard":"/sota/continuous-control-on-pybullet-ant","task":"Continuous Control","dataset":"PyBullet Ant","model":"TD3 gSDE","rank_in_archive_order":2,"of":8,"metrics":{"Return":"3267"},"uses_additional_data":false},{"leaderboard":"/sota/continuous-control-on-pybullet-ant","task":"Continuous Control","dataset":"PyBullet Ant","model":"TD3","rank_in_archive_order":3,"of":8,"metrics":{"Return":"2865"},"uses_additional_data":false},{"leaderboard":"/sota/continuous-control-on-pybullet-ant","task":"Continuous Control","dataset":"PyBullet Ant","model":"SAC","rank_in_archive_order":4,"of":8,"metrics":{"Return":"2859"},"uses_additional_data":false},{"leaderboard":"/sota/continuous-control-on-pybullet-ant","task":"Continuous Control","dataset":"PyBullet Ant","model":"PPO gSDE","rank_in_archive_order":5,"of":8,"metrics":{"Return":"2587"},"uses_additional_data":false},{"leaderboard":"/sota/continuous-control-on-pybullet-ant","task":"Continuous Control","dataset":"PyBullet Ant","model":"A2C gSDE","rank_in_archive_order":6,"of":8,"metrics":{"Return":"2560"},"uses_additional_data":false},{"leaderboard":"/sota/continuous-control-on-pybullet-ant","task":"Continuous Control","dataset":"PyBullet Ant","model":"PPO","rank_in_archive_order":7,"of":8,"metrics":{"Return":"2160"},"uses_additional_data":false},{"leaderboard":"/sota/continuous-control-on-pybullet-ant","task":"Continuous Control","dataset":"PyBullet Ant","model":"A2C","rank_in_archive_order":8,"of":8,"metrics":{"Return":"1967"},"uses_additional_data":false},{"leaderboard":"/sota/continuous-control-on-pybullet-halfcheetah","task":"Continuous Control","dataset":"PyBullet HalfCheetah","model":"SAC","rank_in_archive_order":1,"of":8,"metrics":{"Return":"2883"},"uses_additional_data":false},{"leaderboard":"/sota/continuous-control-on-pybullet-halfcheetah","task":"Continuous Control","dataset":"PyBullet HalfCheetah","model":"SAC gSDE","rank_in_archive_order":2,"of":8,"metrics":{"Return":"2850"},"uses_additional_data":false},{"leaderboard":"/sota/continuous-control-on-pybullet-halfcheetah","task":"Continuous Control","dataset":"PyBullet HalfCheetah","model":"PPO + gSDE","rank_in_archive_order":3,"of":8,"metrics":{"Return":"2760"},"uses_additional_data":false},{"leaderboard":"/sota/continuous-control-on-pybullet-halfcheetah","task":"Continuous Control","dataset":"PyBullet HalfCheetah","model":"TD3","rank_in_archive_order":4,"of":8,"metrics":{"Return":"2687"},"uses_additional_data":false},{"leaderboard":"/sota/continuous-control-on-pybullet-halfcheetah","task":"Continuous Control","dataset":"PyBullet HalfCheetah","model":"TD3 gSDE","rank_in_archive_order":5,"of":8,"metrics":{"Return":"2578"},"uses_additional_data":false},{"leaderboard":"/sota/continuous-control-on-pybullet-halfcheetah","task":"Continuous Control","dataset":"PyBullet HalfCheetah","model":"PPO","rank_in_archive_order":6,"of":8,"metrics":{"Return":"2254"},"uses_additional_data":false},{"leaderboard":"/sota/continuous-control-on-pybullet-halfcheetah","task":"Continuous Control","dataset":"PyBullet HalfCheetah","model":"A2C + gSDE","rank_in_archive_order":7,"of":8,"metrics":{"Return":"2028"},"uses_additional_data":false},{"leaderboard":"/sota/continuous-control-on-pybullet-halfcheetah","task":"Continuous Control","dataset":"PyBullet HalfCheetah","model":"A2C","rank_in_archive_order":8,"of":8,"metrics":{"Return":"1652"},"uses_additional_data":false},{"leaderboard":"/sota/continuous-control-on-pybullet-hopper","task":"Continuous Control","dataset":"PyBullet Hopper","model":"SAC gSDE","rank_in_archive_order":1,"of":8,"metrics":{"Return":"2646"},"uses_additional_data":false},{"leaderboard":"/sota/continuous-control-on-pybullet-hopper","task":"Continuous Control","dataset":"PyBullet Hopper","model":"PPO