{"id":"https://openalex.org/W4382239152","doi":"https://doi.org/10.1609/aaai.v37i6.25903","title":"Model-Based Offline Reinforcement Learning with Local Misspecification","display_name":"Model-Based Offline Reinforcement Learning with Local Misspecification","publication_year":2023,"publication_date":"2023-06-26","ids":{"openalex":"https://openalex.org/W4382239152","doi":"https://doi.org/10.1609/aaai.v37i6.25903"},"language":"en","primary_location":{"id":"doi:10.1609/aaai.v37i6.25903","is_oa":true,"landing_page_url":"http://dx.doi.org/10.1609/aaai.v37i6.25903","pdf_url":"https://ojs.aaai.org/index.php/AAAI/article/download/25903/25675","source":{"id":"https://openalex.org/S4210191458","display_name":"Proceedings of the AAAI Conference on Artificial Intelligence","issn_l":"2159-5399","issn":["2159-5399","2374-3468"],"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/P4310320058","host_organization_name":"Association for the Advancement of Artificial Intelligence","host_organization_lineage":["https://openalex.org/P4310320058"],"host_organization_lineage_names":["Association for the Advancement of Artificial Intelligence"],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the AAAI Conference on Artificial Intelligence","raw_type":"journal-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"diamond","oa_url":"https://ojs.aaai.org/index.php/AAAI/article/download/25903/25675","any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5047803614","display_name":"Kefan Dong","orcid":null},"institutions":[{"id":"https://openalex.org/I97018004","display_name":"Stanford University","ror":"https://ror.org/00f54p054","country_code":"US","type":"education","lineage":["https://openalex.org/I97018004"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Kefan Dong","raw_affiliation_strings":["Stanford University"],"affiliations":[{"raw_affiliation_string":"Stanford University","institution_ids":["https://openalex.org/I97018004"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5045192384","display_name":"Yannis Flet-Berliac","orcid":null},"institutions":[{"id":"https://openalex.org/I97018004","display_name":"Stanford University","ror":"https://ror.org/00f54p054","country_code":"US","type":"education","lineage":["https://openalex.org/I97018004"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Yannis Flet-Berliac","raw_affiliation_strings":["Stanford University"],"affiliations":[{"raw_affiliation_string":"Stanford University","institution_ids":["https://openalex.org/I97018004"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5018535992","display_name":"Allen Nie","orcid":"https://orcid.org/0000-0001-6483-2111"},"institutions":[{"id":"https://openalex.org/I97018004","display_name":"Stanford University","ror":"https://ror.org/00f54p054","country_code":"US","type":"education","lineage":["https://openalex.org/I97018004"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Allen Nie","raw_affiliation_strings":["Stanford University"],"affiliations":[{"raw_affiliation_string":"Stanford University","institution_ids":["https://openalex.org/I97018004"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5084989076","display_name":"Emma Brunskill","orcid":"https://orcid.org/0000-0002-3971-7127"},"institutions":[{"id":"https://openalex.org/I97018004","display_name":"Stanford University","ror":"https://ror.org/00f54p054","country_code":"US","type":"education","lineage":["https://openalex.org/I97018004"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Emma Brunskill","raw_affiliation_strings":["Stanford University"],"affiliations":[{"raw_affiliation_string":"Stanford University","institution_ids":["https://openalex.org/I97018004"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5047803614"],"corresponding_institution_ids":["https://openalex.org/I97018004"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":true,"cited_by_count":0,"citation_normalized_percentile":{"value":0.07680412,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":"37","issue":"6","first_page":"7423","last_page":"7431"},"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/T10603","display_name":"Smart Grid Energy Management","score":0.9498000144958496,"subfield":{"id":"https://openalex.org/subfields/2208","display_name":"Electrical and Electronic