{"id":"https://openalex.org/W4388470016","doi":"https://doi.org/10.1109/tnnls.2023.3322591","title":"EASpace: Enhanced Action Space for Policy Transfer","display_name":"EASpace: Enhanced Action Space for Policy Transfer","publication_year":2023,"publication_date":"2023-11-07","ids":{"openalex":"https://openalex.org/W4388470016","doi":"https://doi.org/10.1109/tnnls.2023.3322591","pmid":"https://pubmed.ncbi.nlm.nih.gov/37934635"},"language":"en","primary_location":{"id":"doi:10.1109/tnnls.2023.3322591","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tnnls.2023.3322591","pdf_url":null,"source":{"id":"https://openalex.org/S4210175523","display_name":"IEEE Transactions on Neural Networks and Learning Systems","issn_l":"2162-237X","issn":["2162-237X","2162-2388"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Transactions on Neural Networks and Learning Systems","raw_type":"journal-article"},"type":"article","indexed_in":["crossref","pubmed"],"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/A5100360209","display_name":"Zheng Zhang","orcid":"https://orcid.org/0000-0001-6674-6495"},"institutions":[{"id":"https://openalex.org/I157773358","display_name":"Sun Yat-sen University","ror":"https://ror.org/0064kty71","country_code":"CN","type":"education","lineage":["https://openalex.org/I157773358"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Zheng Zhang","raw_affiliation_strings":["School of Aeronautics and Astronautics, Sun Yat-sen University, Shenzhen, China"],"affiliations":[{"raw_affiliation_string":"School of Aeronautics and Astronautics, Sun Yat-sen University, Shenzhen, China","institution_ids":["https://openalex.org/I157773358"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5064825247","display_name":"Qingrui Zhang","orcid":"https://orcid.org/0000-0002-1733-159X"},"institutions":[{"id":"https://openalex.org/I157773358","display_name":"Sun Yat-sen University","ror":"https://ror.org/0064kty71","country_code":"CN","type":"education","lineage":["https://openalex.org/I157773358"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Qingrui Zhang","raw_affiliation_strings":["School of Aeronautics and Astronautics, Sun Yat-sen University, Shenzhen, China"],"affiliations":[{"raw_affiliation_string":"School of Aeronautics and Astronautics, Sun Yat-sen University, Shenzhen, China","institution_ids":["https://openalex.org/I157773358"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100619750","display_name":"Bo Zhu","orcid":"https://orcid.org/0000-0001-9817-3855"},"institutions":[{"id":"https://openalex.org/I157773358","display_name":"Sun Yat-sen University","ror":"https://ror.org/0064kty71","country_code":"CN","type":"education","lineage":["https://openalex.org/I157773358"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Bo Zhu","raw_affiliation_strings":["School of Aeronautics and Astronautics, Sun Yat-sen University, Shenzhen, China"],"affiliations":[{"raw_affiliation_string":"School of Aeronautics and Astronautics, Sun Yat-sen University, Shenzhen, China","institution_ids":["https://openalex.org/I157773358"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100354379","display_name":"Xiaohan Wang","orcid":"https://orcid.org/0000-0001-8493-8773"},"institutions":[{"id":"https://openalex.org/I157773358","display_name":"Sun Yat-sen University","ror":"https://ror.org/0064kty71","country_code":"CN","type":"education","lineage":["https://openalex.org/I157773358"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xiaohan Wang","raw_affiliation_strings":["School of Aeronautics and Astronautics, Sun Yat-sen University, Shenzhen, China"],"affiliations":[{"raw_affiliation_string":"School of Aeronautics and Astronautics, Sun Yat-sen University, Shenzhen, China","institution_ids":["https://openalex.org/I157773358"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5076233549","display_name":"Tianjiang Hu","orcid":"https://orcid.org/0000-0002-0587-6752"},"institutions":[{"id":"https://openalex.org/I157773358","display_name":"Sun Yat-sen University","ror":"https://ror.org/0064kty71","country_code":"CN","type":"education","lineage":["https://openalex.org/I157773358"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Tianjiang Hu","raw_affiliation_strings":["School of Aeronautics and Astronautics, Sun Yat-sen University, Shenzhen, China"],"affiliations":[{"raw_affiliation_string":"School of Aeronautics and Astronautics, Sun Yat-sen University, Shenzhen, China","institution_ids":["https://openalex.org/I157773358"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":5,"corresponding_author_ids":["https://openalex.org/A5100360209"],"corresponding_institution_ids":["https://openalex.org/I157773358"],"apc_list":null,"apc_paid":null,"fwci":0.174,"has_fulltext":false,"cited_by_count":1,"citation_normalized_percentile":{"value":0.58117956,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":91,"max":95},"biblio":{"volume":"36","issue":"1","first_page":"1272","last_page":"1286"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10462","display_name":"Reinforcement