{"id":"https://openalex.org/W4413945292","doi":"https://doi.org/10.1109/icra55743.2025.11127503","title":"H2O+: An Improved Framework for Hybrid Offline-and-Online RL with Dynamics Gaps","display_name":"H2O+: An Improved Framework for Hybrid Offline-and-Online RL with Dynamics Gaps","publication_year":2025,"publication_date":"2025-05-19","ids":{"openalex":"https://openalex.org/W4413945292","doi":"https://doi.org/10.1109/icra55743.2025.11127503"},"language":"en","primary_location":{"id":"doi:10.1109/icra55743.2025.11127503","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icra55743.2025.11127503","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 IEEE International Conference on Robotics and Automation (ICRA)","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/A5083537522","display_name":"Haoyi Niu","orcid":null},"institutions":[{"id":"https://openalex.org/I99065089","display_name":"Tsinghua University","ror":"https://ror.org/03cve4549","country_code":"CN","type":"education","lineage":["https://openalex.org/I99065089"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Haoyi Niu","raw_affiliation_strings":["Tsinghua University"],"affiliations":[{"raw_affiliation_string":"Tsinghua University","institution_ids":["https://openalex.org/I99065089"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5079511023","display_name":"Tianying Ji","orcid":"https://orcid.org/0009-0006-8949-5880"},"institutions":[{"id":"https://openalex.org/I99065089","display_name":"Tsinghua University","ror":"https://ror.org/03cve4549","country_code":"CN","type":"education","lineage":["https://openalex.org/I99065089"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Tianying Ji","raw_affiliation_strings":["Tsinghua University"],"affiliations":[{"raw_affiliation_string":"Tsinghua University","institution_ids":["https://openalex.org/I99065089"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5061611470","display_name":"Bingqi Liu","orcid":"https://orcid.org/0000-0003-3728-1830"},"institutions":[{"id":"https://openalex.org/I82880672","display_name":"Beihang University","ror":"https://ror.org/00wk2mp56","country_code":"CN","type":"education","lineage":["https://openalex.org/I82880672"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Bingqi Liu","raw_affiliation_strings":["Beihang University"],"affiliations":[{"raw_affiliation_string":"Beihang University","institution_ids":["https://openalex.org/I82880672"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5047910725","display_name":"Haocheng Zhao","orcid":"https://orcid.org/0000-0001-8932-8106"},"institutions":[{"id":"https://openalex.org/I99065089","display_name":"Tsinghua University","ror":"https://ror.org/03cve4549","country_code":"CN","type":"education","lineage":["https://openalex.org/I99065089"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Haocheng Zhao","raw_affiliation_strings":["Tsinghua University"],"affiliations":[{"raw_affiliation_string":"Tsinghua University","institution_ids":["https://openalex.org/I99065089"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100632822","display_name":"Xiangyu Zhu","orcid":"https://orcid.org/0000-0002-4636-9677"},"institutions":[{"id":"https://openalex.org/I99065089","display_name":"Tsinghua University","ror":"https://ror.org/03cve4549","country_code":"CN","type":"education","lineage":["https://openalex.org/I99065089"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xiangyu Zhu","raw_affiliation_strings":["Tsinghua University"],"affiliations":[{"raw_affiliation_string":"Tsinghua University","institution_ids":["https://openalex.org/I99065089"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5020430058","display_name":"Jianying Zheng","orcid":"https://orcid.org/0000-0002-3902-8495"},"institutions":[{"id":"https://openalex.org/I82880672","display_name":"Beihang University","ror":"https://ror.org/00wk2mp56","country_code":"CN","type":"education","lineage":["https://openalex.org/I82880672"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jianying Zheng","raw_affiliation_strings":["Beihang University"],"affiliations":[{"raw_affiliation_string":"Beihang University","institution_ids":["https://openalex.org/I82880672"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5038566545","display_name":"Pengfei