{"id":"https://openalex.org/W4414359151","doi":"https://doi.org/10.24963/ijcai.2025/970","title":"State Revisit and Re-explore: Bridging Sim-to-Real Gaps in Offline-and-Online Reinforcement Learning with An Imperfect Simulator","display_name":"State Revisit and Re-explore: Bridging Sim-to-Real Gaps in Offline-and-Online Reinforcement Learning with An Imperfect Simulator","publication_year":2025,"publication_date":"2025-09-01","ids":{"openalex":"https://openalex.org/W4414359151","doi":"https://doi.org/10.24963/ijcai.2025/970"},"language":"en","primary_location":{"id":"doi:10.24963/ijcai.2025/970","is_oa":false,"landing_page_url":"https://doi.org/10.24963/ijcai.2025/970","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the Thirty-Fourth International Joint Conference on Artificial Intelligence","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"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/A5100387334","display_name":"Xingyu Chen","orcid":"https://orcid.org/0000-0001-8211-6880"},"institutions":[{"id":"https://openalex.org/I87445476","display_name":"Xi'an Jiaotong University","ror":"https://ror.org/017zhmm22","country_code":"CN","type":"education","lineage":["https://openalex.org/I87445476"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Xingyu Chen","raw_affiliation_strings":["Xi'an Jiaotong University"],"affiliations":[{"raw_affiliation_string":"Xi'an Jiaotong University","institution_ids":["https://openalex.org/I87445476"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5108145652","display_name":"Jiayi Xie","orcid":"https://orcid.org/0009-0009-4204-7863"},"institutions":[{"id":"https://openalex.org/I87445476","display_name":"Xi'an Jiaotong University","ror":"https://ror.org/017zhmm22","country_code":"CN","type":"education","lineage":["https://openalex.org/I87445476"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jiayi Xie","raw_affiliation_strings":["Xi'an Jiaotong University"],"affiliations":[{"raw_affiliation_string":"Xi'an Jiaotong University","institution_ids":["https://openalex.org/I87445476"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5083748084","display_name":"Zhijian Xu","orcid":"https://orcid.org/0000-0002-3063-8473"},"institutions":[{"id":"https://openalex.org/I87445476","display_name":"Xi'an Jiaotong University","ror":"https://ror.org/017zhmm22","country_code":"CN","type":"education","lineage":["https://openalex.org/I87445476"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zhijian Xu","raw_affiliation_strings":["Xi'an Jiaotong University"],"affiliations":[{"raw_affiliation_string":"Xi'an Jiaotong University","institution_ids":["https://openalex.org/I87445476"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5113173886","display_name":"Ruixun Liu","orcid":null},"institutions":[{"id":"https://openalex.org/I87445476","display_name":"Xi'an Jiaotong University","ror":"https://ror.org/017zhmm22","country_code":"CN","type":"education","lineage":["https://openalex.org/I87445476"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Ruixun Liu","raw_affiliation_strings":["Xi'an Jiaotong University"],"affiliations":[{"raw_affiliation_string":"Xi'an Jiaotong University","institution_ids":["https://openalex.org/I87445476"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101900427","display_name":"Shuai Yang","orcid":"https://orcid.org/0000-0001-9719-1840"},"institutions":[{"id":"https://openalex.org/I87445476","display_name":"Xi'an Jiaotong University","ror":"https://ror.org/017zhmm22","country_code":"CN","type":"education","lineage":["https://openalex.org/I87445476"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Shuai Yang","raw_affiliation_strings":["Xi'an Jiaotong University"],"affiliations":[{"raw_affiliation_string":"Xi'an Jiaotong University","institution_ids":["https://openalex.org/I87445476"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5102893461","display_name":"Zeyang Liu","orcid":"https://orcid.org/0000-0002-3110-8618"},"institutions":[{"id":"https://openalex.org/I87445476","display_name":"Xi'an Jiaotong