{"id":"https://openalex.org/W4402352359","doi":"https://doi.org/10.1109/ijcnn60899.2024.10651412","title":"Online Policy Distillation with Decision-Attention","display_name":"Online Policy Distillation with Decision-Attention","publication_year":2024,"publication_date":"2024-06-30","ids":{"openalex":"https://openalex.org/W4402352359","doi":"https://doi.org/10.1109/ijcnn60899.2024.10651412"},"language":"en","primary_location":{"id":"doi:10.1109/ijcnn60899.2024.10651412","is_oa":false,"landing_page_url":"http://dx.doi.org/10.1109/ijcnn60899.2024.10651412","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/A5112942734","display_name":"Xinqiang Yu","orcid":null},"institutions":[{"id":"https://openalex.org/I4210090176","display_name":"Institute of Computing Technology","ror":"https://ror.org/0090r4d87","country_code":"CN","type":"facility","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210090176"]},{"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":"Xinqiang Yu","raw_affiliation_strings":["Chinese Academy of Sciences,Institute of Computing Technology,Beijing,China"],"affiliations":[{"raw_affiliation_string":"Chinese Academy of Sciences,Institute of Computing Technology,Beijing,China","institution_ids":["https://openalex.org/I4210090176","https://openalex.org/I19820366"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5102298480","display_name":"Chuanguang Yang","orcid":null},"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/I4210090176","display_name":"Institute of Computing Technology","ror":"https://ror.org/0090r4d87","country_code":"CN","type":"facility","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210090176"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Chuanguang Yang","raw_affiliation_strings":["Chinese Academy of Sciences,Institute of Computing Technology,Beijing,China"],"affiliations":[{"raw_affiliation_string":"Chinese Academy of Sciences,Institute of Computing Technology,Beijing,China","institution_ids":["https://openalex.org/I4210090176","https://openalex.org/I19820366"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100595911","display_name":"Chengqing Yu","orcid":null},"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/I4210090176","display_name":"Institute of Computing Technology","ror":"https://ror.org/0090r4d87","country_code":"CN","type":"facility","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210090176"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Chengqing Yu","raw_affiliation_strings":["Chinese Academy of Sciences,Institute of Computing Technology,Beijing,China"],"affiliations":[{"raw_affiliation_string":"Chinese Academy of Sciences,Institute of Computing Technology,Beijing,China","institution_ids":["https://openalex.org/I4210090176","https://openalex.org/I19820366"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5018319708","display_name":"Libo Huang","orcid":"https://orcid.org/0000-0002-4479-5840"},"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/I4210090176","display_name":"Institute of Computing Technology","ror":"https://ror.org/0090r4d87","country_code":"CN","type":"facility","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210090176"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Libo Huang","raw_affiliation_strings":["Chinese Academy of Sciences,Institute of Computing Technology,Beijing,China"],"affiliations":[{"raw_affiliation_string":"Chinese Academy of Sciences,Institute of Computing Technology,Beijing,China","institution_ids":["https://openalex.org/I4210090176","https://openalex.org/I19820366"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5055016576","display_name":"Zhulin An","orcid":"https://orcid.org/0000-0002-7593-8293"},"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/I4210090176","display_name":"Institute of Computing Technology","ror":"https://ror.org/0090r4d87","country_code":"CN","type":"facility","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210090176"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zhulin An","raw_affiliation_strings":["Chinese Academy of Sciences,Institute of Computing Technology,Beijing,China"],"affiliations":[{"raw_affiliation_string":"Chinese Academy of Sciences,Institute of Computing Technology,Beijing,China","institution_ids":["https://openalex.org/I4210090176","https://openalex.org/I19820366"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5103245119","display_name":"Yongjun Xu","orcid":"https://orcid.org/0000-0001-6647-0986"},"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/I4210090176","display_name":"Institute of Computing Technology","ror":"https://ror.org/0090r4d87","country_code":"CN","type":"facility","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210090176"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yongjun Xu","raw_affiliation_strings":["Chinese Academy of Sciences,Institute of Computing Technology,Beijing,China"],"affiliations":[{"raw_affiliation_string":"Chinese Academy of Sciences,Institute of Computing Technology,Beijing,China","institution_ids":["https://openalex.org/I4210090176","https://openalex.org/I19820366"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":6,"corresponding_author_ids":["https://openalex.org/A5112942734"],"corresponding_institution_ids":["https://openalex.org/I19820366","https://openalex.org/I4210090176"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.12926298,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":"31","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":0.9962999820709229,"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":0.9962999820709229,"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/T12101","display_name":"Advanced Bandit Algorithms Research","score":0.9901000261306763,"subfield":{"id":"https://openalex.org/subfields/1803","display_name":"Management Science and Operations