Learning in Robotics","score":0.9771000146865845,"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":0.9771000146865845,"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/T10270","display_name":"Blockchain Technology Applications and Security","score":0.9194999933242798,"subfield":{"id":"https://openalex.org/subfields/1710","display_name":"Information Systems"},"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/T11181","display_name":"Advanced Data Storage Technologies","score":0.9075000286102295,"subfield":{"id":"https://openalex.org/subfields/1705","display_name":"Computer Networks and Communications"},"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/macro","display_name":"Macro","score":0.8921748995780945},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.759289562702179},{"id":"https://openalex.org/keywords/action","display_name":"Action (physics)","score":0.6748248338699341},{"id":"https://openalex.org/keywords/process","display_name":"Process (computing)","score":0.6434319019317627},{"id":"https://openalex.org/keywords/space","display_name":"Space (punctuation)","score":0.531448483467102},{"id":"https://openalex.org/keywords/convergence","display_name":"Convergence (economics)","score":0.45664945244789124},{"id":"https://openalex.org/keywords/mathematical-optimization","display_name":"Mathematical optimization","score":0.406908243894577},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.3905700445175171},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.35204601287841797},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.12047797441482544},{"id":"https://openalex.org/keywords/economics","display_name":"Economics","score":0.09204700589179993}],"concepts":[{"id":"https://openalex.org/C166955791","wikidata":"https://www.wikidata.org/wiki/Q629579","display_name":"Macro","level":2,"score":0.8921748995780945},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.759289562702179},{"id":"https://openalex.org/C2780791683","wikidata":"https://www.wikidata.org/wiki/Q846785","display_name":"Action (physics)","level":2,"score":0.6748248338699341},{"id":"https://openalex.org/C98045186","wikidata":"https://www.wikidata.org/wiki/Q205663","display_name":"Process (computing)","level":2,"score":0.6434319019317627},{"id":"https://openalex.org/C2778572836","wikidata":"https://www.wikidata.org/wiki/Q380933","display_name":"Space (punctuation)","level":2,"score":0.531448483467102},{"id":"https://openalex.org/C2777303404","wikidata":"https://www.wikidata.org/wiki/Q759757","display_name":"Convergence (economics)","level":2,"score":0.45664945244789124},{"id":"https://openalex.org/C126255220","wikidata":"https://www.wikidata.org/wiki/Q141495","display_name":"Mathematical optimization","level":1,"score":0.406908243894577},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3905700445175171},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.35204601287841797},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.12047797441482544},{"id":"https://openalex.org/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","level":0,"score":0.09204700589179993},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.0},{"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/C50522688","wikidata":"https://www.wikidata.org/wiki/Q189833","display_name":"Economic growth","level":1,"score":0.0},{"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/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/tnnls.2023.3322591","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tnnls.2023.3322591","pdf_url":null,"source":{"id":"https://openalex.org/S4210175523","display_name":"IEEE Transactions on Neural Networks and Learning Systems","issn_l":"2162-237X","issn":["2162-237X","2162-2388"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Transactions on Neural Networks and Learning Systems","raw_type":"journal-article"},{"id":"pmid:37934635","is_oa":false,"landing_page_url":"https://pubmed.ncbi.nlm.nih.gov/37934635","pdf_url":null,"source":{"id":"https://openalex.org/S4306525036","display_name":"PubMed","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I1299303238","host_organization_name":"National Institutes of Health","host_organization_lineage":["https://openalex.org/I1299303238"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE transactions on neural networks and learning