University","ror":"https://ror.org/017zhmm22","country_code":"CN","type":"education","lineage":["https://openalex.org/I87445476"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zeyang Liu","raw_affiliation_strings":["Xi'an Jiaotong University"],"affiliations":[{"raw_affiliation_string":"Xi'an Jiaotong University","institution_ids":["https://openalex.org/I87445476"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5050982461","display_name":"Lipeng Wan","orcid":null},"institutions":[{"id":"https://openalex.org/I87445476","display_name":"Xi'an Jiaotong University","ror":"https://ror.org/017zhmm22","country_code":"CN","type":"education","lineage":["https://openalex.org/I87445476"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Lipeng Wan","raw_affiliation_strings":["Xi'an Jiaotong University"],"affiliations":[{"raw_affiliation_string":"Xi'an Jiaotong University","institution_ids":["https://openalex.org/I87445476"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5006277484","display_name":"Xuguang Lan","orcid":"https://orcid.org/0000-0002-3422-944X"},"institutions":[{"id":"https://openalex.org/I87445476","display_name":"Xi'an Jiaotong University","ror":"https://ror.org/017zhmm22","country_code":"CN","type":"education","lineage":["https://openalex.org/I87445476"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xuguang Lan","raw_affiliation_strings":["Xi'an Jiaotong University"],"affiliations":[{"raw_affiliation_string":"Xi'an Jiaotong University","institution_ids":["https://openalex.org/I87445476"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":8,"corresponding_author_ids":["https://openalex.org/A5100387334"],"corresponding_institution_ids":["https://openalex.org/I87445476"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.2685155,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"8724","last_page":"8732"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10603","display_name":"Smart Grid Energy Management","score":0.9340000152587891,"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"}},"topics":[{"id":"https://openalex.org/T10603","display_name":"Smart Grid Energy Management","score":0.9340000152587891,"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/T11182","display_name":"Auction Theory and Applications","score":0.9059000015258789,"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"}},{"id":"https://openalex.org/T10462","display_name":"Reinforcement Learning in Robotics","score":0.9032999873161316,"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":0.8241999745368958},{"id":"https://openalex.org/keywords/imperfect","display_name":"Imperfect","score":0.776199996471405},{"id":"https://openalex.org/keywords/bridging","display_name":"Bridging (networking)","score":0.7225000262260437},{"id":"https://openalex.org/keywords/robot","display_name":"Robot","score":0.5045999884605408},{"id":"https://openalex.org/keywords/set","display_name":"Set (abstract data type)","score":0.5001000165939331},{"id":"https://openalex.org/keywords/state","display_name":"State (computer science)","score":0.4422000050544739},{"id":"https://openalex.org/keywords/state-space","display_name":"State space","score":0.4417000114917755}],"concepts":[{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.8241999745368958},{"id":"https://openalex.org/C2780310539","wikidata":"https://www.wikidata.org/wiki/Q12547192","display_name":"Imperfect","level":2,"score":0.776199996471405},{"id":"https://openalex.org/C174348530","wikidata":"https://www.wikidata.org/wiki/Q188635","display_name":"Bridging (networking)","level":2,"score":0.7225000262260437},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7175999879837036},{"id":"https://openalex.org/C90509273","wikidata":"https://www.wikidata.org/wiki/Q11012","display_name":"Robot","level":2,"score":0.5045999884605408},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.5001000165939331},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.47269999980926514},{"id":"https://openalex.org/C48103436","wikidata":"https://www.wikidata.org/wiki/Q599031","display_name":"State (computer