{"id":"https://openalex.org/W4414989407","doi":"https://doi.org/10.1080/01621459.2026.2755097","title":"POLAR: A Pessimistic Model-based Policy Learning Algorithm for Dynamic Treatment Regimes","display_name":"POLAR: A Pessimistic Model-based Policy Learning Algorithm for Dynamic Treatment Regimes","publication_year":2026,"publication_date":"2026-10-27","ids":{"openalex":"https://openalex.org/W4414989407","doi":"https://doi.org/10.1080/01621459.2026.2755097"},"language":"en","primary_location":{"id":"doi:10.1080/01621459.2026.2755097","doi":"https://doi.org/10.1080/01621459.2026.2755097","is_oa":false,"landing_page_url":"https://doi.org/10.1080/01621459.2026.2755097","pdf_url":null,"source":{"id":"https://openalex.org/S4394736638","display_name":"Journal of the American Statistical Association","issn_l":"0162-1459","issn":["0162-1459","1537-274X"],"is_oa":false,"is_in_doaj":false,"is_core":true,"listed_in":["abdc-a-star","anvur-class-a","anvur-scientific","cwts-core","dongbi-a","doyens","jufo-3","ki-jl-3","norway-2","poland-200","russia-white-list-1","vabb-shw"],"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Journal of the American Statistical Association","raw_type":"journal-article"},"volume":null,"type":"article","indexed_in":["arxiv","crossref","datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2506.20406","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5103109423","display_name":"Ruijia Zhang","orcid":"https://orcid.org/0009-0006-8174-618X","observed_orcids":["https://orcid.org/0009-0006-8174-618X"]},"institutions":[{"id":"https://openalex.org/I145311948","display_name":"Johns Hopkins University","ror":"https://ror.org/00za53h95","country_code":"US","type":"education","lineage":["https://openalex.org/I145311948"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Ruijia Zhang","raw_affiliation_strings":["Department of Applied Mathematics and Statistics, Johns Hopkins University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Applied Mathematics and Statistics, Johns Hopkins University","institution_ids":["https://openalex.org/I145311948"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5103546218","display_name":"Xiangyu Zhang","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I145311948","display_name":"Johns Hopkins University","ror":"https://ror.org/00za53h95","country_code":"US","type":"education","lineage":["https://openalex.org/I145311948"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Xiangyu Zhang","raw_affiliation_strings":["Department of Applied Mathematics and Statistics, Johns Hopkins University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Applied Mathematics and Statistics, Johns Hopkins University","institution_ids":["https://openalex.org/I145311948"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5078483423","display_name":"Zhengling Qi","orcid":"https://orcid.org/0000-0003-0270-7969","observed_orcids":["https://orcid.org/0000-0003-0270-7969"]},"institutions":[{"id":"https://openalex.org/I193531525","display_name":"George Washington University","ror":"https://ror.org/00y4zzh67","country_code":"US","type":"education","lineage":["https://openalex.org/I193531525"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Zhengling Qi","raw_affiliation_strings":["School of Business, The George Washington University"],"raw_orcid":"https://orcid.org/0000-0003-0270-7969","affiliations":[{"raw_affiliation_string":"School of Business, The George Washington University","institution_ids":["https://openalex.org/I193531525"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100668826","display_name":"Yue Wu","orcid":"https://orcid.org/0000-0003-0126-3614","observed_orcids":["https://orcid.org/0000-0003-0126-3614"]},"institutions":[{"id":"https://openalex.org/I145311948","display_name":"Johns Hopkins University","ror":"https://ror.org/00za53h95","country_code":"US","type":"education","lineage":["https://openalex.org/I145311948"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Yue Wu","raw_affiliation_strings":["Department of Applied Mathematics and Statistics, Johns Hopkins University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Applied Mathematics and Statistics, Johns Hopkins University","institution_ids":["https://openalex.org/I145311948"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5056825063","display_name":"Yanxun Xu","orcid":"https://orcid.org/0000-0001-5554-8637","observed_orcids":["https://orcid.org/0000-0001-5554-8637"]},"institutions":[{"id":"https://openalex.org/I145311948","display_name":"Johns Hopkins University","ror":"https://ror.org/00za53h95","country_code":"US","type":"education","lineage":["https://openalex.org/I145311948"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Yanxun Xu","raw_affiliation_strings":["Department of Applied Mathematics and Statistics, Johns Hopkins University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Applied Mathematics and Statistics, Johns Hopkins