{"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/supported-policy-optimization-for-offline","title":"Supported Policy Optimization for Offline Reinforcement Learning","arxiv_id":"2202.06239","date":"2022-02-13","proceeding":null,"authors":["Jialong Wu","Haixu Wu","Zihan Qiu","Jianmin Wang","Mingsheng Long"],"abstract":"Policy constraint methods to offline reinforcement learning (RL) typically utilize parameterization or regularization that constrains the policy to perform actions within the support set of the behavior policy. The elaborative designs of parameterization methods usually intrude into the policy networks, which may bring extra inference cost and cannot take full advantage of well-established online methods. Regularization methods reduce the divergence between the learned policy and the behavior policy, which may mismatch the inherent density-based definition of support set thereby failing to avoid the out-of-distribution actions effectively. This paper presents Supported Policy OpTimization (SPOT), which is directly derived from the theoretical formalization of the density-based support constraint. SPOT adopts a VAE-based density estimator to explicitly model the support set of behavior policy and presents a simple but effective density-based regularization term, which can be plugged non-intrusively into off-the-shelf off-policy RL algorithms. SPOT achieves the state-of-the-art performance on standard benchmarks for offline RL. Benefiting from the pluggable design, offline pretrained models from SPOT can also be applied to perform online fine-tuning seamlessly.","url_abs":"https://arxiv.org/abs/2202.06239v3","url_pdf":"https://arxiv.org/pdf/2202.06239v3.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":"supported-policy-optimization-for-offline","repo_url":"https://github.com/thuml/SPOT","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"MIT"}},{"paper_slug":"supported-policy-optimization-for-offline","repo_url":"https://github.com/corl-team/CORL","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"jax","reach":null},{"paper_slug":"supported-policy-optimization-for-offline","repo_url":"https://github.com/zzmtsvv/rl_task","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":null}],"tasks":[{"task_slug":"offline-rl","task_name":"Offline RL"},{"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":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"syntology_url":"https://syntology.ai/paper/2202.06239","atlas_url":"https://app.syntology.ai/?focus=2202.06239","mcp":null,"developers":"https://syntology.ai/developers","held":true,"reason":"arxiv_id_in_atlas","checked_against":{"atlas_ids":549449,"atlas_ids_sha256":"afd72399dafd9906e9062927f70655952385a3d75488558e1f0484e950ab09b7","read_at":"2026-10-05T01:46:21Z"},"agent_calls":[{"tool":"get_citation_path","arguments":{"paper_1":"2202.06239"},"arguments_in":{"paper_2":"another paper's arXiv id or title"},"call":"get_citation_path(paper_1=\"2202.06239\", paper_2=\"…\")"},{"tool":"get_concepts_for_paper","arguments":{"arxiv_id":"2202.06239"},"call":"get_concepts_for_paper(arxiv_id=\"2202.06239\")"}],"by_repo":[{"repo":"thuml/SPOT","kind":"official","samples":0,"ran":0,"instrument":0,"unverified":0,"harvested_for_other_papers":1,"harvested_for":["2306.12755"],"harvested_for_calls":[{"arxiv_id":"2306.12755","tool":"get_harvested_code_for_paper","arguments":{"arxiv_id":"2306.12755"},"call":"get_harvested_code_for_paper(arxiv_id=\"2306.12755\")"}]},{"repo":"corl-team/CORL","kind":"listed","samples":0,"ran":0,"instrument":0,"unverified":0,"harvested_for_other_papers":5,"harvested_for":["2006.04779","2006.09359","2106.01345","2110.01548","2110.06169"],"harvested_for_calls":[{"arxiv_id":"2006.04779","tool":"get_harvested_code_for_paper","arguments":{"arxiv_id":"2006.04779"},"call":"get_harvested_code_for_paper(arxiv_id=\"2006.04779\")"},{"arxiv_id":"2006.09359","tool":"get_harvested_code_for_paper","arguments":{"arxiv_id":"2006.09359"},"call":"get_harvested_code_for_paper(arxiv_id=\"2006.09359\")"},{"arxiv_id":"2106.01345","tool":"get_harvested_code_for_paper","arguments":{"arxiv_id":"2106.01345"},"call":"get_harvested_code_for_paper(arxiv_id=\"2106.01345\")"},{"arxiv_id":"2110.01548","tool":"get_harvested_code_for_paper","arguments":{"arxiv_id":"2110.01548"},"call":"get_harvested_code_for_paper(arxiv_id=\"2110.01548\")"},{"arxiv_id":"2110.06169","tool":"get_harvested_code_for_paper","arguments":{"arxiv_id":"2110.06169"},"call":"get_harvested_code_for_paper(arxiv_id=\"2110.06169\")"}]},{"repo":"zzmtsvv/rl_task","kind":"listed","samples":0,"ran":0,"instrument":0,"unverified":0,"harvested_for_other_papers":8,"harvested_for":["1906.00949","2006.09359","2106.01345","2110.01548","2110.06169","2208.06193","2301.02328","2306.06569"],"harvested_for_calls":[{"arxiv_id":"1906.00949","tool":"get_harvested_code_for_paper","arguments":{"arxiv_id":"1906.00949"},"call":"get_harvested_code_for_paper(arxiv_id=\"1906.00949\")"},{"arxiv_id":"2006.09359","tool":"get_harvested_code_for_paper","arguments":{"arxiv_id":"2006.09359"},"call":"get_harvested_code_for_paper(arxiv_id=\"2006.09359\")"},{"arxiv_id":"2106.01345","tool":"get_harvested_code_for_paper","arguments":{"arxiv_id":"2106.01345"},"call":"get_harvested_code_for_paper(arxiv_id=\"2106.01345\")"},{"arxiv_id":"2110.01548","tool":"get_harvested_code_for_paper","arguments":{"arxiv_id":"2110.01548"},"call":"get_harvested_code_for_paper(arxiv_id=\"2110.01548\")"},{"arxiv_id":"2110.06169","tool":"get_harvested_code_for_paper","arguments":{"arxiv_id":"2110.06169"},"call":"get_harvested_code_for_paper(arxiv_id=\"2110.06169\")"},{"arxiv_id":"2208.06193","tool":"get_harvested_code_for_paper","arguments":{"arxiv_id":"2208.06193"},"call":"get_harvested_code_for_paper(arxiv_id=\"2208.06193\")"},{"arxiv_id":"2301.02328","tool":"get_harvested_code_for_paper","arguments":{"arxiv_id":"2301.02328"},"call":"get_harvested_code_for_paper(arxiv_id=\"2301.02328\")"},{"arxiv_id":"2306.06569","tool":"get_harvested_code_for_paper","arguments":{"arxiv_id":"2306.06569"},"call":"get_harvested_code_for_paper(arxiv_id=\"2306.06569\")"}]}],"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"},"code_links_note":null,"arxiv_metadata":null,"syntology_extracted_results":null,"record_sha256":"bb409638545b47f2ff9a92eccd99d2667ab03fa332eddb8f54f25d43a5fbc9f6","record_changed_at":"2026-09-28","record_changed_at_basis":"first_hashed"}