science)","level":2,"score":0.4422000050544739},{"id":"https://openalex.org/C72434380","wikidata":"https://www.wikidata.org/wiki/Q230930","display_name":"State space","level":2,"score":0.4417000114917755},{"id":"https://openalex.org/C2780490138","wikidata":"https://www.wikidata.org/wiki/Q7079636","display_name":"Offline learning","level":3,"score":0.3716000020503998},{"id":"https://openalex.org/C2780102126","wikidata":"https://www.wikidata.org/wiki/Q10928179","display_name":"Online and offline","level":2,"score":0.3151000142097473},{"id":"https://openalex.org/C48677424","wikidata":"https://www.wikidata.org/wiki/Q6888088","display_name":"Mode (computer interface)","level":2,"score":0.305400013923645},{"id":"https://openalex.org/C123676819","wikidata":"https://www.wikidata.org/wiki/Q1074338","display_name":"Perfect information","level":2,"score":0.2978000044822693},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.2971000075340271},{"id":"https://openalex.org/C2780586882","wikidata":"https://www.wikidata.org/wiki/Q7520643","display_name":"Simple (philosophy)","level":2,"score":0.29100000858306885},{"id":"https://openalex.org/C34413123","wikidata":"https://www.wikidata.org/wiki/Q170978","display_name":"Robotics","level":3,"score":0.28110000491142273},{"id":"https://openalex.org/C44154836","wikidata":"https://www.wikidata.org/wiki/Q45045","display_name":"Simulation","level":1,"score":0.25859999656677246},{"id":"https://openalex.org/C198531522","wikidata":"https://www.wikidata.org/wiki/Q485146","display_name":"Sample (material)","level":2,"score":0.2524999976158142}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.24963/ijcai.2025/970","is_oa":false,"landing_page_url":"https://doi.org/10.24963/ijcai.2025/970","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the Thirty-Fourth International Joint Conference on Artificial Intelligence","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"In":[0,98],"reinforcement":[1],"learning":[2],"(RL)":[3],"based":[4],"robot":[5,129],"skill":[6,130],"acquisition,":[7],"a":[8,88,104,107,151],"high-fidelity":[9],"simulator":[10],"is":[11],"usually":[12],"indispensable":[13],"but":[14],"unattainable":[15],"since":[16],"the":[17,57,61,64,100,110,118,125,128,139,165],"real":[18],"environment":[19],"dynamics":[20],"are":[21],"difficult":[22],"to":[23,27,42,56,113],"model,":[24],"which":[25],"leads":[26],"severe":[28],"sim-to-real":[29,154],"gaps.":[30],"Existing":[31],"methods":[32,68],"solve":[33,83],"this":[34,84],"problem":[35],"by":[36],"combining":[37],"offline":[38,49,119,133],"and":[39,51,75,91,106,124,134,142,160],"online":[40,122,135],"RL":[41,67,96],"jointly":[43],"learn":[44],"transferable":[45],"policies":[46],"from":[47,71],"limited":[48],"data":[50],"imperfect":[52,62],"simulators.":[53],"However,":[54],"due":[55],"unrestricted":[58],"exploration":[59],"in":[60,117],"simulator,":[63],"hybrid":[65,94],"offline-and-online":[66,95],"inevitably":[69],"suffer":[70],"low":[72],"sample":[73],"efficiency":[74],"insufficient":[76],"state-action":[77],"space":[78],"coverage":[79],"during":[80],"training.":[81],"To":[82],"problem,":[85],"we":[86,163],"propose":[87],"State":[89],"Revisit":[90],"Re-exploration":[92],"(SR2)":[93],"framework.":[97],"particular,":[99],"proposed":[101],"algorithm":[102],"employs":[103],"meta-policy":[105,111],"sub-policy,":[108],"where":[109],"aims":[112],"find":[114],"high-quality":[115],"states":[116],"trajectories":[120],"for":[121],"exploration,":[123],"sub-policy":[126],"learns":[127],"using":[131],"mixed":[132],"data.":[136],"By":[137],"introducing":[138],"state":[140],"revisit":[141],"explore":[143],"mechanism,":[144],"our":[145,169],"approach":[146,170],"efficiently":[147],"improves":[148],"performance":[149,167],"on":[150],"set":[152],"of":[153,168],"robotic":[155],"tasks.":[156],"Through":[157],"extensive":[158],"simulation":[159],"real-world":[161],"tasks,":[162],"demonstrate":[164],"superior":[166],"against":[171],"other":[172],"state-of-the-art":[173],"methods.":[174]},"counts_by_year":[],"updated_date":"2026-03-07T16:01:11.037858","created_date":"2025-10-10T00:00:00"}