{"id":"https://openalex.org/W4386869676","doi":"https://doi.org/10.1109/tpami.2023.3317131","title":"Offline Model-Based Adaptable Policy Learning for Decision-Making in Out-of-Support Regions","display_name":"Offline Model-Based Adaptable Policy Learning for Decision-Making in Out-of-Support Regions","publication_year":2023,"publication_date":"2023-09-19","ids":{"openalex":"https://openalex.org/W4386869676","doi":"https://doi.org/10.1109/tpami.2023.3317131","pmid":"https://pubmed.ncbi.nlm.nih.gov/37725727"},"language":"en","primary_location":{"id":"doi:10.1109/tpami.2023.3317131","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tpami.2023.3317131","pdf_url":null,"source":{"id":"https://openalex.org/S199944782","display_name":"IEEE Transactions on Pattern Analysis and Machine Intelligence","issn_l":"0162-8828","issn":["0162-8828","1939-3539","2160-9292"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310320439","host_organization_name":"IEEE Computer Society","host_organization_lineage":["https://openalex.org/P4310320439","https://openalex.org/P4310319808"],"host_organization_lineage_names":["IEEE Computer Society","Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Transactions on Pattern Analysis and Machine Intelligence","raw_type":"journal-article"},"type":"article","indexed_in":["crossref","pubmed"],"open_access":{"is_oa":false,"oa_status":"closed","oa_url":null,"any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5019686106","display_name":"Xiong-Hui Chen","orcid":"https://orcid.org/0000-0003-4911-3148"},"institutions":[{"id":"https://openalex.org/I881766915","display_name":"Nanjing University","ror":"https://ror.org/01rxvg760","country_code":"CN","type":"education","lineage":["https://openalex.org/I881766915"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xiong-Hui Chen","raw_affiliation_strings":["National Key Laboratory for Novel Software Technology, Nanjing University, Nanjing, Jiangsu, China"],"raw_orcid":"https://orcid.org/0000-0003-4911-3148","affiliations":[{"raw_affiliation_string":"National Key Laboratory for Novel Software Technology, Nanjing University, Nanjing, Jiangsu, China","institution_ids":["https://openalex.org/I881766915"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5024630977","display_name":"Fan-Ming Luo","orcid":"https://orcid.org/0000-0003-1062-8726"},"institutions":[{"id":"https://openalex.org/I881766915","display_name":"Nanjing University","ror":"https://ror.org/01rxvg760","country_code":"CN","type":"education","lineage":["https://openalex.org/I881766915"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Fan-Ming Luo","raw_affiliation_strings":["National Key Laboratory for Novel Software Technology, Nanjing University, Nanjing, Jiangsu, China"],"raw_orcid":"https://orcid.org/0000-0003-1062-8726","affiliations":[{"raw_affiliation_string":"National Key Laboratory for Novel Software Technology, Nanjing University, Nanjing, Jiangsu, China","institution_ids":["https://openalex.org/I881766915"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100342263","display_name":"Yang Yu","orcid":"https://orcid.org/0000-0002-1732-9545"},"institutions":[{"id":"https://openalex.org/I881766915","display_name":"Nanjing University","ror":"https://ror.org/01rxvg760","country_code":"CN","type":"education","lineage":["https://openalex.org/I881766915"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yang Yu","raw_affiliation_strings":["National Key Laboratory for Novel Software Technology, Nanjing University, Nanjing, Jiangsu, China"],"raw_orcid":"https://orcid.org/0000-0002-1732-9545","affiliations":[{"raw_affiliation_string":"National Key Laboratory for Novel Software Technology, Nanjing University, Nanjing, Jiangsu, China","institution_ids":["https://openalex.org/I881766915"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100700129","display_name":"Qingyang Li","orcid":"https://orcid.org/0000-0001-6650-2343"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Qingyang Li","raw_affiliation_strings":["DiDi Labs, Mountain View, CA, USA"],"raw_orcid":"https://orcid.org/0000-0001-6650-2343","affiliations":[{"raw_affiliation_string":"DiDi Labs, Mountain View, CA, USA","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5085579946","display_name":"Zhiwei Qin","orcid":"https://orcid.org/0000-0001-5383-4816"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Zhiwei