{"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/leveraging-skills-from-unlabeled-prior-data","title":"Leveraging Skills from Unlabeled Prior Data for Efficient Online Exploration","arxiv_id":"2410.18076","date":"2024-10-23","proceeding":null,"authors":["Max Wilcoxson","Qiyang Li","Kevin Frans","Sergey Levine"],"abstract":"Unsupervised pretraining has been transformative in many supervised domains. However, applying such ideas to reinforcement learning (RL) presents a unique challenge in that fine-tuning does not involve mimicking task-specific data, but rather exploring and locating the solution through iterative self-improvement. In this work, we study how unlabeled prior trajectory data can be leveraged to learn efficient exploration strategies. While prior data can be used to pretrain a set of low-level skills, or as additional off-policy data for online RL, it has been unclear how to combine these ideas effectively for online exploration. Our method SUPE (Skills from Unlabeled Prior data for Exploration) demonstrates that a careful combination of these ideas compounds their benefits. Our method first extracts low-level skills using a variational autoencoder (VAE), and then pseudo-relabels unlabeled trajectories using an optimistic reward model, transforming prior data into high-level, task-relevant examples. Finally, SUPE uses these transformed examples as additional off-policy data for online RL to learn a high-level policy that composes pretrained low-level skills to explore efficiently. We empirically show that SUPE reliably outperforms prior strategies, successfully solving a suite of long-horizon, sparse-reward tasks. Code: https://github.com/rail-berkeley/supe.","url_abs":"https://arxiv.org/abs/2410.18076v2","url_pdf":"https://arxiv.org/pdf/2410.18076v2.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":"leveraging-skills-from-unlabeled-prior-data","repo_url":"https://github.com/rail-berkeley/supe","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"jax","reach":{"status":"ok","spdx":"MIT"}}],"tasks":[{"task_slug":"efficient-exploration","task_name":"Efficient Exploration"},{"task_slug":"reinforcement-learning-1","task_name":"Reinforcement Learning (RL)"}],"methods":[{"method_slug":"set","method_name":"SET"}],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"syntology_url":"https://syntology.ai/paper/2410.18076","atlas_url":"https://app.syntology.ai/?focus=2410.18076","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2410.18076"},"calls":[{"tool":"get_harvested_code_for_paper","arguments":{"arxiv_id":"2410.18076"},"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":"2410.18076"},"call":"get_harvested_code_for_paper(arxiv_id=\"2410.18076\")"},{"tool":"get_code","arguments_in":{"code_sha256":"syntology.samples[].code_sha256"},"call":"get_code(code_sha256=\"…\")"},{"tool":"get_citation_path","arguments":{"paper_1":"2410.18076"},"arguments_in":{"paper_2":"another paper's arXiv id or title"},"call":"get_citation_path(paper_1=\"2410.18076\", paper_2=\"…\")"},{"tool":"get_concepts_for_paper","arguments":{"arxiv_id":"2410.18076"},"call":"get_concepts_for_paper(arxiv_id=\"2410.18076\")"}],"by_repo":[{"repo":"rail-berkeley/supe","kind":"official","samples":8,"ran":8,"instrument":6,"unverified":0}],"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/2410.18076.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/2410.18076.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":"deterministic:regex_extraction","url":"https://github.com/rail-berkeley/supe","reach":{"status":"ok","spdx":"MIT"}}],"summary":{"ran_draft_wrong":6,"ran":2},"n_samples":8,"n_ran":8,"n_constructed":0,"n_ran_checked":2,"n_instrument":6,"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":{"official":{"samples":8,"ran":8,"n_ran_checked":2,"n_instrument":6,"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"},"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":8,"n_ran_without_level_date":0,"n_ran_signature_not_shown":0,"levels_written_between":{"first":"2026-09-26","last":"2026-09-26","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":"58986e64f92121be","code_sha256_prefix":"58986e64f92121be","entry":"default_init","repo":"rail-berkeley/supe","repo_kind":"official","path":"supe/agents/model.py","file_url":"https://github.com/rail-berkeley/supe/blob/HEAD/supe/agents/model.py","link_basis":"first_harvest_node","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"OUTPUT_MISDECLARED","metamorphic_tier":null,"behaviour_fingerprint":false,"signature":"scale:float/0/float","fixture_out_type":"function","level_recorded_at":"2026-09-26T01:24:49.973517+00:00","code_page":"/code/default-init","census":null,"licence":"MIT","inline_ok":true,"inline_ok_link":true,"withheld_clause":null,"mcp_get_code":{"code_sha256":"58986e64f92121be"}},{"code_sha256":"7029f5c1fca329c2","code_sha256_prefix":"7029f5c1fca329c2","entry":"get_observation_at_index_in_chunk","repo":"rail-berkeley/supe","repo_kind":"official","path":"supe/utils.py","