{"id":"https://openalex.org/W3211185654","doi":"https://doi.org/10.1109/dsaa53316.2021.9564185","title":"Feature-Option-Action: A domain adaption transfer reinforcement learning framework","display_name":"Feature-Option-Action: A domain adaption transfer reinforcement learning framework","publication_year":2021,"publication_date":"2021-10-06","ids":{"openalex":"https://openalex.org/W3211185654","doi":"https://doi.org/10.1109/dsaa53316.2021.9564185","mag":"3211185654"},"language":"en","primary_location":{"id":"doi:10.1109/dsaa53316.2021.9564185","is_oa":false,"landing_page_url":"https://doi.org/10.1109/dsaa53316.2021.9564185","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2021 IEEE 8th International Conference on Data Science and Advanced Analytics (DSAA)","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/A5100756264","display_name":"Yunxiao Zhang","orcid":"https://orcid.org/0000-0003-4488-6352"},"institutions":[{"id":"https://openalex.org/I4210100255","display_name":"Beijing Academy of Artificial Intelligence","ror":"https://ror.org/016a74861","country_code":"CN","type":"other","lineage":["https://openalex.org/I4210100255"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Yunxiao Zhang","raw_affiliation_strings":["Artificial Intelligence Research Center, DII,Beijing,China","Artificial Intelligence Research Center, DII, Beijing, China"],"affiliations":[{"raw_affiliation_string":"Artificial Intelligence Research Center, DII,Beijing,China","institution_ids":["https://openalex.org/I4210100255"]},{"raw_affiliation_string":"Artificial Intelligence Research Center, DII, Beijing, China","institution_ids":["https://openalex.org/I4210100255"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5053199843","display_name":"Xiaochuan Zhang","orcid":"https://orcid.org/0000-0001-5875-8592"},"institutions":[{"id":"https://openalex.org/I4210100255","display_name":"Beijing Academy of Artificial Intelligence","ror":"https://ror.org/016a74861","country_code":"CN","type":"other","lineage":["https://openalex.org/I4210100255"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xiaochuan Zhang","raw_affiliation_strings":["Artificial Intelligence Research Center, DII,Beijing,China","Artificial Intelligence Research Center, DII, Beijing, China"],"affiliations":[{"raw_affiliation_string":"Artificial Intelligence Research Center, DII,Beijing,China","institution_ids":["https://openalex.org/I4210100255"]},{"raw_affiliation_string":"Artificial Intelligence Research Center, DII, Beijing, China","institution_ids":["https://openalex.org/I4210100255"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5024163828","display_name":"Tianlong Shen","orcid":null},"institutions":[{"id":"https://openalex.org/I4210100255","display_name":"Beijing Academy of Artificial Intelligence","ror":"https://ror.org/016a74861","country_code":"CN","type":"other","lineage":["https://openalex.org/I4210100255"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Tianlong Shen","raw_affiliation_strings":["Artificial Intelligence Research Center, DII,Beijing,China","Artificial Intelligence Research Center, DII, Beijing, China"],"affiliations":[{"raw_affiliation_string":"Artificial Intelligence Research Center, DII,Beijing,China","institution_ids":["https://openalex.org/I4210100255"]},{"raw_affiliation_string":"Artificial Intelligence Research Center, DII, Beijing, China","institution_ids":["https://openalex.org/I4210100255"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5049853160","display_name":"Yuan Zhou","orcid":"https://orcid.org/0000-0002-9198-6586"},"institutions":[{"id":"https://openalex.org/I4210100255","display_name":"Beijing Academy of Artificial Intelligence","ror":"https://ror.org/016a74861","country_code":"CN","type":"other","lineage":["https://openalex.org/I4210100255"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yuan Zhou","raw_affiliation_strings":["Artificial Intelligence Research Center, DII,Beijing,China","Artificial Intelligence Research Center, DII, Beijing, China"],"affiliations":[{"raw_affiliation_string":"Artificial Intelligence Research Center, DII,Beijing,China","institution_ids":["https://openalex.org/I4210100255"]},{"raw_affiliation_string":"Artificial Intelligence Research Center, DII, Beijing, China","institution_ids":["https://openalex.org/I4210100255"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5100462278","display_name":"Zhiyuan Wang","orcid":"https://orcid.org/0000-0001-6986-9589"},"institutions":[{"id":"https://openalex.org/I4210100255","display_name":"Beijing