Qin","raw_affiliation_strings":["DiDi Labs, Mountain View, CA, USA","Lyft, CA, USA"],"raw_orcid":"https://orcid.org/0000-0001-5383-4816","affiliations":[{"raw_affiliation_string":"DiDi Labs, Mountain View, CA, USA","institution_ids":[]},{"raw_affiliation_string":"Lyft, CA, USA","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5002985691","display_name":"Wenjie Shang","orcid":"https://orcid.org/0000-0002-9331-4062"},"institutions":[{"id":"https://openalex.org/I4401726870","display_name":"Didi Chuxing (China)","ror":"https://ror.org/02ksqcf75","country_code":null,"type":"company","lineage":["https://openalex.org/I4401726870"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Wenjie Shang","raw_affiliation_strings":["DiDi Chuxing, Beijing, China"],"raw_orcid":"https://orcid.org/0000-0002-9331-4062","affiliations":[{"raw_affiliation_string":"DiDi Chuxing, Beijing, China","institution_ids":["https://openalex.org/I4401726870"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5010419481","display_name":"Jieping Ye","orcid":"https://orcid.org/0000-0001-8662-5818"},"institutions":[{"id":"https://openalex.org/I4401726870","display_name":"Didi Chuxing (China)","ror":"https://ror.org/02ksqcf75","country_code":null,"type":"company","lineage":["https://openalex.org/I4401726870"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jieping Ye","raw_affiliation_strings":["DiDi Chuxing, Beijing, China"],"raw_orcid":"https://orcid.org/0000-0001-8662-5818","affiliations":[{"raw_affiliation_string":"DiDi Chuxing, Beijing, China","institution_ids":["https://openalex.org/I4401726870"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.7931,"has_fulltext":false,"cited_by_count":5,"citation_normalized_percentile":{"value":0.76821047,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":97},"biblio":{"volume":"45","issue":"12","first_page":"15260","last_page":"15274"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10462","display_name":"Reinforcement Learning in Robotics","score":0.9990000128746033,"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"}},"topics":[{"id":"https://openalex.org/T10462","display_name":"Reinforcement Learning in Robotics","score":0.9990000128746033,"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/T11704","display_name":"Mobile Crowdsensing and Crowdsourcing","score":0.9740999937057495,"subfield":{"id":"https://openalex.org/subfields/1706","display_name":"Computer Science Applications"},"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/T10653","display_name":"Robot Manipulation and Learning","score":0.9722999930381775,"subfield":{"id":"https://openalex.org/subfields/2207","display_name":"Control and Systems Engineering"},"field":{"id":"https://openalex.org/fields/22","display_name":"Engineering"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/reinforcement-learning","display_name":"Reinforcement learning","score":0.8392536640167236},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.793118953704834},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.7253931760787964},{"id":"https://openalex.org/keywords/robustness","display_name":"Robustness (evolution)","score":0.7214588522911072},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.7153014540672302},{"id":"https://openalex.org/keywords/offline-learning","display_name":"Offline learning","score":0.5815556049346924},{"id":"https://openalex.org/keywords/ensemble-learning","display_name":"Ensemble learning","score":0.5546836853027344},{"id":"https://openalex.org/keywords/decision-tree","display_name":"Decision tree","score":0.42328643798828125},{"id":"https://openalex.org/keywords/outcome","display_name":"Outcome (game theory)","score":0.41559308767318726},{"id":"https://openalex.org/keywords/online-learning","display_name":"Online learning","score":0.27269986271858215}],"concepts":[{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.8392536640167236},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.793118953704834},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.7253931760787964},{"id":"https://openalex.org/C63479239","wikidata":"https://www.wikidata.org/wiki/Q7353546","display_name":"Robustness (evolution)","level":3,"score":0.7214588522911072},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.7153014540672302},{"id":"https://openalex.org/C2780490138","wikidata":"https://www.wikidata.org/wiki/Q7079636","display_name":"Offline