{"id":"https://openalex.org/W4402353565","doi":"https://doi.org/10.1109/ijcnn60899.2024.10651458","title":"Extraction and Transfer of General Deep Feature in Reinforcement Learning","display_name":"Extraction and Transfer of General Deep Feature in Reinforcement Learning","publication_year":2024,"publication_date":"2024-06-30","ids":{"openalex":"https://openalex.org/W4402353565","doi":"https://doi.org/10.1109/ijcnn60899.2024.10651458"},"language":"en","primary_location":{"id":"doi:10.1109/ijcnn60899.2024.10651458","is_oa":false,"landing_page_url":"http://dx.doi.org/10.1109/ijcnn60899.2024.10651458","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2024 International Joint Conference on Neural Networks (IJCNN)","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/A5108153997","display_name":"Min Chen","orcid":null},"institutions":[{"id":"https://openalex.org/I4210112150","display_name":"Institute of Automation","ror":"https://ror.org/022c3hy66","country_code":"CN","type":"facility","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210112150"]},{"id":"https://openalex.org/I19820366","display_name":"Chinese Academy of Sciences","ror":"https://ror.org/034t30j35","country_code":"CN","type":"funder","lineage":["https://openalex.org/I19820366"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Min Chen","raw_affiliation_strings":["Chinese Academy of Sciences,Institute of Automation,Beijing,China,100190"],"affiliations":[{"raw_affiliation_string":"Chinese Academy of Sciences,Institute of Automation,Beijing,China,100190","institution_ids":["https://openalex.org/I4210112150","https://openalex.org/I19820366"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5102234458","display_name":"Yi Pan","orcid":"https://orcid.org/0009-0009-5417-6013"},"institutions":[{"id":"https://openalex.org/I19820366","display_name":"Chinese Academy of Sciences","ror":"https://ror.org/034t30j35","country_code":"CN","type":"funder","lineage":["https://openalex.org/I19820366"]},{"id":"https://openalex.org/I4210112150","display_name":"Institute of Automation","ror":"https://ror.org/022c3hy66","country_code":"CN","type":"facility","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210112150"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yi Pan","raw_affiliation_strings":["Chinese Academy of Sciences,Institute of Automation,Beijing,China,100190"],"affiliations":[{"raw_affiliation_string":"Chinese Academy of Sciences,Institute of Automation,Beijing,China,100190","institution_ids":["https://openalex.org/I4210112150","https://openalex.org/I19820366"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5060319097","display_name":"Zhiqiang Pu","orcid":"https://orcid.org/0000-0002-4841-4048"},"institutions":[{"id":"https://openalex.org/I4210112150","display_name":"Institute of Automation","ror":"https://ror.org/022c3hy66","country_code":"CN","type":"facility","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210112150"]},{"id":"https://openalex.org/I19820366","display_name":"Chinese Academy of Sciences","ror":"https://ror.org/034t30j35","country_code":"CN","type":"funder","lineage":["https://openalex.org/I19820366"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zhiqiang Pu","raw_affiliation_strings":["Chinese Academy of Sciences,Institute of Automation,Beijing,China,100190"],"affiliations":[{"raw_affiliation_string":"Chinese Academy of Sciences,Institute of Automation,Beijing,China,100190","institution_ids":["https://openalex.org/I4210112150","https://openalex.org/I19820366"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5019541846","display_name":"Jianqiang Yi","orcid":"https://orcid.org/0000-0003-3268-9482"},"institutions":[{"id":"https://openalex.org/I4210112150","display_name":"Institute of Automation","ror":"https://ror.org/022c3hy66","country_code":"CN","type":"facility","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210112150"]},{"id":"https://openalex.org/I19820366","display_name":"Chinese Academy of Sciences","ror":"https://ror.org/034t30j35","country_code":"CN","type":"funder","lineage":["https://openalex.org/I19820366"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jianqiang Yi","raw_affiliation_strings":["Chinese Academy of Sciences,Institute of Automation,Beijing,China,100190"],"affiliations":[{"raw_affiliation_string":"Chinese Academy of Sciences,Institute of Automation,Beijing,China,100190","institution_ids":["https://openalex.org/I4210112150","https://openalex.org/I19820366"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5090380831","display_name":"Shijie