{"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/does-the-markov-decision-process-fit-the-data","title":"Does the Markov Decision Process Fit the Data: Testing for the Markov Property in Sequential Decision Making","arxiv_id":"2002.01751","date":"2020-02-05","proceeding":"ICML 2020 1","authors":["Chengchun Shi","Runzhe Wan","Rui Song","Wenbin Lu","Ling Leng"],"abstract":"The Markov assumption (MA) is fundamental to the empirical validity of reinforcement learning. In this paper, we propose a novel Forward-Backward Learning procedure to test MA in sequential decision making. The proposed test does not assume any parametric form on the joint distribution of the observed data and plays an important role for identifying the optimal policy in high-order Markov decision processes and partially observable MDPs. We apply our test to both synthetic datasets and a real data example from mobile health studies to illustrate its usefulness.","url_abs":"https://arxiv.org/abs/2002.01751v1","url_pdf":"https://arxiv.org/pdf/2002.01751v1.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":"does-the-markov-decision-process-fit-the-data","repo_url":"https://github.com/RunzheStat/TestMDP","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"none","reach":null}],"tasks":[{"task_slug":"decision-making","task_name":"Decision Making"},{"task_slug":"reinforcement-learning","task_name":"Reinforcement Learning"},{"task_slug":"reinforcement-learning-1","task_name":"Reinforcement Learning (RL)"},{"task_slug":"sequential-decision-making","task_name":"Sequential Decision Making"},{"task_slug":"reinforcement-learning-2","task_name":"reinforcement-learning"}],"methods":[{"method_slug":"test","method_name":"Test"}],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=2002.01751","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2002.01751"}},"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/RunzheStat/TestMDP","reach":null}],"summary":{"unverified":4},"by_repo_kind":{"listed":{"samples":4,"ran":0,"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":"d15f037727d014f5","entry":"get_pairs","repo":"RunzheStat/TestMDP","repo_kind":"listed","path":"test_func/_core_test_fun.py","file_url":"https://github.com/RunzheStat/TestMDP/blob/HEAD/test_func/_core_test_fun.py","link_basis":"first_harvest_node","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":"d15f037727d014f5"}},{"code_sha256_prefix":"03c2d4ff2a81da34","entry":"one_setting_mul_J","repo":"RunzheStat/TestMDP","repo_kind":"listed","path":"experiment_script/Ohio_simu_testing.py","file_url":"https://github.com/RunzheStat/TestMDP/blob/HEAD/experiment_script/Ohio_simu_testing.py","link_basis":"first_harvest_node","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":"03c2d4ff2a81da34"}},{"code_sha256_prefix":"29016d8ed810736c","entry":"one_setting_one_J","repo":"RunzheStat/TestMDP","repo_kind":"listed","path":"experiment_script/Ohio_simu_testing.py","file_url":"https://github.com/RunzheStat/TestMDP/blob/HEAD/experiment_script/Ohio_simu_testing.py","link_basis":"first_harvest_node","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":"29016d8ed810736c"}},{"code_sha256_prefix":"634275003852fbe1","entry":"one_time","repo":"RunzheStat/TestMDP","repo_kind":"listed","path":"experiment_script/Ohio_simu_testing.py","file_url":"https://github.com/RunzheStat/TestMDP/blob/HEAD/experiment_script/Ohio_simu_testing.py","link_basis":"first_harvest_node","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":"634275003852fbe1"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}