{"id":"https://openalex.org/W4383109224","doi":"https://doi.org/10.1109/icra48891.2023.10161298","title":"Sim-to-Real Policy and Reward Transfer with Adaptive Forward Dynamics Model","display_name":"Sim-to-Real Policy and Reward Transfer with Adaptive Forward Dynamics Model","publication_year":2023,"publication_date":"2023-05-29","ids":{"openalex":"https://openalex.org/W4383109224","doi":"https://doi.org/10.1109/icra48891.2023.10161298"},"language":"en","primary_location":{"id":"doi:10.1109/icra48891.2023.10161298","is_oa":false,"landing_page_url":"http://dx.doi.org/10.1109/icra48891.2023.10161298","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2023 IEEE International Conference on Robotics and Automation (ICRA)","raw_type":"proceedings-article"},"type":"conference-paper","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/A5065250586","display_name":"Rongshun Juan","orcid":"https://orcid.org/0000-0002-0840-2528"},"institutions":[{"id":"https://openalex.org/I59028903","display_name":"Ocean University of China","ror":"https://ror.org/04rdtx186","country_code":"CN","type":"education","lineage":["https://openalex.org/I59028903"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Rongshun Juan","raw_affiliation_strings":["College of Information Science and Engineering, Ocean University of China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"College of Information Science and Engineering, Ocean University of China","institution_ids":["https://openalex.org/I59028903"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101922739","display_name":"Hao Ju","orcid":"https://orcid.org/0009-0008-5341-8263"},"institutions":[{"id":"https://openalex.org/I59028903","display_name":"Ocean University of China","ror":"https://ror.org/04rdtx186","country_code":"CN","type":"education","lineage":["https://openalex.org/I59028903"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Hao Ju","raw_affiliation_strings":["College of Information Science and Engineering, Ocean University of China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"College of Information Science and Engineering, Ocean University of China","institution_ids":["https://openalex.org/I59028903"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5048299480","display_name":"Jie Huang","orcid":"https://orcid.org/0000-0003-1570-6797"},"institutions":[{"id":"https://openalex.org/I59028903","display_name":"Ocean University of China","ror":"https://ror.org/04rdtx186","country_code":"CN","type":"education","lineage":["https://openalex.org/I59028903"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jie Huang","raw_affiliation_strings":["College of Information Science and Engineering, Ocean University of China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"College of Information Science and Engineering, Ocean University of China","institution_ids":["https://openalex.org/I59028903"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5052470310","display_name":"Randy G\u00f3mez","orcid":"https://orcid.org/0000-0002-3191-6818"},"institutions":[{"id":"https://openalex.org/I1283473643","display_name":"Honda (Japan)","ror":"https://ror.org/03jzay846","country_code":"JP","type":"company","lineage":["https://openalex.org/I1283473643"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Randy Gomez","raw_affiliation_strings":["Honda Research Institute Japan Co., Ltd,Wako,Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Honda Research Institute Japan Co., Ltd,Wako,Japan","institution_ids":["https://openalex.org/I1283473643"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5049329632","display_name":"Keisuke Nakamura","orcid":"https://orcid.org/0000-0002-4979-2083"},"institutions":[{"id":"https://openalex.org/I1283473643","display_name":"Honda (Japan)","ror":"https://ror.org/03jzay846","country_code":"JP","type":"company","lineage":["https://openalex.org/I1283473643"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Keisuke Nakamura","raw_affiliation_strings":["Honda Research Institute Japan Co., Ltd,Wako,Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Honda Research Institute Japan Co., Ltd,Wako,Japan","institution_ids":["https://openalex.org/I1283473643"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5101812014","display_name":"Guangliang Li","orcid":"https://orcid.org/0000-0003-1728-5711"},"institutions":[{"id":"https://openalex.org/I59028903","display_name":"Ocean University of China","ror":"https://ror.org/04rdtx186","country_code":"CN","type":"education","lineage":["https://openalex.org/I59028903"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Guangliang Li","raw_affiliation_strings":["College of Information Science and Engineering, Ocean University of China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"College of Information Science and Engineering, Ocean University of China","institution_ids":["https://openalex.org/I59028903"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":3,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":"86","issue":null,"first_page":"7212","last_page":"7218"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10462","display_name":"Reinforcement Learning in Robotics","score":0.9997000098228455,"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":0.9997000098228455,"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/T10876","display_name":"Fault Detection and Control Systems","score":0.9811999797821045,"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/T10409","display_name":"Fuel Cells and Related Materials","score":0.9775999784469604,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/reinforcement-learning","display_name":"Reinforcement learning","score":0.7560458183288574},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7423715591430664},{"id":"https://openalex.org/keywords/robot","display_name":"Robot","score":0.5804493427276611},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5538656115531921},{"id":"https://openalex.org/keywords/dynamics","display_name":"Dynamics (music)","score":0.5496231317520142},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.520056426525116},{"id":"https://openalex.org/keywords/space","display_name":"Space (punctuation)","score":0.44583818316459656},{"id":"https://openalex.org/keywords/transfer-of-learning","display_name":"Transfer of learning","score":0.4327763617038727}],"concepts":[{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.7560458183288574},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7423715591430664},{"id":"https://openalex.org/C90509273","wikidata":"https://www.wikidata.org/wiki/Q11012","display_name":"Robot","level":2,"score":0.5804493427276611},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5538656115531921},{"id":"https://openalex.org/C145912823","wikidata":"https://www.wikidata.org/wiki/Q113558","display_name":"Dynamics (music)","level":2,"score":0.5496231317520142},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.520056426525116},{"id":"https://openalex.org/C2778572836","wikidata":"https://www.wikidata.org/wiki/Q380933","display_name":"Space (punctuation)","level":2,"score":0.44583818316459656},{"id":"https://openalex.org/C150899416","wikidata":"https://www.wikidata.org/wiki/Q1820378","display_name":"Transfer of learning","level":2,"score":0.4327763617038727},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","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},{"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/icra48891.2023.10161298","is_oa":false,"landing_page_url":"http://dx.doi.org/10.1109/icra48891.2023.10161298","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2023 IEEE International Conference on Robotics and Automation (ICRA)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G8754186815","display_name":null,"funder_award_id":"51809246","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"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":41,"referenced_works":["https://openalex.org/W1525280637","https://openalex.org/W2099597159","https://openalex.org/W2107726111","https://openalex.org/W2127572219","https://openalex.org/W2158796564","https://openalex.org/W2174364281","https://openalex.org/W2530944449","https://openalex.org/W2580909119","https://openalex.org/W2605102758","https://openalex.org/W2767050701","https://openalex.org/W2952629144","https://openalex.org/W2962872206","https://openalex.org/W2963411833","https://openalex.org/W2990747716","https://openalex.org/W3020718655","https://openalex.org/W3086412568","https://openalex.org/W3090897645","https://openalex.org/W3097841467","https://openalex.org/W3101442004","https://openalex.org/W3127031155","https://openalex.org/W3131536626","https://openalex.org/W3136025385","https://openalex.org/W3137837033","https://openalex.org/W3174428490","https://openalex.org/W4214717370","https://openalex.org/W4297918469","https://openalex.org/W4298857966","https://openalex.org/W4319988532","https://openalex.org/W6637967152","https://openalex.org/W6682968728","https://openalex.org/W6685200760","https://openalex.org/W6728367041","https://openalex.org/W6728925229","https://openalex.org/W6734827232","https://openalex.org/W6744563498","https://openalex.org/W6780559895","https://openalex.org/W6783068448","https://openalex.org/W6784826119","https://openalex.org/W6791554432","https://openalex.org/W6797659266","https://openalex.org/W6849896277"],"related_works":["https://openalex.org/W4362501864","https://openalex.org/W4306904969","https://openalex.org/W4380318855","https://openalex.org/W2138720691","https://openalex.org/W2031695474","https://openalex.org/W2586732548","https://openalex.org/W3049728571","https://openalex.org/W20361778","https://openalex.org/W2024136090","https://openalex.org/W2964765435"],"abstract_inverted_index":{"Deep":[0],"reinforcement":[1],"learning":[2,7,27,61,179],"has":[3,28,42],"shown":[4],"promise":[5],"in":[6,39,45,62,115,122,140,163,183],"robust":[8],"skills":[9],"for":[10,119],"robot":[11,171],"control,":[12],"but":[13,35,88],"typically":[14],"requires":[15],"a":[16,110,145,169],"large":[17],"amount":[18],"of":[19,55,80],"samples":[20],"to":[21,31,131],"achieve":[22],"good":[23],"performance.":[24],"Sim-to-real":[25],"transfer":[26,70],"been":[29],"developed":[30],"solve":[32],"this":[33],"problem,":[34],"the":[36,46,53,63,78,89,93,107,135,177,184],"policy":[37,69,96,108],"trained":[38],"simulation":[40,81,98,153],"usually":[41],"unsatisfactory":[43],"performance":[44,182],"real":[47,64,83,141,170,185],"world":[48,84,142,186],"because":[49],"simulators":[50],"inevitably":[51],"model":[52,74,114],"dynamics":[54,73,79,113,157],"reality":[56],"imperfectly.":[57],"To":[58],"enable":[59],"sample-efficient":[60],"world,":[65],"we":[66],"proposed":[67],"progressive":[68,100],"with":[71,109,175],"adaptive":[72],"(PPTADM).":[75],"PPTADM":[76,137],"assumes":[77],"and":[82,104,133,167,181],"do":[85,158],"not":[86,159],"match":[87],"state":[90],"space":[91],"is":[92,150],"same,":[94],"transfers":[95],"from":[97,144,152],"via":[99],"neural":[101],"network":[102],"(PNN)":[103],"further":[105],"improves":[106],"learned":[111],"forward":[112],"reality.":[116],"In":[117],"addition,":[118],"real-world":[120],"tasks":[121,166],"which":[123],"reward":[124,147],"functions":[125],"are":[126],"difficult":[127],"or":[128],"even":[129,154],"impossible":[130],"define":[132],"verify":[134],"effectiveness,":[136],"can":[138,187],"learn":[139],"solely":[143],"transferred":[146],"function":[148],"that":[149,174],"estimated":[151],"though":[155],"their":[156],"match.":[160],"Our":[161],"results":[162],"five":[164],"simulated":[165],"on":[168],"arm":[172],"show":[173],"PPTADM,":[176],"robot's":[178],"efficiency":[180],"be":[188],"significantly":[189],"improved.":[190]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2024,"cited_by_count":2}],"updated_date":"2026-07-15T18:14:33.161393","created_date":"2025-10-10T00:00:00"}