Research"},"field":{"id":"https://openalex.org/fields/18","display_name":"Decision Sciences"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}},{"id":"https://openalex.org/T12761","display_name":"Data Stream Mining Techniques","score":0.9886999726295471,"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/distillation","display_name":"Distillation","score":0.6494698524475098},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.5964515209197998},{"id":"https://openalex.org/keywords/chemistry","display_name":"Chemistry","score":0.11673399806022644},{"id":"https://openalex.org/keywords/chromatography","display_name":"Chromatography","score":0.10484832525253296}],"concepts":[{"id":"https://openalex.org/C204030448","wikidata":"https://www.wikidata.org/wiki/Q101017","display_name":"Distillation","level":2,"score":0.6494698524475098},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5964515209197998},{"id":"https://openalex.org/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","level":0,"score":0.11673399806022644},{"id":"https://openalex.org/C43617362","wikidata":"https://www.wikidata.org/wiki/Q170050","display_name":"Chromatography","level":1,"score":0.10484832525253296}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/ijcnn60899.2024.10651412","is_oa":false,"landing_page_url":"http://dx.doi.org/10.1109/ijcnn60899.2024.10651412","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":[{"id":"https://metadata.un.org/sdg/16","score":0.5400000214576721,"display_name":"Peace, Justice and strong institutions"}],"awards":[],"funders":[{"id":"https://openalex.org/F4320321133","display_name":"Chinese Academy of Sciences","ror":"https://ror.org/034t30j35"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":44,"referenced_works":["https://openalex.org/W1690739335","https://openalex.org/W1821462560","https://openalex.org/W2101786389","https://openalex.org/W2121863487","https://openalex.org/W2620998106","https://openalex.org/W2731516819","https://openalex.org/W2736601468","https://openalex.org/W2747909401","https://openalex.org/W2807912816","https://openalex.org/W2896457183","https://openalex.org/W2912185124","https://openalex.org/W2993790416","https://openalex.org/W2996970889","https://openalex.org/W2997006708","https://openalex.org/W2997471409","https://openalex.org/W3023213286","https://openalex.org/W3034225898","https://openalex.org/W3103559770","https://openalex.org/W3136021864","https://openalex.org/W3159551428","https://openalex.org/W3163825800","https://openalex.org/W3192946406","https://openalex.org/W3198500549","https://openalex.org/W4213019189","https://openalex.org/W4298857966","https://openalex.org/W4312309807","https://openalex.org/W4313182973","https://openalex.org/W4313426025","https://openalex.org/W4327662218","https://openalex.org/W4380479950","https://openalex.org/W4382239046","https://openalex.org/W4385245566","https://openalex.org/W4387848755","https://openalex.org/W4393159688","https://openalex.org/W6637551013","https://openalex.org/W6637967152","https://openalex.org/W6638523607","https://openalex.org/W6732665253","https://openalex.org/W6732837357","https://openalex.org/W6740493225","https://openalex.org/W6741002519","https://openalex.org/W6755207826","https://openalex.org/W6781328791","https://openalex.org/W6847363464"],"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":{"Policy":[0,75],"Distillation":[1,76],"(PD)":[2],"has":[3],"become":[4],"an":[5,81,206],"effective":[6],"method":[7,201],"to":[8,20,28,94,104,107,131,140,155,174],"improve":[9],"deep":[10],"reinforcement":[11,190],"learning":[12,83,191],"tasks.":[13],"The":[14,161],"core":[15],"idea":[16],"of":[17,48,98,115,169,178],"PD":[18],"is":[19,42],"distill":[21],"policy":[22,173,209],"knowledge":[23,50,55,64,103,130,223],"from":[24,65],"a":[25,29,37,116,124,166],"teacher":[26,39,118],"agent":[27],"student":[30,133,142],"agent.":[31],"However,":[32,135],"the":[33,46,54,66,91,99,113,120,148,152,156,176,183],"teacher-student":[34],"framework":[35,84],"requires":[36],"well-trained":[38],"model":[40],"which":[41,86],"computationally":[43],"expensive.":[44],"In":[45,69,197],"light":[47],"online":[49,82,157],"distillation,":[51],"we":[52,72,150],"study":[53],"transfer":[56,102,222],"between":[57,224],"different":[58,87,96,198,225],"policies":[59,88,143,158,226],"that":[60,218],"can":[61,164,202,221],"learn":[62,95],"diverse":[63],"same":[67,92],"environment.":[68],"this":[70],"work,":[71],"propose":[73],"Online":[74],"(OPD)":[77],"with":[78,188],"Decision-Attention":[79,153,162],"(DA),":[80],"in":[85,90,127],"operate":[89],"environment":[93,100],"perspectives":[97],"and":[101,195,213,228],"each":[105,132,172],"other":[106],"obtain":[108,231],"better":[109,204],"performance":[110],"together.":[111],"With":[112],"absence":[114],"well-performance":[117],"policy,":[119],"group-derived":[121],"targets":[122],"play":[123],"key":[125],"role":[126],"transferring":[128],"group":[129,179],"policy.":[134],"naive":[136],"aggregation":[137],"functions":[138],"tend":[139],"cause":[141],"quickly":[144],"homogenize.":[145],"To":[146],"address":[147],"challenge,":[149],"introduce":[151],"module":[154,163],"distillation":[159],"framework.":[160],"generate":[165],"distinct":[167],"set":[168],"weights":[170],"for":[171,186],"measure":[175],"importance":[177],"members.":[180],"We":[181],"use":[182],"Atari":[184],"platform":[185],"experiments":[187],"various":[189],"algorithms,":[192],"including":[193],"PPO":[194,212],"DQN.":[196],"tasks,":[199],"our":[200,219],"perform":[203],"than":[205],"independent":[207],"training":[208],"on":[210],"both":[211],"DQN":[214],"algorithms.":[215],"This":[216],"suggests":[217],"OPD-DA":[220],"well":[227],"help":[229],"agents":[230],"more":[232],"rewards.":[233]},"counts_by_year":[],"updated_date":"2025-12-21T01:58:51.020947","created_date":"2025-10-10T00:00:00"}