Wang","orcid":"https://orcid.org/0000-0001-8429-9449"},"institutions":[{"id":"https://openalex.org/I4210112150","display_name":"Institute of Automation","ror":"https://ror.org/022c3hy66","country_code":"CN","type":"facility","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210112150"]},{"id":"https://openalex.org/I19820366","display_name":"Chinese Academy of Sciences","ror":"https://ror.org/034t30j35","country_code":"CN","type":"funder","lineage":["https://openalex.org/I19820366"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Shijie Wang","raw_affiliation_strings":["Chinese Academy of Sciences,Institute of Automation,Beijing,China,100190"],"affiliations":[{"raw_affiliation_string":"Chinese Academy of Sciences,Institute of Automation,Beijing,China,100190","institution_ids":["https://openalex.org/I4210112150","https://openalex.org/I19820366"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5000412491","display_name":"Boyin Liu","orcid":null},"institutions":[{"id":"https://openalex.org/I4210112150","display_name":"Institute of Automation","ror":"https://ror.org/022c3hy66","country_code":"CN","type":"facility","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210112150"]},{"id":"https://openalex.org/I19820366","display_name":"Chinese Academy of Sciences","ror":"https://ror.org/034t30j35","country_code":"CN","type":"funder","lineage":["https://openalex.org/I19820366"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Boyin Liu","raw_affiliation_strings":["Chinese Academy of Sciences,Institute of Automation,Beijing,China,100190"],"affiliations":[{"raw_affiliation_string":"Chinese Academy of Sciences,Institute of Automation,Beijing,China,100190","institution_ids":["https://openalex.org/I4210112150","https://openalex.org/I19820366"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":6,"corresponding_author_ids":["https://openalex.org/A5108153997"],"corresponding_institution_ids":["https://openalex.org/I19820366","https://openalex.org/I4210112150"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.12982222,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":"21","issue":null,"first_page":"1","last_page":"8"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10462","display_name":"Reinforcement Learning in Robotics","score":0.9993000030517578,"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":0.9993000030517578,"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/T10653","display_name":"Robot Manipulation and Learning","score":0.9973999857902527,"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/T10879","display_name":"Robotic Locomotion and Control","score":0.9692000150680542,"subfield":{"id":"https://openalex.org/subfields/2204","display_name":"Biomedical 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":0.7218831777572632},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.6991368532180786},{"id":"https://openalex.org/keywords/feature-extraction","display_name":"Feature extraction","score":0.6883524060249329},{"id":"https://openalex.org/keywords/transfer-of-learning","display_name":"Transfer of learning","score":0.6430889964103699},{"id":"https://openalex.org/keywords/reinforcement-learning","display_name":"Reinforcement learning","score":0.5833746194839478},{"id":"https://openalex.org/keywords/extraction","display_name":"Extraction (chemistry)","score":0.4869188070297241},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.47398748993873596},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.46015504002571106},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.3249134421348572},{"id":"https://openalex.org/keywords/chromatography","display_name":"Chromatography","score":0.10167893767356873},{"id":"https://openalex.org/keywords/chemistry","display_name":"Chemistry","score":0.0533481240272522}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7218831777572632},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6991368532180786},{"id":"https://openalex.org/C52622490","wikidata":"https://www.wikidata.org/wiki/Q1026626","display_name":"Feature extraction","level":2,"score":0.6883524060249329},{"id":"https://openalex.org/C150899416","wikidata":"https://www.wikidata.org/wiki/Q1820378","display_name":"Transfer of learning","level":2,"score":0.6430889964103699},{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.5833746194839478},{"id":"https://openalex.org/C4725764","wikidata":"https://www.wikidata.org/wiki/Q844704","display_name":"Extraction (chemistry)","level":2,"score":0.4869188070297241},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.47398748993873596},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.46015504002571106},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.3249134421348572},{"id":"https://openalex.org/C43617362","wikidata":"https://www.wikidata.org/wiki/Q170050","display_name":"Chromatography","level":1,"score":0.10167893767356873},{"id":"https://openalex.org/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","level":0,"score":0.0533481240272522},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/ijcnn60899.2024.10651458","is_oa":false,"landing_page_url":"http://dx.doi.org/10.1109/ijcnn60899.2024.10651458","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2024 International Joint Conference on Neural Networks (IJCNN)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"},{"id":"https://openalex.org/F4320321133","display_name":"Chinese Academy of Sciences","ror":"https://ror.org/034t30j35"},{"id":"https://openalex.org/F4320326444","display_name":"Nova","ror":null}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":36,"referenced_works":["https://openalex.org/W1191599655","https://openalex.org/W1986014385","https://openalex.org/W2022638422","https://openalex.org/W2747213132","https://openalex.org/W2766447205","https://openalex.org/W2794908222","https://openalex.org/W2963802910","https://openalex.org/W2982316857","https://openalex.org/W2989696291","https://openalex.org/W2997502221","https://openalex.org/W3012544020","https://openalex.org/W3035173916","https://openalex.org/W3092609815","https://openalex.org/W3138984732","https://openalex.org/W4223908421","https://openalex.org/W4286748781","https://openalex.org/W4287078276","https://openalex.org/W4287864064","https://openalex.org/W4298857966","https://openalex.org/W4300198501","https://openalex.org/W4383109329","https://openalex.org/W6627932998","https://openalex.org/W6637967152","https://openalex.org/W6639480849","https://openalex.org/W6732417791","https://openalex.org/W6751955673","https://openalex.org/W6752601656","https://openalex.org/W6770722459","https://openalex.org/W6774065826","https://openalex.org/W6775683342","https://openalex.org/W6779313190","https://openalex.org/W6780114599","https://openalex.org/W6791000347","https://openalex.org/W6798316476","https://openalex.org/W6809583738","https://openalex.org/W6840380725"],"related_works":["https://openalex.org/W4306904969","https://openalex.org/W2138720691","https://openalex.org/W4362501864","https://openalex.org/W4380318855","https://openalex.org/W2031695474","https://openalex.org/W2024136090","https://openalex.org/W2586732548","https://openalex.org/W3049728571","https://openalex.org/W2964765435","https://openalex.org/W4391331176"],"abstract_inverted_index":{"Knowledge":[0],"transfer":[1,56],"from":[2,18],"teacher":[3,34],"agent":[4,7],"to":[5,45,140],"student":[6,93],"in":[8,42,95,102],"reinforcement":[9],"learning":[10,76,120],"addresses":[11],"the":[12,27,61,89,119,130,133,136,148,151],"issue":[13],"of":[14,33,64,122,132,150],"sample":[15],"inefficiency":[16],"resulting":[17],"random":[19],"exploration.":[20],"However,":[21],"existing":[22],"approaches":[23],"usually":[24],"assume":[25],"that":[26,114],"policy":[28],"or":[29],"state-action":[30],"pairs":[31],"(demonstrations)":[32],"is":[35],"accessible,":[36],"which":[37],"may":[38],"not":[39],"be":[40],"met":[41],"reality":[43],"due":[44],"privacy":[46],"and":[47,79,87,105,124,144],"other":[48],"limitations.":[49],"This":[50],"paper":[51],"proposes":[52],"a":[53],"novel":[54],"knowledge":[55],"method":[57,101,116],"based":[58,83],"solely":[59],"on":[60,84],"state":[62,70,77],"sequences":[63],"teacher.":[65],"Specifically,":[66],"We":[67,98],"encode":[68],"raw":[69],"into":[71],"general":[72],"deep":[73],"feature":[74,137],"through":[75],"evaluation":[78],"domain":[80],"discrimination":[81],"tasks":[82],"teachers\u2019":[85,141],"experience,":[86],"share":[88],"encoder":[90],"among":[91],"different":[92],"agents":[94,123],"various":[96],"scenarios.":[97],"validate":[99],"our":[100,115],"Starcraft":[103],"II":[104],"Google":[106],"Research":[107],"Football":[108],"environment.":[109],"The":[110],"experimental":[111],"results":[112],"show":[113],"significantly":[117],"accelerates":[118],"process":[121],"improves":[125],"their":[126],"convergence":[127],"performance,":[128],"showcasing":[129],"\"depth\"":[131],"feature.":[134,152],"Additionally,":[135],"successfully":[138],"generalize":[139],"unseen":[142],"scenarios":[143],"unfamiliar":[145],"roles,":[146],"demonstrating":[147],"\"generality\"":[149]},"counts_by_year":[],"updated_date":"2025-12-22T23:10:17.713674","created_date":"2025-10-10T00:00:00"}