gSDE","rank_in_archive_order":2,"of":8,"metrics":{"Return":"2508"},"uses_additional_data":false},{"leaderboard":"/sota/continuous-control-on-pybullet-hopper","task":"Continuous Control","dataset":"PyBullet Hopper","model":"SAC","rank_in_archive_order":3,"of":8,"metrics":{"Return":"2477"},"uses_additional_data":false},{"leaderboard":"/sota/continuous-control-on-pybullet-hopper","task":"Continuous Control","dataset":"PyBullet Hopper","model":"TD3","rank_in_archive_order":4,"of":8,"metrics":{"Return":"2470"},"uses_additional_data":false},{"leaderboard":"/sota/continuous-control-on-pybullet-hopper","task":"Continuous Control","dataset":"PyBullet Hopper","model":"TD3 gSDE","rank_in_archive_order":5,"of":8,"metrics":{"Return":"2353"},"uses_additional_data":false},{"leaderboard":"/sota/continuous-control-on-pybullet-hopper","task":"Continuous Control","dataset":"PyBullet Hopper","model":"PPO","rank_in_archive_order":6,"of":8,"metrics":{"Return":"1622"},"uses_additional_data":false},{"leaderboard":"/sota/continuous-control-on-pybullet-hopper","task":"Continuous Control","dataset":"PyBullet Hopper","model":"A2C","rank_in_archive_order":7,"of":8,"metrics":{"Return":"1559"},"uses_additional_data":false},{"leaderboard":"/sota/continuous-control-on-pybullet-hopper","task":"Continuous Control","dataset":"PyBullet Hopper","model":"A2C gSDE","rank_in_archive_order":8,"of":8,"metrics":{"Return":"1448"},"uses_additional_data":false},{"leaderboard":"/sota/continuous-control-on-pybullet-walker2d","task":"Continuous Control","dataset":"PyBullet Walker2D","model":"SAC gSDE","rank_in_archive_order":1,"of":8,"metrics":{"Return":"2341"},"uses_additional_data":false},{"leaderboard":"/sota/continuous-control-on-pybullet-walker2d","task":"Continuous Control","dataset":"PyBullet Walker2D","model":"SAC","rank_in_archive_order":2,"of":8,"metrics":{"Return":"2215"},"uses_additional_data":false},{"leaderboard":"/sota/continuous-control-on-pybullet-walker2d","task":"Continuous Control","dataset":"PyBullet Walker2D","model":"TD3","rank_in_archive_order":3,"of":8,"metrics":{"Return":"2106"},"uses_additional_data":false},{"leaderboard":"/sota/continuous-control-on-pybullet-walker2d","task":"Continuous Control","dataset":"PyBullet Walker2D","model":"TD3 gSDE","rank_in_archive_order":4,"of":8,"metrics":{"Return":"1989"},"uses_additional_data":false},{"leaderboard":"/sota/continuous-control-on-pybullet-walker2d","task":"Continuous Control","dataset":"PyBullet Walker2D","model":"PPO gSDE","rank_in_archive_order":5,"of":8,"metrics":{"Return":"1776"},"uses_additional_data":false},{"leaderboard":"/sota/continuous-control-on-pybullet-walker2d","task":"Continuous Control","dataset":"PyBullet Walker2D","model":"PPO","rank_in_archive_order":6,"of":8,"metrics":{"Return":"1238"},"uses_additional_data":false},{"leaderboard":"/sota/continuous-control-on-pybullet-walker2d","task":"Continuous Control","dataset":"PyBullet Walker2D","model":"A2C gSDE","rank_in_archive_order":7,"of":8,"metrics":{"Return":"694"},"uses_additional_data":false},{"leaderboard":"/sota/continuous-control-on-pybullet-walker2d","task":"Continuous Control","dataset":"PyBullet Walker2D","model":"A2C","rank_in_archive_order":8,"of":8,"metrics":{"Return":"443"},"uses_additional_data":false}],"syntology":{"syntology_url":"https://syntology.ai/paper/2005.05719","atlas_url":"https://app.syntology.ai/?focus=2005.05719","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2005.05719"},"calls":[{"tool":"get_harvested_code_for_paper","arguments":{"arxiv_id":"2005.05719"},"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":"2005.05719"},"call":"get_harvested_code_for_paper(arxiv_id=\"2005.05719\")"},{"tool":"get_code","arguments_in":{"code_sha256":"syntology.samples[].code_sha256"},"call":"get_code(code_sha256=\"…\")"},{"tool":"get_citation_path","arguments":{"paper_1":"2005.05719"},"arguments_in":{"paper_2":"another