Academy of Artificial Intelligence","ror":"https://ror.org/016a74861","country_code":"CN","type":"other","lineage":["https://openalex.org/I4210100255"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zhiyuan Wang","raw_affiliation_strings":["Artificial Intelligence Research Center, DII,Beijing,China","Artificial Intelligence Research Center, DII, Beijing, China"],"affiliations":[{"raw_affiliation_string":"Artificial Intelligence Research Center, DII,Beijing,China","institution_ids":["https://openalex.org/I4210100255"]},{"raw_affiliation_string":"Artificial Intelligence Research Center, DII, Beijing, China","institution_ids":["https://openalex.org/I4210100255"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":5,"corresponding_author_ids":["https://openalex.org/A5100756264"],"corresponding_institution_ids":["https://openalex.org/I4210100255"],"apc_list":null,"apc_paid":null,"fwci":0.8158,"has_fulltext":false,"cited_by_count":6,"citation_normalized_percentile":{"value":0.78670519,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":97},"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"12"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11307","display_name":"Domain Adaptation and Few-Shot Learning","score":0.9994000196456909,"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/T11307","display_name":"Domain Adaptation and Few-Shot Learning","score":0.9994000196456909,"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/T10462","display_name":"Reinforcement Learning in Robotics","score":0.9983999729156494,"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/T12676","display_name":"Machine Learning and ELM","score":0.9794999957084656,"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":0.847486138343811},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7703030109405518},{"id":"https://openalex.org/keywords/domain","display_name":"Domain (mathematical analysis)","score":0.674622654914856},{"id":"https://openalex.org/keywords/transfer-of-learning","display_name":"Transfer of learning","score":0.631934404373169},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.596779465675354},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.5600594878196716},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.5349271297454834},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.5220372676849365},{"id":"https://openalex.org/keywords/focus","display_name":"Focus (optics)","score":0.4590221345424652},{"id":"https://openalex.org/keywords/action","display_name":"Action (physics)","score":0.4331305921077728},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.09255388379096985}],"concepts":[{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.847486138343811},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7703030109405518},{"id":"https://openalex.org/C36503486","wikidata":"https://www.wikidata.org/wiki/Q11235244","display_name":"Domain (mathematical analysis)","level":2,"score":0.674622654914856},{"id":"https://openalex.org/C150899416","wikidata":"https://www.wikidata.org/wiki/Q1820378","display_name":"Transfer of learning","level":2,"score":0.631934404373169},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.596779465675354},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.5600594878196716},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.5349271297454834},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.5220372676849365},{"id":"https://openalex.org/C192209626","wikidata":"https://www.wikidata.org/wiki/Q190909","display_name":"Focus (optics)","level":2,"score":0.4590221345424652},{"id":"https://openalex.org/C2780791683","wikidata":"https://www.wikidata.org/wiki/Q846785","display_name":"Action (physics)","level":2,"score":0.4331305921077728},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.09255388379096985},{"id":"https://openalex.org/C62520636","wikidata":"https://www.wikidata.org/wiki/Q944","display_name":"Quantum mechanics","level":1,"score":0.0},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.0},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0},{"id":"https://openalex.org/C120665830","wikidata":"https://www.wikidata.org/wiki/Q14620","display_name":"Optics","level":1,"score":0.0},{"id":"https://openalex.org/C134306372","wikidata":"https://www.wikidata.org/wiki/Q7754","display_name":"Mathematical