Huang","orcid":"https://orcid.org/0000-0001-5602-1730"},"institutions":[{"id":"https://openalex.org/I99065089","display_name":"Tsinghua University","ror":"https://ror.org/03cve4549","country_code":"CN","type":"education","lineage":["https://openalex.org/I99065089"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Pengfei Huang","raw_affiliation_strings":["Tsinghua University"],"affiliations":[{"raw_affiliation_string":"Tsinghua University","institution_ids":["https://openalex.org/I99065089"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5011913905","display_name":"Guyue Zhou","orcid":"https://orcid.org/0000-0002-3894-9858"},"institutions":[{"id":"https://openalex.org/I99065089","display_name":"Tsinghua University","ror":"https://ror.org/03cve4549","country_code":"CN","type":"education","lineage":["https://openalex.org/I99065089"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Guyue Zhou","raw_affiliation_strings":["Tsinghua University"],"affiliations":[{"raw_affiliation_string":"Tsinghua University","institution_ids":["https://openalex.org/I99065089"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101570775","display_name":"Jianming Hu","orcid":"https://orcid.org/0009-0002-5844-0116"},"institutions":[{"id":"https://openalex.org/I99065089","display_name":"Tsinghua University","ror":"https://ror.org/03cve4549","country_code":"CN","type":"education","lineage":["https://openalex.org/I99065089"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jianming Hu","raw_affiliation_strings":["Tsinghua University"],"affiliations":[{"raw_affiliation_string":"Tsinghua University","institution_ids":["https://openalex.org/I99065089"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5052921346","display_name":"Xianyuan Zhan","orcid":"https://orcid.org/0000-0002-3683-0554"},"institutions":[{"id":"https://openalex.org/I99065089","display_name":"Tsinghua University","ror":"https://ror.org/03cve4549","country_code":"CN","type":"education","lineage":["https://openalex.org/I99065089"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xianyuan Zhan","raw_affiliation_strings":["Tsinghua University"],"affiliations":[{"raw_affiliation_string":"Tsinghua University","institution_ids":["https://openalex.org/I99065089"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":10,"corresponding_author_ids":["https://openalex.org/A5083537522"],"corresponding_institution_ids":["https://openalex.org/I99065089"],"apc_list":null,"apc_paid":null,"fwci":1.2604,"has_fulltext":false,"cited_by_count":1,"citation_normalized_percentile":{"value":0.83872258,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":91,"max":95},"biblio":{"volume":null,"issue":null,"first_page":"1421","last_page":"1428"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T14083","display_name":"Extremum Seeking Control Systems","score":0.9775000214576721,"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"}},"topics":[{"id":"https://openalex.org/T14083","display_name":"Extremum Seeking Control Systems","score":0.9775000214576721,"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"}},{"id":"https://openalex.org/T10791","display_name":"Advanced Control Systems Optimization","score":0.9732000231742859,"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"}},{"id":"https://openalex.org/T12810","display_name":"Real-time simulation and control systems","score":0.965399980545044,"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/dynamics","display_name":"Dynamics (music)","score":0.6498976349830627},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6326319575309753},{"id":"https://openalex.org/keywords/physics","display_name":"Physics","score":0.10219728946685791}],"concepts":[{"id":"https://openalex.org/C145912823","wikidata":"https://www.wikidata.org/wiki/Q113558","display_name":"Dynamics (music)","level":2,"score":0.6498976349830627},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6326319575309753},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.10219728946685791},{"id":"https://openalex.org/C24890656","wikidata":"https://www.wikidata.org/wiki/Q82811","display_name":"Acoustics","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icra55743.2025.11127503","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icra55743.2025.11127503","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 IEEE International