paper's arXiv id or title"},"call":"get_citation_path(paper_1=\"2005.05719\", paper_2=\"…\")"},{"tool":"get_concepts_for_paper","arguments":{"arxiv_id":"2005.05719"},"call":"get_concepts_for_paper(arxiv_id=\"2005.05719\")"}],"by_repo":[{"repo":"DLR-RM/stable-baselines3","kind":"official","samples":0,"ran":0,"instrument":0,"unverified":0,"harvested_for_other_papers":1,"harvested_for":["2603.01771"],"harvested_for_calls":[{"arxiv_id":"2603.01771","tool":"get_harvested_code_for_paper","arguments":{"arxiv_id":"2603.01771"},"call":"get_harvested_code_for_paper(arxiv_id=\"2603.01771\")"}]},{"repo":"markub3327/rl-toolkit","kind":"listed","samples":1,"ran":1,"instrument":0,"unverified":0},{"repo":"araffin/sbx","kind":"listed","samples":0,"ran":0,"instrument":0,"unverified":0,"harvested_for_other_papers":1,"harvested_for":["2410.09754"],"harvested_for_calls":[{"arxiv_id":"2410.09754","tool":"get_harvested_code_for_paper","arguments":{"arxiv_id":"2410.09754"},"call":"get_harvested_code_for_paper(arxiv_id=\"2410.09754\")"}]},{"repo":"facebookresearch/rl","kind":"listed","samples":0,"ran":0,"instrument":0,"unverified":0,"harvested_for_other_papers":1,"harvested_for":["2306.17100"],"harvested_for_calls":[{"arxiv_id":"2306.17100","tool":"get_harvested_code_for_paper","arguments":{"arxiv_id":"2306.17100"},"call":"get_harvested_code_for_paper(arxiv_id=\"2306.17100\")"}]}],"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","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/2005.05719.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/2005.05719.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/DLR-RM/stable-baselines3","reach":null},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/facebookresearch/rl","reach":{"status":"ok","spdx":"MIT"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/araffin/sbx","reach":null},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/markub3327/rl-toolkit","reach":{"status":"ok","spdx":"MIT"}}],"summary":{"ran":1},"n_samples":1,"n_ran":1,"n_constructed":0,"n_ran_checked":1,"n_instrument":0,"n_unverified":0,"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":1,"ran":1,"n_ran_checked":1,"n_instrument":0,"repositories":1}},"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":["DLR-RM/stable-baselines3"],"harvested_for_other_papers":[1],"samples_from_other_repositories":1,"other_repositories":1,"samples_unlocated":0},"n_pointer_only_for_licence":0,"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":1,"n_ran_without_level_date":0,"n_ran_signature_not_shown":0,"levels_written_between":{"first":"2026-09-24","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":"38aa9c2f06df49b7","code_sha256_prefix":"38aa9c2f06df49b7","entry":"cosine_schedule","repo":"markub3327/rl-toolkit","repo_kind":"listed","path":"rl_toolkit/networks/callbacks/lr.py","file_url":"https://github.com/markub3327/rl-toolkit/blob/HEAD/rl_toolkit/networks/callbacks/lr.py","link_basis":"harvester_set","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"signature":"base_lr:float/0/float, total_steps:int/0/int, warmup_steps:int/0/int","fixture_out_type":"function","level_recorded_at":"2026-09-24T22:24:42.659479+00:00","code_page":"/code/cosine-schedule","census":null,"licence":"MIT","inline_ok":true,"inline_ok_link":true,"withheld_clause":null,"mcp_get_code":{"code_sha256":"38aa9c2f06df49b7"}}]},"code_links_note":null,"arxiv_metadata":null,"syntology_extracted_results":null,"record_sha256":"a356ddc7b43e6745e9ec8efe3b947a3d86b2325095426dee0a05d3f65186ef8f","record_changed_at":"2026-09-28","record_changed_at_basis":"first_hashed"}