systems","raw_type":null}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G461659314","display_name":null,"funder_award_id":"62373386","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G699479682","display_name":null,"funder_award_id":"62103451","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G7820711889","display_name":null,"funder_award_id":"61973327","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":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":56,"referenced_works":["https://openalex.org/W106792269","https://openalex.org/W1520148289","https://openalex.org/W1608481154","https://openalex.org/W2031727428","https://openalex.org/W2082247780","https://openalex.org/W2109910161","https://openalex.org/W2113286054","https://openalex.org/W2124477018","https://openalex.org/W2567811016","https://openalex.org/W2581240229","https://openalex.org/W2604618034","https://openalex.org/W2760355785","https://openalex.org/W2768629321","https://openalex.org/W2788862220","https://openalex.org/W2792645523","https://openalex.org/W2886885155","https://openalex.org/W2902024803","https://openalex.org/W2963523627","https://openalex.org/W2963761387","https://openalex.org/W2964227312","https://openalex.org/W2971481292","https://openalex.org/W3034815680","https://openalex.org/W3041133507","https://openalex.org/W3043763914","https://openalex.org/W3134939669","https://openalex.org/W3171453668","https://openalex.org/W3174733757","https://openalex.org/W3183210514","https://openalex.org/W3195143297","https://openalex.org/W3216884019","https://openalex.org/W4221155562","https://openalex.org/W4233061323","https://openalex.org/W4283790957","https://openalex.org/W4383112908","https://openalex.org/W6616173779","https://openalex.org/W6638088447","https://openalex.org/W6682802936","https://openalex.org/W6683821272","https://openalex.org/W6684159546","https://openalex.org/W6685444567","https://openalex.org/W6685726866","https://openalex.org/W6691230391","https://openalex.org/W6703271639","https://openalex.org/W6712392314","https://openalex.org/W6718190810","https://openalex.org/W6719360576","https://openalex.org/W6732837357","https://openalex.org/W6734215269","https://openalex.org/W6740879895","https://openalex.org/W6751720535","https://openalex.org/W6751794878","https://openalex.org/W6752089545","https://openalex.org/W6761754428","https://openalex.org/W6765166828","https://openalex.org/W6775683342","https://openalex.org/W6922480057"],"related_works":["https://openalex.org/W2030816003","https://openalex.org/W2076325756","https://openalex.org/W81423522","https://openalex.org/W1509860481","https://openalex.org/W2150013480","https://openalex.org/W1989362889","https://openalex.org/W4386206750","https://openalex.org/W1605713622","https://openalex.org/W2186928467","https://openalex.org/W2183526291"],"abstract_inverted_index":{"Formulating":[0],"expert":[1,71,77],"policies":[2],"as":[3],"macro":[4,30,39,56,81,89,111,121],"actions":[5,57,82,90],"promises":[6],"to":[7,62,106,115,130,135,144,177],"alleviate":[8],"the":[9,64,88,95,107,117,137,146,149],"long-horizon":[10],"issue":[11],"via":[12],"structured":[13],"exploration":[14,28],"and":[15,33,163],"efficient":[16],"credit":[17],"assignment.":[18],"However,":[19],"traditional":[20],"option-based":[21],"multipolicy":[22],"transfer":[23],"methods":[24],"suffer":[25],"from":[26],"inefficient":[27],"of":[29,36,110,119,148,155],"action's":[31],"length":[32],"insufficient":[34],"exploitation":[35,118],"useful":[37,120],"long-duration":[38],"actions.":[40,122],"In":[41],"this":[42],"article,":[43],"a":[44,160,164],"novel":[45],"algorithm":[46,170],"named":[47],"enhanced":[48],"action":[49,97],"space":[50,98],"(EASpace)":[51],"is":[52,104,113,128,133,142,157,171],"proposed,":[53],"which":[54,103],"formulates":[55,75],"in":[58,174],"an":[59],"alternative":[60],"form":[61],"accelerate":[63],"learning":[65,125,151],"process":[66],"using":[67],"multiple":[68,80],"available":[69],"suboptimal":[70],"policies.":[72],"Specifically,":[73],"EASpace":[74,156],"each":[76],"policy":[78],"into":[79,94],"with":[83],"different":[84],"execution":[85,108],"times.":[86],"All":[87],"are":[91],"then":[92],"integrated":[93],"primitive":[96],"directly.":[99],"An":[100],"intrinsic":[101],"reward,":[102],"proportional":[105],"time":[109],"actions,":[112],"introduced":[114],"encourage":[116],"The":[123,153,168],"corresponding":[124],"rule":[126],"that":[127],"similar":[129],"intraoption":[131],"Q-learning":[132],"employed":[134],"improve":[136],"data":[138],"efficiency.":[139],"Theoretical":[140],"analysis":[141],"presented":[143],"show":[145],"convergence":[147],"proposed":[150,169],"rule.":[152],"efficiency":[154],"illustrated":[158],"by":[159],"grid-based":[161],"game":[162],"multiagent":[165],"pursuit":[166],"problem.":[167],"also":[172],"implemented":[173],"physical":[175],"systems":[176],"validate":[178],"its":[179],"effectiveness.":[180]},"counts_by_year":[{"year":2025,"cited_by_count":1}],"updated_date":"2026-03-27T05:58:40.876381","created_date":"2025-10-10T00:00:00"}