{"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/representation-balancing-mdps-for-off-policy","title":"Representation Balancing MDPs for Off-Policy Policy Evaluation","arxiv_id":"1805.09044","date":"2018-05-23","proceeding":"NeurIPS 2018 12","authors":["Yao Liu","Omer Gottesman","Aniruddh Raghu","Matthieu Komorowski","Aldo Faisal","Finale Doshi-Velez","Emma Brunskill"],"abstract":"We study the problem of off-policy policy evaluation (OPPE) in RL. In\ncontrast to prior work, we consider how to estimate both the individual policy\nvalue and average policy value accurately. We draw inspiration from recent work\nin causal reasoning, and propose a new finite sample generalization error bound\nfor value estimates from MDP models. Using this upper bound as an objective, we\ndevelop a learning algorithm of an MDP model with a balanced representation,\nand show that our approach can yield substantially lower MSE in common\nsynthetic benchmarks and a HIV treatment simulation domain.","url_abs":"http://arxiv.org/abs/1805.09044v4","url_pdf":"http://arxiv.org/pdf/1805.09044v4.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":"representation-balancing-mdps-for-off-policy","repo_url":"https://github.com/stanfordai4hi/repbm","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":null}],"tasks":[],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"syntology_url":null,"atlas_url":"https://app.syntology.ai/?focus=1805.09044","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1805.09044"}},"developers":"https://syntology.ai/developers","read_at":"2026-09-24T18:15:14+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/stanfordai4hi/repbm","reach":null}],"summary":{"ran_honours":1,"ran_draft_wrong":1,"ran_fixture":1},"by_repo_kind":{"listed":{"samples":3,"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":"e306e4c17f92b539","entry":"epsilon_decay_per_ep","repo":"stanfordai4hi/repbm","repo_kind":"listed","path":"qlearning_cartpole.py","file_url":"https://github.com/stanfordai4hi/repbm/blob/HEAD/qlearning_cartpole.py","link_basis":"first_harvest_node","language":"python","status":"ran_honours","verification_level":1,"contract_check":"HONOURS","metamorphic_tier":"well_formed","behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"e306e4c17f92b539"}},{"code_sha256_prefix":"39cd30a78d9b6b86","entry":"preprocess_state","repo":"stanfordai4hi/repbm","repo_kind":"listed","path":"qlearning_cartpole.py","file_url":"https://github.com/stanfordai4hi/repbm/blob/HEAD/qlearning_cartpole.py","link_basis":"first_harvest_node","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"MISDECLARED","metamorphic_tier":"invariant","behaviour_fingerprint":true,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"39cd30a78d9b6b86"}},{"code_sha256_prefix":"a1999e91696fab13","entry":"select_action","repo":"stanfordai4hi/repbm","repo_kind":"listed","path":"qlearning_cartpole.py","file_url":"https://github.com/stanfordai4hi/repbm/blob/HEAD/qlearning_cartpole.py","link_basis":"first_harvest_node","language":"python","status":"ran_fixture","verification_level":1,"contract_check":"RAISES","metamorphic_tier":"invariant","behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"a1999e91696fab13"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}