{"id":"https://openalex.org/W4401417073","doi":"https://doi.org/10.1109/icra57147.2024.10611110","title":"Cross Domain Policy Transfer with Effect Cycle-Consistency","display_name":"Cross Domain Policy Transfer with Effect Cycle-Consistency","publication_year":2024,"publication_date":"2024-05-13","ids":{"openalex":"https://openalex.org/W4401417073","doi":"https://doi.org/10.1109/icra57147.2024.10611110"},"language":"en","primary_location":{"id":"doi:10.1109/icra57147.2024.10611110","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icra57147.2024.10611110","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2024 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/A5100577606","display_name":"Ruiqi Zhu","orcid":null},"institutions":[{"id":"https://openalex.org/I4210119896","display_name":"King's College School","ror":"https://ror.org/02bbqcn27","country_code":"GB","type":"education","lineage":["https://openalex.org/I4210119896"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Ruiqi Zhu","raw_affiliation_strings":["King’s College London,Department of Engineering"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"King’s College London,Department of Engineering","institution_ids":["https://openalex.org/I4210119896"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5084139877","display_name":"Tianhong Dai","orcid":"https://orcid.org/0000-0001-8904-1551"},"institutions":[{"id":"https://openalex.org/I195460627","display_name":"University of Aberdeen","ror":"https://ror.org/016476m91","country_code":"GB","type":"education","lineage":["https://openalex.org/I195460627"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Tianhong Dai","raw_affiliation_strings":["University of Aberdeen,Department of Computing Science"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Aberdeen,Department of Computing Science","institution_ids":["https://openalex.org/I195460627"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5059459055","display_name":"Oya \u00c7eliktutan","orcid":"https://orcid.org/0000-0002-7213-6359"},"institutions":[{"id":"https://openalex.org/I4210119896","display_name":"King's College School","ror":"https://ror.org/02bbqcn27","country_code":"GB","type":"education","lineage":["https://openalex.org/I4210119896"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Oya Celiktutan","raw_affiliation_strings":["King’s College London,Department of Engineering"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"King’s College London,Department of Engineering","institution_ids":["https://openalex.org/I4210119896"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":1,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"9471","last_page":"9477"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10462","display_name":"Reinforcement Learning in Robotics","score":0.9926999807357788,"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":0.9926999807357788,"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/T11307","display_name":"Domain Adaptation and Few-Shot Learning","score":0.9470000267028809,"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":0.9370999932289124,"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/computer-science","display_name":"Computer science","score":0.513391375541687},{"id":"https://openalex.org/keywords/consistency","display_name":"Consistency (knowledge bases)","score":0.4984099864959717},{"id":"https://openalex.org/keywords/transfer","display_name":"Transfer (computing)","score":0.44532740116119385},{"id":"https://openalex.org/keywords/parallel-computing","display_name":"Parallel computing","score":0.09831452369689941},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.0804411768913269}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.513391375541687},{"id":"https://openalex.org/C2776436953","wikidata":"https://www.wikidata.org/wiki/Q5163215","display_name":"Consistency (knowledge bases)","level":2,"score":0.4984099864959717},{"id":"https://openalex.org/C2776175482","wikidata":"https://www.wikidata.org/wiki/Q1195816","display_name":"Transfer (computing)","level":2,"score":0.44532740116119385},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.09831452369689941},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.0804411768913269}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icra57147.2024.10611110","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icra57147.2024.10611110","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2024 IEEE International Conference on Robotics and Automation (ICRA)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[{"id":"https://openalex.org/F4320322725","display_name":"China Scholarship Council","ror":"https://ror.org/04atp4p48"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":47,"referenced_works":["https://openalex.org/W1959608418","https://openalex.org/W2097381042","https://openalex.org/W2145339207","https://openalex.org/W2158782408","https://openalex.org/W2595845486","https://openalex.org/W2605102758","https://openalex.org/W2767050701","https://openalex.org/W2769112066","https://openalex.org/W2785948534","https://openalex.org/W2877093712","https://openalex.org/W2949600457","https://openalex.org/W2962793481","https://openalex.org/W2963802910","https://openalex.org/W2963917969","https://openalex.org/W2990747716","https://openalex.org/W3026092005","https://openalex.org/W3035756007","https://openalex.org/W3088304681","https://openalex.org/W3096831136","https://openalex.org/W3097841467","https://openalex.org/W3101442004","https://openalex.org/W3121989526","https://openalex.org/W3127561923","https://openalex.org/W3152893301","https://openalex.org/W3206394619","https://openalex.org/W4212863985","https://openalex.org/W4223568377","https://openalex.org/W4224938351","https://openalex.org/W4226080840","https://openalex.org/W4287646021","https://openalex.org/W4389666555","https://openalex.org/W6640963894","https://openalex.org/W6674600207","https://openalex.org/W6736469832","https://openalex.org/W6746282794","https://openalex.org/W6747769025","https://openalex.org/W6748839928","https://openalex.org/W6774544712","https://openalex.org/W6774733536","https://openalex.org/W6777179611","https://openalex.org/W6780559457","https://openalex.org/W6782766965","https://openalex.org/W6783987590","https://openalex.org/W6784826119","https://openalex.org/W6786816963","https://openalex.org/W6839805037","https://openalex.org/W6922480057"],"related_works":["https://openalex.org/W4391375266","https://openalex.org/W2748952813","https://openalex.org/W2390279801","https://openalex.org/W2358668433","https://openalex.org/W4396701345","https://openalex.org/W2376932109","https://openalex.org/W2001405890","https://openalex.org/W4396696052","https://openalex.org/W2382290278","https://openalex.org/W4395014643"],"abstract_inverted_index":{"Training":[0],"a":[1,96,128],"robotic":[2,168],"policy":[3,79,148],"from":[4,80,149],"scratch":[5],"using":[6,111],"deep":[7],"reinforcement":[8],"learning":[9,100,133],"methods":[10,88],"can":[11,144,178],"be":[12],"prohibitively":[13],"expensive":[14],"due":[15],"to":[16,30,83,153,188],"sample":[17],"inefficiency.":[18],"To":[19],"address":[20],"this":[21,57],"challenge,":[22],"transferring":[23],"policies":[24],"trained":[25],"in":[26,53,63],"the":[27,31,78,101,120,138,147,150,154,189],"source":[28,151],"domain":[29,33,152],"target":[32,155],"becomes":[34],"an":[35],"attractive":[36],"paradigm.":[37],"Previous":[38],"research":[39],"has":[40,72,159],"typically":[41],"focused":[42],"on":[43,91,162],"domains":[44,64,110,126],"with":[45,65],"similar":[46],"state":[47,67,105],"and":[48,68,106,166,183],"action":[49,69,107],"spaces":[50,108],"but":[51],"differing":[52],"other":[54],"aspects.":[55],"In":[56],"paper,":[58],"our":[59,176],"primary":[60],"focus":[61],"lies":[62],"different":[66],"spaces,":[70],"which":[71,118],"broader":[73],"practical":[74],"implications,":[75],"i.e.":[76],"transfer":[77,146],"robot":[81,84],"A":[82],"B.":[85],"Unlike":[86],"prior":[87],"that":[89,175],"rely":[90],"paired":[92],"data,":[93],"we":[94,143],"propose":[95,115],"novel":[97],"approach":[98,158],"for":[99,132],"mapping":[102,135,139],"functions":[103,140],"between":[104],"across":[109,124],"unpaired":[112],"data.":[113],"We":[114],"effect":[116],"cycle-consistency,":[117],"aligns":[119],"effects":[121],"of":[122],"transitions":[123],"two":[125,167],"through":[127],"symmetrical":[129],"optimization":[130],"structure":[131],"these":[134],"functions.":[136],"Once":[137],"are":[141],"learned,":[142],"seamlessly":[145],"domain.":[156],"Our":[157],"been":[160],"tested":[161],"three":[163],"locomotion":[164],"tasks":[165],"manipulation":[169],"tasks.":[170],"The":[171],"empirical":[172],"results":[173],"demonstrate":[174],"method":[177],"reduce":[179],"alignment":[180],"errors":[181],"significantly":[182],"achieve":[184],"better":[185],"performance":[186],"compared":[187],"state-of-the-art":[190],"method.":[191],"Project":[192],"page:":[193],"https://ricky-zhu.github.io/effect_cycle_consistency.":[194]},"counts_by_year":[{"year":2025,"cited_by_count":1}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}