{"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/a-closer-look-at-advantage-filtered","title":"A Closer Look at Advantage-Filtered Behavioral Cloning in High-Noise Datasets","arxiv_id":"2110.04698","date":"2021-10-10","proceeding":null,"authors":["Jake Grigsby","Yanjun Qi"],"abstract":"Recent Offline Reinforcement Learning methods have succeeded in learning high-performance policies from fixed datasets of experience. A particularly effective approach learns to first identify and then mimic optimal decision-making strategies. Our work evaluates this method's ability to scale to vast datasets consisting almost entirely of sub-optimal noise. A thorough investigation on a custom benchmark helps identify several key challenges involved in learning from high-noise datasets. We re-purpose prioritized experience sampling to locate expert-level demonstrations among millions of low-performance samples. This modification enables offline agents to learn state-of-the-art policies in benchmark tasks using datasets where expert actions are outnumbered nearly 65:1.","url_abs":"https://arxiv.org/abs/2110.04698v2","url_pdf":"https://arxiv.org/pdf/2110.04698v2.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":"a-closer-look-at-advantage-filtered","repo_url":"https://github.com/jakegrigsby/cc-afbc","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"MIT"}},{"paper_slug":"a-closer-look-at-advantage-filtered","repo_url":"https://github.com/jakegrigsby/deep_control","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":null},{"paper_slug":"a-closer-look-at-advantage-filtered","repo_url":"https://github.com/jakegrigsby/super_sac","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok"}}],"tasks":[{"task_slug":"decision-making","task_name":"Decision Making"},{"task_slug":"reinforcement-learning-1","task_name":"Reinforcement Learning (RL)"},{"task_slug":"reinforcement-learning-2","task_name":"reinforcement-learning"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"syntology_url":"https://syntology.ai/paper/2110.04698","atlas_url":"https://app.syntology.ai/?focus=2110.04698","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2110.04698"}},"developers":"https://syntology.ai/developers","read_at":"2026-09-25T09:33:49+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/jakegrigsby/cc-afbc","reach":{"status":"ok","spdx":"MIT"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/jakegrigsby/super_sac","reach":{"status":"ok"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/jakegrigsby/deep_control","reach":null}],"summary":{"ran":2,"ran_fixture":1,"unverified":2},"by_repo_kind":{"official":{"samples":5,"ran":3,"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,"samples":[{"code_sha256_prefix":"63bb6952481500e6","entry":"get_linear_schedule","repo":"jakegrigsby/cc-afbc","repo_kind":"official","path":"filters.py","file_url":"https://github.com/jakegrigsby/cc-afbc/blob/HEAD/filters.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":true,"mcp_get_code":{"code_sha256":"63bb6952481500e6"}},{"code_sha256_prefix":"ab198159e66084fd","entry":"robosuite_action_adjustment","repo":"jakegrigsby/cc-afbc","repo_kind":"official","path":"rl_utils/envs.py","file_url":"https://github.com/jakegrigsby/cc-afbc/blob/HEAD/rl_utils/envs.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":true,"mcp_get_code":{"code_sha256":"ab198159e66084fd"}},{"code_sha256_prefix":"cf11c744c61b2185","entry":"unique","repo":"jakegrigsby/cc-afbc","repo_kind":"official","path":"rl_utils/replay.py","file_url":"https://github.com/jakegrigsby/cc-afbc/blob/HEAD/rl_utils/replay.py","link_basis":"harvester_set","language":"python","status":"ran_fixture","verification_level":1,"contract_check":"RAISES","metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"cf11c744c61b2185"}},{"code_sha256_prefix":"771d49bb23e04b6c","entry":"highway_env","repo":"jakegrigsby/cc-afbc","repo_kind":"official","path":"rl_utils/envs.py","file_url":"https://github.com/jakegrigsby/cc-afbc/blob/HEAD/rl_utils/envs.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":"771d49bb23e04b6c"}},{"code_sha256_prefix":"d13ad67924e983b5","entry":"load_gym","repo":"jakegrigsby/cc-afbc","repo_kind":"official","path":"rl_utils/envs.py","file_url":"https://github.com/jakegrigsby/cc-afbc/blob/HEAD/rl_utils/envs.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":"d13ad67924e983b5"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}