{"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/percentile-criterion-optimization-in-offline-1","title":"Percentile Criterion Optimization in Offline Reinforcement Learning","arxiv_id":"2404.05055","date":"2024-04-07","proceeding":"NeurIPS 2023 11","authors":["Elita A. Lobo","Cyrus Cousins","Yair Zick","Marek Petrik"],"abstract":"In reinforcement learning, robust policies for high-stakes decision-making problems with limited data are usually computed by optimizing the \\emph{percentile criterion}. The percentile criterion is approximately solved by constructing an \\emph{ambiguity set} that contains the true model with high probability and optimizing the policy for the worst model in the set. Since the percentile criterion is non-convex, constructing ambiguity sets is often challenging. Existing work uses \\emph{Bayesian credible regions} as ambiguity sets, but they are often unnecessarily large and result in learning overly conservative policies. To overcome these shortcomings, we propose a novel Value-at-Risk based dynamic programming algorithm to optimize the percentile criterion without explicitly constructing any ambiguity sets. Our theoretical and empirical results show that our algorithm implicitly constructs much smaller ambiguity sets and learns less conservative robust policies.","url_abs":"https://arxiv.org/abs/2404.05055v1","url_pdf":"https://arxiv.org/pdf/2404.05055v1.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":"percentile-criterion-optimization-in-offline-1","repo_url":"https://github.com/elitalobo/varframework","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":0,"framework":"none","reach":{"status":"ok"}}],"tasks":[{"task_slug":"decision-making","task_name":"Decision Making"},{"task_slug":"reinforcement-learning","task_name":"Reinforcement Learning"},{"task_slug":"reinforcement-learning-2","task_name":"reinforcement-learning"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"syntology_url":"https://syntology.ai/paper/2404.05055","atlas_url":"https://app.syntology.ai/?focus=2404.05055","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2404.05055"}},"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/elitalobo/varframework","reach":{"status":"ok"}}],"summary":{"ran":6,"unverified":3},"by_repo_kind":{"official":{"samples":9,"ran":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":9,"samples":[{"code_sha256_prefix":"f2b3e7b71b5c895c","entry":"compute_covariance","repo":"elitalobo/varframework","repo_kind":"official","path":"src/plot_radii.py","file_url":"https://github.com/elitalobo/varframework/blob/HEAD/src/plot_radii.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"f2b3e7b71b5c895c"}},{"code_sha256_prefix":"e123e2efd7912694","entry":"load_nsa","repo":"elitalobo/varframework","repo_kind":"official","path":"src/algorithms.py","file_url":"https://github.com/elitalobo/varframework/blob/HEAD/src/algorithms.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"e123e2efd7912694"}},{"code_sha256_prefix":"02051dc1bb24f648","entry":"permute_point","repo":"elitalobo/varframework","repo_kind":"official","path":"src/plot_ternary.py","file_url":"https://github.com/elitalobo/varframework/blob/HEAD/src/plot_ternary.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"02051dc1bb24f648"}},{"code_sha256_prefix":"3a8ea5b39d16b89e","entry":"project_point","repo":"elitalobo/varframework","repo_kind":"official","path":"src/plot_ternary.py","file_url":"https://github.com/elitalobo/varframework/blob/HEAD/src/plot_ternary.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"3a8ea5b39d16b89e"}},{"code_sha256_prefix":"566b67b5fd055137","entry":"unzip","repo":"elitalobo/varframework","repo_kind":"official","path":"src/plot_ternary.py","file_url":"https://github.com/elitalobo/varframework/blob/HEAD/src/plot_ternary.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"566b67b5fd055137"}},{"code_sha256_prefix":"79aeeca51b756813","entry":"validate_transitionp","repo":"elitalobo/varframework","repo_kind":"official","path":"src/algorithms.py","file_url":"https://github.com/elitalobo/varframework/blob/HEAD/src/algorithms.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"79aeeca51b756813"}},{"code_sha256_prefix":"4b7502512933d5f0","entry":"compute_dist","repo":"elitalobo/varframework","repo_kind":"official","path":"src/plot_radii.py","file_url":"https://github.com/elitalobo/varframework/blob/HEAD/src/plot_radii.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"4b7502512933d5f0"}},{"code_sha256_prefix":"b50ac088edfdc3dc","entry":"load_initial","repo":"elitalobo/varframework","repo_kind":"official","path":"src/algorithms.py","file_url":"https://github.com/elitalobo/varframework/blob/HEAD/src/algorithms.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"b50ac088edfdc3dc"}},{"code_sha256_prefix":"a6f52c6798c3197c","entry":"validate_bcr","repo":"elitalobo/varframework","repo_kind":"official","path":"src/plot_radii.py","file_url":"https://github.com/elitalobo/varframework/blob/HEAD/src/plot_radii.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"a6f52c6798c3197c"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}