analysis","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}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/dsaa53316.2021.9564185","is_oa":false,"landing_page_url":"https://doi.org/10.1109/dsaa53316.2021.9564185","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2021 IEEE 8th International Conference on Data Science and Advanced Analytics (DSAA)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G4849924244","display_name":null,"funder_award_id":"11801563","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":48,"referenced_works":["https://openalex.org/W1492014007","https://openalex.org/W1565327149","https://openalex.org/W1585861384","https://openalex.org/W1612195517","https://openalex.org/W1822705290","https://openalex.org/W1830058461","https://openalex.org/W2012036715","https://openalex.org/W2079247031","https://openalex.org/W2097381042","https://openalex.org/W2109910161","https://openalex.org/W2119567691","https://openalex.org/W2123990218","https://openalex.org/W2149933564","https://openalex.org/W2156737235","https://openalex.org/W2164114810","https://openalex.org/W2165698076","https://openalex.org/W2174786457","https://openalex.org/W2282350268","https://openalex.org/W2293521724","https://openalex.org/W2395579298","https://openalex.org/W2594829461","https://openalex.org/W2949267040","https://openalex.org/W2962817122","https://openalex.org/W2963168418","https://openalex.org/W2964227312","https://openalex.org/W2964262254","https://openalex.org/W4255421341","https://openalex.org/W4287750003","https://openalex.org/W4298023569","https://openalex.org/W4298174377","https://openalex.org/W4299518610","https://openalex.org/W4300065704","https://openalex.org/W6629461247","https://openalex.org/W6633949838","https://openalex.org/W6636553048","https://openalex.org/W6638398152","https://openalex.org/W6674600207","https://openalex.org/W6678550980","https://openalex.org/W6682132143","https://openalex.org/W6683195989","https://openalex.org/W6685726866","https://openalex.org/W6695303531","https://openalex.org/W6727349600","https://openalex.org/W6727623491","https://openalex.org/W6732837357","https://openalex.org/W6734215269","https://openalex.org/W6738637145","https://openalex.org/W6780856455"],"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/W2024136090","https://openalex.org/W2964765435","https://openalex.org/W2585069576"],"abstract_inverted_index":{"Transfer":[0],"reinforcement":[1,16],"learning":[2,17],"(TRL)":[3],"algorithms":[4],"have":[5,102],"achieved":[6],"success":[7],"on":[8,26],"alleviating":[9],"the":[10,31,58,75,79,82,86,95,110,123,144,152,166],"resource-consumption":[11],"and":[12,36,66,78,137,165,182],"sample-insufficiency":[13],"problem":[14],"in":[15,53,74,85,97,114,135],"(RL).":[18],"Existing":[19],"works":[20],"of":[21,34,60,81,112,147,154],"cross-domain":[22],"TRL":[23,44],"mainly":[24],"focus":[25],"designing":[27],"a":[28,42],"mapping":[29,62],"between":[30,64],"state-action":[32],"space":[33],"source":[35,65,76],"target":[37,67,98,115],"domains.":[38,116],"We,":[39],"however,":[40],"propose":[41],"novel":[43,49],"framework,":[45],"Feature-Option-Action":[46],"(FOA),":[47],"with":[48,122,160],"neural":[50,87],"network":[51,88],"architecture":[52],"this":[54,140],"work,":[55],"to":[56,93,177],"avoid":[57],"design":[59],"explicit":[61],"functions":[63],"domain.":[68,99],"FOA":[69,120,148,175],"learner":[70],"is":[71],"normally":[72],"trained":[73],"domain,":[77],"parameters":[80],"option":[83],"components":[84],"would":[89],"then":[90],"be":[91],"used":[92,134],"initialize":[94],"learners":[96,113],"Empirical":[100],"evidences":[101],"shown":[103],"that":[104,139,169],"our":[105,128],"technique":[106],"could":[107],"significantly":[108],"improve":[109,143],"performance":[111],"Meanwhile,":[117],"we":[118,130],"train":[119],"models":[121,149],"model":[124,162,176],"updating":[125,163],"methods":[126],"(in":[127],"works,":[129],"call":[131],"it":[132],"step-update)":[133],"Option-Critic,":[136],"illustrate":[138],"method":[141,171],"can":[142],"exploration":[145],"ability":[146],"by":[150],"increasing":[151],"diversity":[153],"options.":[155],"We":[156],"also":[157],"compare":[158],"step-update":[159,170],"other":[161],"methods,":[164],"results":[167],"show":[168],"performs":[172],"better":[173],"for":[174],"make":[178],"transfer":[179],"training":[180],"faster":[181],"smoother.":[183]},"counts_by_year":[{"year":2024,"cited_by_count":1},{"year":2023,"cited_by_count":3},{"year":2022,"cited_by_count":2}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}