Engineering"},"field":{"id":"https://openalex.org/fields/22","display_name":"Engineering"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T12101","display_name":"Advanced Bandit Algorithms Research","score":0.9135000109672546,"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/reinforcement-learning","display_name":"Reinforcement learning","score":0.8487637042999268},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6546614766120911},{"id":"https://openalex.org/keywords/bellman-equation","display_name":"Bellman equation","score":0.5941272377967834},{"id":"https://openalex.org/keywords/key","display_name":"Key (lock)","score":0.546967625617981},{"id":"https://openalex.org/keywords/pessimism","display_name":"Pessimism","score":0.5435717701911926},{"id":"https://openalex.org/keywords/set","display_name":"Set (abstract data type)","score":0.5385199189186096},{"id":"https://openalex.org/keywords/function","display_name":"Function (biology)","score":0.5257307291030884},{"id":"https://openalex.org/keywords/upper-and-lower-bounds","display_name":"Upper and lower bounds","score":0.5210694074630737},{"id":"https://openalex.org/keywords/selection","display_name":"Selection (genetic algorithm)","score":0.514628529548645},{"id":"https://openalex.org/keywords/value","display_name":"Value (mathematics)","score":0.467422217130661},{"id":"https://openalex.org/keywords/dynamics","display_name":"Dynamics (music)","score":0.46303021907806396},{"id":"https://openalex.org/keywords/action-selection","display_name":"Action selection","score":0.4481019675731659},{"id":"https://openalex.org/keywords/q-learning","display_name":"Q-learning","score":0.4258875846862793},{"id":"https://openalex.org/keywords/mathematical-optimization","display_name":"Mathematical optimization","score":0.36938196420669556},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.3217635750770569},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.2650715112686157},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.24752816557884216}],"concepts":[{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.8487637042999268},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6546614766120911},{"id":"https://openalex.org/C14646407","wikidata":"https://www.wikidata.org/wiki/Q1430750","display_name":"Bellman equation","level":2,"score":0.5941272377967834},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.546967625617981},{"id":"https://openalex.org/C9992130","wikidata":"https://www.wikidata.org/wiki/Q484954","display_name":"Pessimism","level":2,"score":0.5435717701911926},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.5385199189186096},{"id":"https://openalex.org/C14036430","wikidata":"https://www.wikidata.org/wiki/Q3736076","display_name":"Function (biology)","level":2,"score":0.5257307291030884},{"id":"https://openalex.org/C77553402","wikidata":"https://www.wikidata.org/wiki/Q13222579","display_name":"Upper and lower bounds","level":2,"score":0.5210694074630737},{"id":"https://openalex.org/C81917197","wikidata":"https://www.wikidata.org/wiki/Q628760","display_name":"Selection (genetic algorithm)","level":2,"score":0.514628529548645},{"id":"https://openalex.org/C2776291640","wikidata":"https://www.wikidata.org/wiki/Q2912517","display_name":"Value (mathematics)","level":2,"score":0.467422217130661},{"id":"https://openalex.org/C145912823","wikidata":"https://www.wikidata.org/wiki/Q113558","display_name":"Dynamics (music)","level":2,"score":0.46303021907806396},{"id":"https://openalex.org/C166109690","wikidata":"https://www.wikidata.org/wiki/Q4677422","display_name":"Action selection","level":3,"score":0.4481019675731659},{"id":"https://openalex.org/C188116033","wikidata":"https://www.wikidata.org/wiki/Q2664563","display_name":"Q-learning","level":3,"score":0.4258875846862793},{"id":"https://openalex.org/C126255220","wikidata":"https://www.wikidata.org/wiki/Q141495","display_name":"Mathematical optimization","level":1,"score":0.36938196420669556},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3217635750770569},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.2650715112686157},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.24752816557884216},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.0},{"id":"https://openalex.org/C134306372","wikidata":"https://www.wikidata.org/wiki/Q7754","display_name":"Mathematical