University","institution_ids":["https://openalex.org/I145311948"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5056825063"],"corresponding_institution_ids":["https://openalex.org/I145311948"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":true,"cited_by_count":0,"citation_normalized_percentile":{"value":0.02922364,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"67"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10845","display_name":"Advanced Causal Inference Techniques","score":0.7559000253677368,"subfield":{"id":"https://openalex.org/subfields/2613","display_name":"Statistics and Probability"},"field":{"id":"https://openalex.org/fields/26","display_name":"Mathematics"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},"topics":[{"id":"https://openalex.org/T10845","display_name":"Advanced Causal Inference Techniques","score":0.7559000253677368,"subfield":{"id":"https://openalex.org/subfields/2613","display_name":"Statistics and Probability"},"field":{"id":"https://openalex.org/fields/26","display_name":"Mathematics"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T10462","display_name":"Reinforcement Learning in Robotics","score":0.13050000369548798,"subfield":{"id":"https://openalex.org/subfields/1702","display_name":"Artificial Intelligence"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T12101","display_name":"Advanced Bandit Algorithms Research","score":0.06109999865293503,"subfield":{"id":"https://openalex.org/subfields/1803","display_name":"Management Science and Operations Research"},"field":{"id":"https://openalex.org/fields/18","display_name":"Decision Sciences"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/dynamic-treatment-regimes","display_name":"dynamic treatment regimes","score":0.9980000257492065},{"id":"https://openalex.org/keywords/offline-reinforcement-learning","display_name":"offline reinforcement learning","score":0.8730000257492065},{"id":"https://openalex.org/keywords/uncertainty-quantification","display_name":"uncertainty quantification","score":0.6949999928474426},{"id":"https://openalex.org/keywords/nonasymptotic-bounds","display_name":"non-asymptotic bounds","score":0.9279999732971191},{"id":"https://openalex.org/keywords/sequential-decision-making","display_name":"sequential decision making","score":0.6769999861717224},{"id":"https://openalex.org/keywords/mimic-iii","display_name":"MIMIC-III","score":0.8849999904632568}],"concepts":[{"id":"https://openalex.org/C9992130","wikidata":"https://www.wikidata.org/wiki/Q484954","display_name":"Pessimism","level":2,"score":0.6757000088691711},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6717000007629395},{"id":"https://openalex.org/C63479239","wikidata":"https://www.wikidata.org/wiki/Q7353546","display_name":"Robustness (evolution)","level":3,"score":0.6107000112533569},{"id":"https://openalex.org/C55166926","wikidata":"https://www.wikidata.org/wiki/Q2892946","display_name":"Oracle","level":2,"score":0.5454999804496765},{"id":"https://openalex.org/C149728462","wikidata":"https://www.wikidata.org/wiki/Q751319","display_name":"Minimax","level":2,"score":0.5454000234603882},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.4934999942779541},{"id":"https://openalex.org/C192209626","wikidata":"https://www.wikidata.org/wiki/Q190909","display_name":"Focus (optics)","level":2,"score":0.48570001125335693},{"id":"https://openalex.org/C126255220","wikidata":"https://www.wikidata.org/wiki/Q141495","display_name":"Mathematical optimization","level":1,"score":0.4327999949455261},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4187999963760376},{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.40790000557899475},{"id":"https://openalex.org/C14036430","wikidata":"https://www.wikidata.org/wiki/Q3736076","display_name":"Function (biology)","level":2,"score":0.34150001406669617},{"id":"https://openalex.org/C2982736386","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Statistical learning","level":2,"score":0.32280001044273376},{"id":"https://openalex.org/C114289077","wikidata":"https://www.wikidata.org/wiki/Q3284399","display_name":"Statistical model","level":2,"score":0.3224000036716461},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.3093000054359436},{"id":"https://openalex.org/C45942800","wikidata":"https://www.wikidata.org/wiki/Q245652","display_name":"Ensemble learning","level":2,"score":0.29120001196861267},{"id":"https://openalex.org/C106301342","wikidata":"https://www.wikidata.org/wiki/Q4117933","display_name":"Entropy (arrow of time)","level":2,"score":0.2858000099658966},{"id":"https://openalex.org/C120936955","wikidata":"https://www.wikidata.org/wiki/Q2155640","display_name":"Empirical research","level":2,"score":0.2827000021934509},{"id":"https://openalex.org/C46686674","wikidata":"https://www.wikidata.org/wiki/Q466303","display_name":"Boosting (machine learning)","level":2,"score":0.28029999136924744},{"id":"https://openalex.org/C51632099","wikidata":"https://www.wikidata.org/wiki/Q3985153","display_name":"Training