Conference on Robotics and Automation (ICRA)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G4884248357","display_name":null,"funder_award_id":"L231014","funder_id":"https://openalex.org/F4320322919","funder_display_name":"Natural Science Foundation of Beijing Municipality"},{"id":"https://openalex.org/G5611937910","display_name":null,"funder_award_id":"62333015,62273017","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G6396942078","display_name":null,"funder_award_id":"20242001120","funder_id":"https://openalex.org/F4320322392","funder_display_name":"Tsinghua University"},{"id":"https://openalex.org/G6582213310","display_name":null,"funder_award_id":"2022YFB2502904","funder_id":"https://openalex.org/F4320335777","funder_display_name":"National Key Research and Development Program 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/F4320322392","display_name":"Tsinghua University","ror":"https://ror.org/03cve4549"},{"id":"https://openalex.org/F4320322919","display_name":"Natural Science Foundation of Beijing Municipality","ror":null},{"id":"https://openalex.org/F4320335777","display_name":"National Key Research and Development Program of China","ror":null}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":17,"referenced_works":["https://openalex.org/W1977655452","https://openalex.org/W2145339207","https://openalex.org/W2766447205","https://openalex.org/W2767050701","https://openalex.org/W2963614114","https://openalex.org/W2963906246","https://openalex.org/W2968116426","https://openalex.org/W2990747716","https://openalex.org/W3093922502","https://openalex.org/W3118300017","https://openalex.org/W3207591725","https://openalex.org/W4214717370","https://openalex.org/W4229014698","https://openalex.org/W4231367092","https://openalex.org/W4283790903","https://openalex.org/W4311414408","https://openalex.org/W4401023433"],"related_works":["https://openalex.org/W4391375266","https://openalex.org/W2899084033","https://openalex.org/W2748952813","https://openalex.org/W2390279801","https://openalex.org/W4391913857","https://openalex.org/W2358668433","https://openalex.org/W4396701345","https://openalex.org/W2376932109","https://openalex.org/W2001405890","https://openalex.org/W4396696052"],"abstract_inverted_index":{"Solving":[0],"real-world":[1,127],"complex":[2],"tasks":[3],"using":[4],"reinforcement":[5],"learning":[6,109],"(RL)":[7],"without":[8],"high-fidelity":[9],"simulation":[10,28,121,125],"environments":[11,29],"or":[12],"large":[13],"amounts":[14],"of":[15,54,72,105,136],"offline":[16,56,74,106,147],"data":[17,75],"can":[18,30],"be":[19],"quite":[20],"challenging.":[21],"Online":[22],"RL":[23,37,63,148],"agents":[24],"trained":[25],"in":[26],"imperfect":[27,77],"suffer":[31],"from":[32],"severe":[33],"sim-to-real":[34],"issues.":[35],"Offline":[36],"approaches":[38],"although":[39],"bypass":[40],"the":[41,50,55,118],"need":[42],"for":[43,79,114],"simulators,":[44],"often":[45],"pose":[46],"demanding":[47],"requirements":[48],"on":[49],"size":[51],"and":[52,76,107,120,126,134,146],"quality":[53],"datasets.":[57],"The":[58],"recently":[59],"emerged":[60],"hybrid":[61],"offline-and-online":[62],"provides":[64],"an":[65],"attractive":[66],"framework":[67],"that":[68],"enables":[69],"joint":[70],"use":[71],"limited":[73],"simulator":[78],"transferable":[80],"policy":[81],"learning.":[82],"In":[83],"this":[84],"paper,":[85],"we":[86,130],"develop":[87],"a":[88],"new":[89],"algorithm,":[90],"called":[91],"<tex":[92,137],"xmlns:mml=\"http://www.w3.org/1998/Math/MathML\"":[93,138],"xmlns:xlink=\"http://www.w3.org/1999/xlink\">$\\mathrm{H}":[94],"2":[95,140],"\\mathrm{O}+$</tex>,":[96],"which":[97],"offers":[98],"great":[99],"flexibility":[100,135],"to":[101],"bridge":[102],"various":[103],"choices":[104],"online":[108,145],"methods,":[110],"while":[111],"also":[112],"accounting":[113],"dynamics":[115],"gaps":[116],"between":[117],"real":[119],"environments.":[122],"Through":[123],"extensive":[124],"robotics":[128],"experiments,":[129],"demonstrate":[131],"superior":[132],"performance":[133],"xmlns:xlink=\"http://www.w3.org/1999/xlink\">$\\mathbf{H":[139],"O}+$</tex>":[141],"over":[142],"advanced":[143],"cross-domain":[144],"algorithms.":[149]},"counts_by_year":[{"year":2025,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}