analysis","level":1,"score":0.0},{"id":"https://openalex.org/C169760540","wikidata":"https://www.wikidata.org/wiki/Q207011","display_name":"Neuroscience","level":1,"score":0.0},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.0},{"id":"https://openalex.org/C24890656","wikidata":"https://www.wikidata.org/wiki/Q82811","display_name":"Acoustics","level":1,"score":0.0},{"id":"https://openalex.org/C111472728","wikidata":"https://www.wikidata.org/wiki/Q9471","display_name":"Epistemology","level":1,"score":0.0},{"id":"https://openalex.org/C26760741","wikidata":"https://www.wikidata.org/wiki/Q160402","display_name":"Perception","level":2,"score":0.0},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0},{"id":"https://openalex.org/C38652104","wikidata":"https://www.wikidata.org/wiki/Q3510521","display_name":"Computer security","level":1,"score":0.0},{"id":"https://openalex.org/C78458016","wikidata":"https://www.wikidata.org/wiki/Q840400","display_name":"Evolutionary biology","level":1,"score":0.0},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1609/aaai.v37i6.25903","is_oa":true,"landing_page_url":"http://dx.doi.org/10.1609/aaai.v37i6.25903","pdf_url":"https://ojs.aaai.org/index.php/AAAI/article/download/25903/25675","source":{"id":"https://openalex.org/S4210191458","display_name":"Proceedings of the AAAI Conference on Artificial Intelligence","issn_l":"2159-5399","issn":["2159-5399","2374-3468"],"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/P4310320058","host_organization_name":"Association for the Advancement of Artificial Intelligence","host_organization_lineage":["https://openalex.org/P4310320058"],"host_organization_lineage_names":["Association for the Advancement of Artificial Intelligence"],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the AAAI Conference on Artificial Intelligence","raw_type":"journal-article"}],"best_oa_location":{"id":"doi:10.1609/aaai.v37i6.25903","is_oa":true,"landing_page_url":"http://dx.doi.org/10.1609/aaai.v37i6.25903","pdf_url":"https://ojs.aaai.org/index.php/AAAI/article/download/25903/25675","source":{"id":"https://openalex.org/S4210191458","display_name":"Proceedings of the AAAI Conference on Artificial Intelligence","issn_l":"2159-5399","issn":["2159-5399","2374-3468"],"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/P4310320058","host_organization_name":"Association for the Advancement of Artificial Intelligence","host_organization_lineage":["https://openalex.org/P4310320058"],"host_organization_lineage_names":["Association for the Advancement of Artificial Intelligence"],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the AAAI Conference on Artificial Intelligence","raw_type":"journal-article"},"sustainable_development_goals":[{"score":0.6100000143051147,"id":"https://metadata.un.org/sdg/16","display_name":"Peace, Justice and strong institutions"}],"awards":[{"id":"https://openalex.org/G1034401897","display_name":null,"funder_award_id":"W911NF-17-2-0196","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"},{"id":"https://openalex.org/G1637379582","display_name":null,"funder_award_id":"W911NF-17-2-0196","funder_id":"https://openalex.org/F4320338295","funder_display_name":"Army Research Laboratory"},{"id":"https://openalex.org/G4759515801","display_name":null,"funder_award_id":"W911NF-17-2-0196","funder_id":"https://openalex.org/F4320338456","funder_display_name":"DEVCOM Army Research Laboratory"},{"id":"https://openalex.org/G5259331294","display_name":null,"funder_award_id":"W911NF","funder_id":"https://openalex.org/F4320338295","funder_display_name":"Army Research Laboratory"},{"id":"https://openalex.org/G6186404519","display_name":"RI: Small: Using and Gathering Data for Efficient Batch Reinforcement Learning","funder_award_id":"2112926","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"}],"funders":[{"id":"https://openalex.org/F4320306076","display_name":"National Science Foundation","ror":"https://ror.org/021nxhr62"},{"id":"https://openalex.org/F4320337807","display_name":"U.S. Army Combat Capabilities Development Command","ror":null},{"id":"https://openalex.org/F4320338295","display_name":"Army Research Laboratory","ror":"https://ror.org/011hc8f90"},{"id":"https://openalex.org/F4320338456","display_name":"DEVCOM Army Research