{"id":"https://openalex.org/W7137945159","doi":"https://doi.org/10.1609/aaai.v40i26.39315","title":"Reliability-Guaranteed and Reward-Seeking Sequence Modeling for Model-Based Offline Reinforcement Learning","display_name":"Reliability-Guaranteed and Reward-Seeking Sequence Modeling for Model-Based Offline Reinforcement Learning","publication_year":2026,"publication_date":"2026-03-14","ids":{"openalex":"https://openalex.org/W7137945159","doi":"https://doi.org/10.1609/aaai.v40i26.39315"},"language":null,"primary_location":{"id":"doi:10.1609/aaai.v40i26.39315","is_oa":true,"landing_page_url":"https://doi.org/10.1609/aaai.v40i26.39315","pdf_url":null,"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://doi.org/10.1609/aaai.v40i26.39315","any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5102751081","display_name":"Shenghong He","orcid":null},"institutions":[{"id":"https://openalex.org/I157773358","display_name":"Sun Yat-sen University","ror":"https://ror.org/0064kty71","country_code":"CN","type":"education","lineage":["https://openalex.org/I157773358"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Shenghong He","raw_affiliation_strings":["Sun Yat-sen University"],"affiliations":[{"raw_affiliation_string":"Sun Yat-sen University","institution_ids":["https://openalex.org/I157773358"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5129663048","display_name":"Chao Yu","orcid":null},"institutions":[{"id":"https://openalex.org/I157773358","display_name":"Sun Yat-sen University","ror":"https://ror.org/0064kty71","country_code":"CN","type":"education","lineage":["https://openalex.org/I157773358"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Chao Yu","raw_affiliation_strings":["Sun Yat-sen University, Pengcheng Laboratory"],"affiliations":[{"raw_affiliation_string":"Sun Yat-sen University, Pengcheng Laboratory","institution_ids":["https://openalex.org/I157773358"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5129667677","display_name":"Qian Lin","orcid":null},"institutions":[{"id":"https://openalex.org/I157773358","display_name":"Sun Yat-sen University","ror":"https://ror.org/0064kty71","country_code":"CN","type":"education","lineage":["https://openalex.org/I157773358"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Qian Lin","raw_affiliation_strings":["Sun Yat-sen University"],"affiliations":[{"raw_affiliation_string":"Sun Yat-sen University","institution_ids":["https://openalex.org/I157773358"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5129645910","display_name":"Yile Liang","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Yile Liang","raw_affiliation_strings":["Meituan"],"affiliations":[{"raw_affiliation_string":"Meituan","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5129752018","display_name":"Donghui Li","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Donghui Li","raw_affiliation_strings":["Meituan"],"affiliations":[{"raw_affiliation_string":"Meituan","institution_ids":[]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5006106006","display_name":"Xuetao Ding","orcid":"https://orcid.org/0009-0002-3551-5613"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Xuetao Ding","raw_affiliation_strings":["Meituan"],"affiliations":[{"raw_affiliation_string":"Meituan","institution_ids":[]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":6,"corresponding_author_ids":["https://openalex.org/A5102751081"],"corresponding_institution_ids":["https://openalex.org/I157773358"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.15685225,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":"40","issue":"26","first_page":"21654","last_page":"21662"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10462","display_name":"Reinforcement Learning in Robotics","score":0.5314000248908997,"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":0.5314000248908997,"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/T10328","display_name":"Supply Chain and Inventory Management","score":0.029999999329447746,"subfield":{"id":"https://openalex.org/subfields/1404","display_name":"Management Information Systems"},"field":{"id":"https://openalex.org/fields/14","display_name":"Business, Management and Accounting"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}},{"id":"https://openalex.org/T11689","display_name":"Adversarial Robustness in Machine Learning","score":0.02419999986886978,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/reinforcement-learning","display_name":"Reinforcement learning","score":0.7889999747276306},{"id":"https://openalex.org/keywords/trajectory","display_name":"Trajectory","score":0.5447999835014343},{"id":"https://openalex.org/keywords/benchmark","display_name":"Benchmark (surveying)","score":0.5260999798774719},{"id":"https://openalex.org/keywords/offline-learning","display_name":"Offline learning","score":0.4839000105857849},{"id":"https://openalex.org/keywords/sequence","display_name":"Sequence (biology)","score":0.4578000009059906},{"id":"https://openalex.org/keywords/reliability","display_name":"Reliability (semiconductor)","score":0.44620001316070557},{"id":"https://openalex.org/keywords/sampling","display_name":"Sampling (signal processing)","score":0.32499998807907104}],"concepts":[{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.7889999747276306},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7016000151634216},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5579000115394592},{"id":"https://openalex.org/C13662910","wikidata":"https://www.wikidata.org/wiki/Q193139","display_name":"Trajectory","level":2,"score":0.5447999835014343},{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.5260999798774719},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.5234000086784363},{"id":"https://openalex.org/C2780490138","wikidata":"https://www.wikidata.org/wiki/Q7079636","display_name":"Offline learning","level":3,"score":0.4839000105857849},{"id":"https://openalex.org/C2778112365","wikidata":"https://www.wikidata.org/wiki/Q3511065","display_name":"Sequence (biology)","level":2,"score":0.4578000009059906},{"id":"https://openalex.org/C43214815","wikidata":"https://www.wikidata.org/wiki/Q7310987","display_name":"Reliability (semiconductor)","level":3,"score":0.44620001316070557},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.38190001249313354},{"id":"https://openalex.org/C140779682","wikidata":"https://www.wikidata.org/wiki/Q210868","display_name":"Sampling (signal processing)","level":3,"score":0.32499998807907104},{"id":"https://openalex.org/C77405623","wikidata":"https://www.wikidata.org/wiki/Q598451","display_name":"System dynamics","level":2,"score":0.3100999891757965},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.2971000075340271},{"id":"https://openalex.org/C66322947","wikidata":"https://www.wikidata.org/wiki/Q11658","display_name":"Transformer","level":3,"score":0.29350000619888306},{"id":"https://openalex.org/C52740198","wikidata":"https://www.wikidata.org/wiki/Q1539564","display_name":"Importance sampling","level":3,"score":0.28040000796318054},{"id":"https://openalex.org/C67186912","wikidata":"https://www.wikidata.org/wiki/Q367664","display_name":"Data modeling","level":2,"score":0.273499995470047},{"id":"https://openalex.org/C188116033","wikidata":"https://www.wikidata.org/wiki/Q2664563","display_name":"Q-learning","level":3,"score":0.2694000005722046},{"id":"https://openalex.org/C2777851325","wikidata":"https://www.wikidata.org/wiki/Q7094102","display_name":"Online model","level":2,"score":0.26739999651908875}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1609/aaai.v40i26.39315","is_oa":true,"landing_page_url":"https://doi.org/10.1609/aaai.v40i26.39315","pdf_url":null,"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.v40i26.39315","is_oa":true,"landing_page_url":"https://doi.org/10.1609/aaai.v40i26.39315","pdf_url":null,"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":0.5316300988197327,"id":"https://metadata.un.org/sdg/2","display_name":"Zero hunger"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"As":[0],"a":[1,13,17,80,107,171],"data-driven":[2],"learning":[3,8],"approach,":[4],"model-based":[5,163],"offline":[6,138,167],"reinforcement":[7],"(MORL)":[9],"aims":[10],"to":[11,28,45,68],"learn":[12],"policy":[14,47,143,154],"by":[15,122],"exploiting":[16],"dynamics":[18,30],"model":[19],"derived":[20],"from":[21,135,175],"an":[22,176],"existing":[23,33,137],"dataset.":[24],"Applying":[25],"conservative":[26],"quantification":[27],"the":[29,41,54,71,97,103,112,117,136,148],"model,":[31],"most":[32],"works":[34],"on":[35,59,165],"MORL":[36,82],"generate":[37,132],"trajectories":[38,65,95,134],"that":[39,66],"approximate":[40],"real":[42],"data":[43,73,119],"distribution":[44,115],"facilitate":[46],"learning.":[48,144],"However,":[49],"these":[50],"methods":[51,164],"typically":[52],"overlook":[53],"influence":[55],"of":[56,99,102,151],"historical":[57],"information":[58],"environmental":[60],"dynamics,":[61],"thus":[62],"generating":[63,93],"unreliable":[64,94],"fail":[67],"align":[69],"with":[70,126],"true":[72,118],"distribution.":[74,120],"In":[75],"this":[76],"paper,":[77],"we":[78],"propose":[79],"new":[81],"algorithm":[83],"called":[84],"Reliability-guaranteed":[85],"and":[86,116,156,170],"Reward-seeking":[87],"Transformer":[88],"(RT).":[89],"RT":[90,129,152],"can":[91,130],"avoid":[92],"through":[96],"calculation":[98],"cumulative":[100],"reliability":[101],"trajectories,":[104],"which":[105],"is":[106],"weighted":[108],"variational":[109],"distance":[110],"between":[111],"generated":[113],"trajectory":[114],"Moreover,":[121],"sampling":[123],"candidate":[124],"actions":[125],"high":[127],"rewards,":[128],"efficiently":[131],"high-reward":[133],"data,":[139],"thereby":[140],"further":[141],"facilitating":[142],"We":[145],"theoretically":[146],"prove":[147],"performance":[149],"guarantees":[150],"in":[153],"learning,":[155],"empirically":[157],"demonstrate":[158],"its":[159],"effectiveness":[160],"against":[161],"state-of-the-art":[162],"several":[166],"benchmark":[168],"tasks":[169],"large-scale":[172],"industrial":[173],"dataset":[174],"on-demand":[177],"food":[178],"delivery":[179],"platform.":[180]},"counts_by_year":[],"updated_date":"2026-03-20T20:47:17.329874","created_date":"2026-03-18T00:00:00"}