set","level":2,"score":0.2524999976158142},{"id":"https://openalex.org/C160920958","wikidata":"https://www.wikidata.org/wiki/Q7662746","display_name":"Synthetic data","level":2,"score":0.251800000667572}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.1080/01621459.2026.2755097","doi":"https://doi.org/10.1080/01621459.2026.2755097","is_oa":false,"landing_page_url":"https://doi.org/10.1080/01621459.2026.2755097","pdf_url":null,"source":{"id":"https://openalex.org/S4394736638","display_name":"Journal of the American Statistical Association","issn_l":"0162-1459","issn":["0162-1459","1537-274X"],"is_oa":false,"is_in_doaj":false,"is_core":true,"listed_in":["abdc-a-star","anvur-class-a","anvur-scientific","cwts-core","dongbi-a","doyens","jufo-3","ki-jl-3","norway-2","poland-200","russia-white-list-1","vabb-shw"],"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Journal of the American Statistical Association","raw_type":"journal-article"},{"id":"pmh:oai:arXiv.org:2506.20406","doi":null,"is_oa":true,"landing_page_url":"http://arxiv.org/abs/2506.20406","pdf_url":"https://arxiv.org/pdf/2506.20406","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},{"id":"doi:10.48550/arxiv.2506.20406","doi":"https://doi.org/10.48550/arxiv.2506.20406","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2506.20406","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":null,"is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Preprint"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2506.20406","doi":null,"is_oa":true,"landing_page_url":"http://arxiv.org/abs/2506.20406","pdf_url":"https://arxiv.org/pdf/2506.20406","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},"sustainable_development_goals":[],"study_designs":[],"awards":[],"funders":[],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4414989407.pdf","grobid_xml":"https://content.openalex.org/works/W4414989407.grobid-xml"},"referenced_works_count":0,"referenced_works":[],"related_works":["https://openalex.org/W4410732767","https://openalex.org/W2970315086","https://openalex.org/W4399197872","https://openalex.org/W4293483658","https://openalex.org/W2561141779","https://openalex.org/W7125822737","https://openalex.org/W4301057187","https://openalex.org/W4226435540","https://openalex.org/W7103547840","https://openalex.org/W7084026155"],"abstract_inverted_index":{"Dynamic":[0],"treatment":[1,206],"regimes":[2],"(DTRs)":[3],"provide":[4,129,174],"a":[5,76],"principled":[6],"framework":[7],"for":[8,83,98,132],"optimizing":[9],"sequential":[10],"decision-making":[11],"in":[12,20],"domains":[13],"where":[14],"decisions":[15],"must":[16],"adapt":[17],"over":[18],"time":[19],"response":[21],"to":[22,112,173],"individual":[23],"trajectories,":[24],"such":[25],"as":[26],"healthcare,":[27],"education,":[28],"and":[29,42,63,95,146,177,192,202],"digital":[30],"interventions.":[31],"However,":[32],"existing":[33,120],"statistical":[34,61,176],"methods":[35,121,201],"often":[36],"rely":[37],"on":[38,56,124,152,183,188],"strong":[39],"positivity":[40],"assumptions":[41],"lack":[43,60],"robustness":[44],"under":[45],"partial":[46],"data":[47,94,191],"coverage,":[48],"while":[49],"offline":[50,84,93],"reinforcement":[51],"learning":[52,81],"approaches":[53],"typically":[54],"focus":[55,123],"average":[57,125],"training":[58,126],"performance,":[59],"guarantees,":[62,149,179],"require":[64],"solving":[65],"complex":[66],"optimization":[67,158],"problems.":[68],"To":[69,160],"address":[70],"these":[71],"challenges,":[72],"we":[73],"propose":[74],"POLAR,":[75],"novel":[77],"pessimistic":[78,103],"model-based":[79,170],"policy":[80,145,184],"algorithm":[82],"DTR":[85,171],"optimization.":[86],"POLAR":[87,136,166,198],"estimates":[88],"the":[89,109,139,142,161,168,193],"transition":[90],"dynamics":[91],"from":[92],"quantifies":[96],"uncertainty":[97],"each":[99],"history-action":[100],"pair.":[101],"A":[102],"penalty":[104],"is":[105,167],"then":[106],"incorporated":[107],"into":[108],"reward":[110],"function":[111],"discourage":[113],"actions":[114],"with":[115],"high":[116],"uncertainty.":[117],"Unlike":[118],"many":[119],"that":[122,197],"performance":[127],"or":[128,156],"guarantees":[130],"only":[131],"an":[133],"oracle":[134],"policy,":[135],"directly":[137],"targets":[138],"suboptimality":[140],"of":[141,163],"final":[143],"learned":[144],"offers":[147],"theoretical":[148],"without":[150],"relying":[151],"computationally":[153],"intensive":[154],"minimax":[155],"constrained":[157],"procedures.":[159],"best":[162],"our":[164],"knowledge,":[165],"first":[169],"method":[172],"both":[175,189],"computational":[178],"including":[180],"finite-sample":[181],"bounds":[182],"suboptimality.":[185],"Empirical":[186],"results":[187],"synthetic":[190],"MIMIC-III":[194],"dataset":[195],"demonstrate":[196],"outperforms":[199],"state-of-the-art":[200],"yields":[203],"near-optimal,":[204],"history-aware":[205],"strategies.":[207]},"counts_by_year":[],"updated_date":"2026-11-04T10:54:05.112534","created_date":"2025-10-09T00:00:00"}