Laboratory","ror":null}],"has_content":{"grobid_xml":false,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4382239152.pdf"},"referenced_works_count":66,"referenced_works":["https://openalex.org/W1191599655","https://openalex.org/W1575592356","https://openalex.org/W1730555343","https://openalex.org/W1835900096","https://openalex.org/W1931027396","https://openalex.org/W2098432798","https://openalex.org/W2128812357","https://openalex.org/W2605323209","https://openalex.org/W2626747984","https://openalex.org/W2781726626","https://openalex.org/W2787938642","https://openalex.org/W2788575380","https://openalex.org/W2804152667","https://openalex.org/W2890022552","https://openalex.org/W2942709080","https://openalex.org/W2944847804","https://openalex.org/W2947150733","https://openalex.org/W2948210913","https://openalex.org/W2948416696","https://openalex.org/W2951466561","https://openalex.org/W2951470703","https://openalex.org/W2952295663","https://openalex.org/W2952867909","https://openalex.org/W2959895084","https://openalex.org/W2962734844","https://openalex.org/W2962759351","https://openalex.org/W2969337892","https://openalex.org/W2981182167","https://openalex.org/W2981972696","https://openalex.org/W2991598122","https://openalex.org/W2992035660","https://openalex.org/W2994798986","https://openalex.org/W3003404538","https://openalex.org/W3003587309","https://openalex.org/W3005407492","https://openalex.org/W3016525976","https://openalex.org/W3025606523","https://openalex.org/W3028766998","https://openalex.org/W3033324992","https://openalex.org/W3034084488","https://openalex.org/W3034525128","https://openalex.org/W3035203794","https://openalex.org/W3035634530","https://openalex.org/W3037792667","https://openalex.org/W3046395471","https://openalex.org/W3048911479","https://openalex.org/W3097907450","https://openalex.org/W3103383763","https://openalex.org/W3130158566","https://openalex.org/W3150807214","https://openalex.org/W3178225342","https://openalex.org/W3197485521","https://openalex.org/W3199265017","https://openalex.org/W3201700917","https://openalex.org/W4283819375","https://openalex.org/W4286965539","https://openalex.org/W4287018575","https://openalex.org/W4287689949","https://openalex.org/W4287714048","https://openalex.org/W4287756978","https://openalex.org/W4288335419","https://openalex.org/W4294620504","https://openalex.org/W4301430420","https://openalex.org/W6637597983","https://openalex.org/W6640490175","https://openalex.org/W6791380809"],"related_works":["https://openalex.org/W2015051472","https://openalex.org/W2386410636","https://openalex.org/W2168501056","https://openalex.org/W3038962357","https://openalex.org/W2120009678","https://openalex.org/W3096874164","https://openalex.org/W2166117066","https://openalex.org/W4376605461","https://openalex.org/W2357975469","https://openalex.org/W2025663273"],"abstract_inverted_index":{"We":[0,92],"present":[1],"a":[2,34,64,78,114],"model-based":[3],"offline":[4,28],"reinforcement":[5],"learning":[6],"policy":[7,29,37,111],"performance":[8,105],"lower":[9,95,108],"bound":[10,96],"that":[11,89],"explicitly":[12],"captures":[13],"dynamics":[14,57,65,71],"model":[15,66],"misspecification":[16],"and":[17,20,59,101],"distribution":[18],"mismatch":[19],"we":[21,32],"propose":[22],"an":[23],"empirical":[24],"algorithm":[25],"for":[26],"optimal":[27],"selection.":[30],"Theoretically,":[31],"prove":[33],"novel":[35],"safe":[36],"improvement":[38],"theorem":[39],"by":[40,77],"establishing":[41],"pessimism":[42],"approximations":[43],"to":[44,52,84,106],"the":[45,70,73,86,98],"value":[46,87],"function.":[47],"Our":[48],"key":[49],"insight":[50],"is":[51,82],"jointly":[53],"consider":[54],"selecting":[55],"over":[56],"models":[58],"policies:":[60],"as":[61,63],"long":[62],"can":[67],"accurately":[68],"represent":[69],"of":[72,88,116],"state-action":[74],"pairs":[75],"visited":[76],"given":[79],"policy,":[80],"it":[81],"possible":[83],"approximate":[85],"particular":[90],"policy.":[91],"analyze":[93],"our":[94],"in":[97],"LQR":[99],"setting":[100],"also":[102],"show":[103],"competitive":[104],"previous":[107],"bounds":[109],"on":[110],"selection":[112],"across":[113],"set":[115],"D4RL":[117],"tasks.":[118]},"counts_by_year":[],"updated_date":"2026-04-10T15:06:20.359241","created_date":"2025-10-10T00:00:00"}