file_url":"https://github.com/rail-berkeley/supe/blob/HEAD/supe/utils.py","link_basis":"first_harvest_node","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"OUTPUT_MISDECLARED","metamorphic_tier":null,"behaviour_fingerprint":false,"signature":"observations:dict/0/?, index:int/0/int","fixture_out_type":"dict","level_recorded_at":"2026-09-26T01:24:49.973517+00:00","code_page":null,"census":null,"licence":"MIT","inline_ok":true,"inline_ok_link":true,"withheld_clause":null,"mcp_get_code":{"code_sha256":"7029f5c1fca329c2"}},{"code_sha256":"25d6b4feb55a5cc6","code_sha256_prefix":"25d6b4feb55a5cc6","entry":"list_1d_of_dicts_to_dict_of_1d_lists","repo":"rail-berkeley/supe","repo_kind":"official","path":"supe/utils.py","file_url":"https://github.com/rail-berkeley/supe/blob/HEAD/supe/utils.py","link_basis":"first_harvest_node","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"OUTPUT_MISDECLARED","metamorphic_tier":null,"behaviour_fingerprint":false,"signature":"list_of_dicts:list/1/dict","fixture_out_type":"dict","level_recorded_at":"2026-09-26T01:24:49.973517+00:00","code_page":null,"census":null,"licence":"MIT","inline_ok":true,"inline_ok_link":true,"withheld_clause":null,"mcp_get_code":{"code_sha256":"25d6b4feb55a5cc6"}},{"code_sha256":"662f22bdb29e3d83","code_sha256_prefix":"662f22bdb29e3d83","entry":"list_2d_of_dicts_to_dict_of_2d_lists","repo":"rail-berkeley/supe","repo_kind":"official","path":"supe/utils.py","file_url":"https://github.com/rail-berkeley/supe/blob/HEAD/supe/utils.py","link_basis":"first_harvest_node","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"OUTPUT_MISDECLARED","metamorphic_tier":null,"behaviour_fingerprint":false,"signature":"list_of_dicts:list/1/list","fixture_out_type":"dict","level_recorded_at":"2026-09-26T01:24:49.973517+00:00","code_page":null,"census":null,"licence":"MIT","inline_ok":true,"inline_ok_link":true,"withheld_clause":null,"mcp_get_code":{"code_sha256":"662f22bdb29e3d83"}},{"code_sha256":"7f86bee8890076da","code_sha256_prefix":"7f86bee8890076da","entry":"orthogonal_init","repo":"rail-berkeley/supe","repo_kind":"official","path":"supe/agents/model.py","file_url":"https://github.com/rail-berkeley/supe/blob/HEAD/supe/agents/model.py","link_basis":"first_harvest_node","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"OUTPUT_MISDECLARED","metamorphic_tier":null,"behaviour_fingerprint":false,"signature":"scale:ArrayImpl/0/float","fixture_out_type":"function","level_recorded_at":"2026-09-26T01:24:49.973517+00:00","code_page":"/code/orthogonal-init","census":null,"licence":"MIT","inline_ok":true,"inline_ok_link":true,"withheld_clause":null,"mcp_get_code":{"code_sha256":"7f86bee8890076da"}},{"code_sha256":"0718f0eea8311eba","code_sha256_prefix":"0718f0eea8311eba","entry":"share_encoder","repo":"rail-berkeley/supe","repo_kind":"official","path":"supe/networks/pixel_multiplexer.py","file_url":"https://github.com/rail-berkeley/supe/blob/HEAD/supe/networks/pixel_multiplexer.py","link_basis":"first_harvest_node","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"OUTPUT_MISDECLARED","metamorphic_tier":null,"behaviour_fingerprint":false,"signature":"source:MockModel/0/?, target:MockModel/0/?","fixture_out_type":"MockModel","level_recorded_at":"2026-09-26T01:24:49.973517+00:00","code_page":null,"census":null,"licence":"MIT","inline_ok":true,"inline_ok_link":true,"withheld_clause":null,"mcp_get_code":{"code_sha256":"0718f0eea8311eba"}},{"code_sha256":"84f8f91dd99ce50f","code_sha256_prefix":"84f8f91dd99ce50f","entry":"subsample_ensemble","repo":"rail-berkeley/supe","repo_kind":"official","path":"supe/networks/ensemble.py","file_url":"https://github.com/rail-berkeley/supe/blob/HEAD/supe/networks/ensemble.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"signature":"key:ArrayImpl/1/int, params:dict/0/?, num_sample:int/0/int, num_qs:int/0/int","fixture_out_type":"FrozenDict","level_recorded_at":"2026-09-26T01:24:49.973517+00:00","code_page":"/code/subsample-ensemble","census":null,"licence":"MIT","inline_ok":true,"inline_ok_link":true,"withheld_clause":null,"mcp_get_code":{"code_sha256":"84f8f91dd99ce50f"}},{"code_sha256":"f23c0c9faf00d830","code_sha256_prefix":"f23c0c9faf00d830","entry":"update_target_network","repo":"rail-berkeley/supe","repo_kind":"official","path":"supe/agents/model.py","file_url":"https://github.com/rail-berkeley/supe/blob/HEAD/supe/agents/model.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"signature":"main_params:dict/0/?, target_params:dict/0/?, tau:float/0/float","fixture_out_type":"dict","level_recorded_at":"2026-09-26T01:55:17.694675+00:00","code_page":"/code/update-target-network","census":null,"licence":"MIT","inline_ok":true,"inline_ok_link":true,"withheld_clause":null,"mcp_get_code":{"code_sha256":"f23c0c9faf00d830"}}]},"code_links_note":null,"arxiv_metadata":null,"syntology_extracted_results":null,"record_sha256":"688dd1d6a703089bfbf88190481fa05849b3d355f6a50a3088c9c9da3306638c","record_changed_at":"2026-10-04","record_changed_at_basis":"changed"}