learning","level":3,"score":0.5815556049346924},{"id":"https://openalex.org/C45942800","wikidata":"https://www.wikidata.org/wiki/Q245652","display_name":"Ensemble learning","level":2,"score":0.5546836853027344},{"id":"https://openalex.org/C84525736","wikidata":"https://www.wikidata.org/wiki/Q831366","display_name":"Decision tree","level":2,"score":0.42328643798828125},{"id":"https://openalex.org/C148220186","wikidata":"https://www.wikidata.org/wiki/Q7111912","display_name":"Outcome (game theory)","level":2,"score":0.41559308767318726},{"id":"https://openalex.org/C2986087404","wikidata":"https://www.wikidata.org/wiki/Q15946010","display_name":"Online learning","level":2,"score":0.27269986271858215},{"id":"https://openalex.org/C104317684","wikidata":"https://www.wikidata.org/wiki/Q7187","display_name":"Gene","level":2,"score":0.0},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.0},{"id":"https://openalex.org/C136764020","wikidata":"https://www.wikidata.org/wiki/Q466","display_name":"World Wide Web","level":1,"score":0.0},{"id":"https://openalex.org/C144237770","wikidata":"https://www.wikidata.org/wiki/Q747534","display_name":"Mathematical economics","level":1,"score":0.0},{"id":"https://openalex.org/C55493867","wikidata":"https://www.wikidata.org/wiki/Q7094","display_name":"Biochemistry","level":1,"score":0.0},{"id":"https://openalex.org/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","level":0,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/tpami.2023.3317131","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tpami.2023.3317131","pdf_url":null,"source":{"id":"https://openalex.org/S199944782","display_name":"IEEE Transactions on Pattern Analysis and Machine Intelligence","issn_l":"0162-8828","issn":["0162-8828","1939-3539","2160-9292"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310320439","host_organization_name":"IEEE Computer Society","host_organization_lineage":["https://openalex.org/P4310320439","https://openalex.org/P4310319808"],"host_organization_lineage_names":["IEEE Computer Society","Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Transactions on Pattern Analysis and Machine Intelligence","raw_type":"journal-article"},{"id":"pmid:37725727","is_oa":false,"landing_page_url":"https://pubmed.ncbi.nlm.nih.gov/37725727","pdf_url":null,"source":{"id":"https://openalex.org/S4306525036","display_name":"PubMed","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I1299303238","host_organization_name":"National Institutes of Health","host_organization_lineage":["https://openalex.org/I1299303238"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE transactions on pattern analysis and machine intelligence","raw_type":null}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Peace, Justice and strong institutions","id":"https://metadata.un.org/sdg/16","score":0.7900000214576721}],"awards":[{"id":"https://openalex.org/G4366907579","display_name":null,"funder_award_id":"2020AAA0107200","funder_id":"https://openalex.org/F4320335777","funder_display_name":"National Key Research and Development Program of China"},{"id":"https://openalex.org/G528746023","display_name":null,"funder_award_id":"61921006","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"}],"funders":[{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"},{"id":"https://openalex.org/F4320335777","display_name":"National Key Research and Development Program of China","ror":null}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":83,"referenced_works":["https://openalex.org/W41554520","https://openalex.org/W192920577","https://openalex.org/W2064675550","https://openalex.org/W2155027007","https://openalex.org/W2158782408","https://openalex.org/W2158796564","https://openalex.org/W2275802500","https://openalex.org/W2562337727","https://openalex.org/W2578206533","https://openalex.org/W2604763608","https://openalex.org/W2605323209","https://openalex.org/W2736601468","https://openalex.org/W2767050701","https://openalex.org/W2781726626","https://openalex.org/W2784068709","https://openalex.org/W2788295351","https://openalex.org/W2897405591","https://openalex.org/W2904246096","https://openalex.org/W2904453761","https://openalex.org/W2922881794","https://openalex.org/W2947150733","https://openalex.org/W2951625652","https://openalex.org/W2952526277","https://openalex.org/W2962736495","https://openalex.org/W2963614114","https://openalex.org/W2964199361","https://openalex.org/W2971998163","https://openalex.org/W2980555752","https://openalex.org/W2981030070","https://openalex.org/W2991355586","https://openalex.org/W2995706821","https://openalex.org/W3009584650","https://openalex.org/W3016525976","https://openalex.org/W3022566517","https://openalex.org/W3025606523","https://openalex.org/W3028766998","https://openalex.org/W3033324992","https://openalex.org/W3034752558","https://openalex.org/W3039737909","https://openalex.org/W3091897465","https://openalex.org/W3099420497","https://openalex.org/W3101442004","https://openalex.org/W3102778384","https://openalex.org/W3128328080","https://openalex.org/W3132167096","https://openalex.org/W4221158443","https://openalex.org/W4281686999","https://openalex.org/W4282813355","https://openalex.org/W4288319859","https://openalex.org/W4293653493","https://openalex.org/W4322718377","https://openalex.org/W6682968728","https://openalex.org/W6683204974","https://openalex.org/W6694521564","https://openalex.org/W6713893753","https://openalex.org/W6731982132","https://openalex.org/W6736057607","https://openalex.org/W6741002519","https://openalex.org/W6747473740","https://openalex.org/W6757469721","https://openalex.org/W6757592117","https://openalex.org/W6760698134","https://openalex.org/W6760955315","https://openalex.org/W6762613057","https://openalex.org/W6763704811","https://openalex.org/W6764053384","https://openalex.org/W6767406461","https://openalex.org/W6769269530","https://openalex.org/W6771270455","https://openalex.org/W6771886500","https://openalex.org/W6774583691","https://openalex.org/W6776438516","https://openalex.org/W6776601253","https://openalex.org/W6777091672","https://openalex.org/W6777635358","https://openalex.org/W6777656069","https://openalex.org/W6779265984","https://openalex.org/W6790767801","https://openalex.org/W6790864743","https://openalex.org/W6810030924","https://openalex.org/W6838523626","https://openalex.org/W6838635778","https://openalex.org/W6841112233"],"related_works":["https://openalex.org/W4225619808","https://openalex.org/W3136871737","https://openalex.org/W2558685994","https://openalex.org/W4390860632","https://openalex.org/W4388926065","https://openalex.org/W4386160446","https://openalex.org/W4387545330","https://openalex.org/W4226042081","https://openalex.org/W4284974072","https://openalex.org/W4376223516"],"abstract_inverted_index":{"In":[0,57],"reinforcement":[1,19],"learning,":[2,67],"a":[3,111],"promising":[4],"direction":[5],"to":[6,29,38,60],"avoid":[7],"online":[8],"trial-and-error":[9],"costs":[10],"is":[11],"learning":[12,20,90,122],"from":[13],"an":[14,96],"offline":[15,18,34,65,79,132],"dataset.":[16],"Current":[17],"methods":[21],"commonly":[22],"learn":[23,95],"in":[24,36,73,91,104,145],"the":[25,33,40,43,51,54,62,70,138],"policy":[26,66,98],"space":[27],"constrained":[28],"in-support":[30,92],"regions":[31,75,106,147],"by":[32],"dataset,":[35],"order":[37],"ensure":[39],"robustness":[41],"of":[42,53,64,89,114],"outcome":[44,55],"policies.":[45,56],"Such":[46],"constraints,":[47],"however,":[48],"also":[49],"limit":[50],"potential":[52,63],"this":[58,86],"paper,":[59],"release":[61],"we":[68,94],"investigate":[69],"decision-making":[71],"problems":[72],"out-of-support":[74,105,146],"directly":[76],"and":[77,119,148],"propose":[78],"Model-based":[80],"Adaptable":[81],"Policy":[82],"LEarning":[83],"(MAPLE).":[84],"By":[85],"approach,":[87],"instead":[88],"regions,":[93],"adaptable":[97],"that":[99,137],"can":[100,141],"adapt":[101],"its":[102],"behavior":[103],"when":[107],"deployed.":[108],"We":[109,124],"give":[110],"practical":[112],"implementation":[113],"MAPLE":[115],"via":[116],"meta-learning":[117],"techniques":[118],"ensemble":[120],"model":[121],"techniques.":[123],"conduct":[125],"experiments":[126],"on":[127],"MuJoCo":[128],"locomotion":[129],"tasks":[130],"with":[131],"datasets.":[133],"The":[134],"results":[135],"show":[136],"proposed":[139],"method":[140],"make":[142],"robust":[143],"decisions":[144],"achieve":[149],"better":[150],"performance":[151],"than":[152],"SOTA":[153],"algorithms.":[154]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":3},{"year":2024,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}