{"id":"https://openalex.org/W4293518564","doi":"https://doi.org/10.1109/icme52920.2022.9859768","title":"Learn Effective Representation for Deep Reinforcement Learning","display_name":"Learn Effective Representation for Deep Reinforcement Learning","publication_year":2022,"publication_date":"2022-07-18","ids":{"openalex":"https://openalex.org/W4293518564","doi":"https://doi.org/10.1109/icme52920.2022.9859768"},"language":"en","primary_location":{"id":"doi:10.1109/icme52920.2022.9859768","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icme52920.2022.9859768","pdf_url":null,"source":{"id":"https://openalex.org/S4363607799","display_name":"2022 IEEE International Conference on Multimedia and Expo (ICME)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2022 IEEE International Conference on Multimedia and Expo (ICME)","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/A5100926694","display_name":"Yuan Zhan","orcid":null},"institutions":[{"id":"https://openalex.org/I19820366","display_name":"Chinese Academy of Sciences","ror":"https://ror.org/034t30j35","country_code":"CN","type":"government","lineage":["https://openalex.org/I19820366"]},{"id":"https://openalex.org/I4210165038","display_name":"University of Chinese Academy of Sciences","ror":"https://ror.org/05qbk4x57","country_code":"CN","type":"education","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210165038"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yuan Zhan","raw_affiliation_strings":["Institute of Automation, Chinese Academy of Sciences","University of Chinese Academy of Sciences, School of Artificial Intelligence"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Institute of Automation, Chinese Academy of Sciences","institution_ids":["https://openalex.org/I19820366"]},{"raw_affiliation_string":"University of Chinese Academy of Sciences, School of Artificial Intelligence","institution_ids":["https://openalex.org/I4210165038"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100628168","display_name":"Zhiwei Xu","orcid":"https://orcid.org/0000-0002-0754-5295"},"institutions":[{"id":"https://openalex.org/I19820366","display_name":"Chinese Academy of Sciences","ror":"https://ror.org/034t30j35","country_code":"CN","type":"government","lineage":["https://openalex.org/I19820366"]},{"id":"https://openalex.org/I4210165038","display_name":"University of Chinese Academy of Sciences","ror":"https://ror.org/05qbk4x57","country_code":"CN","type":"education","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210165038"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zhiwei Xu","raw_affiliation_strings":["Institute of Automation, Chinese Academy of Sciences","University of Chinese Academy of Sciences, School of Artificial Intelligence"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Institute of Automation, Chinese Academy of Sciences","institution_ids":["https://openalex.org/I19820366"]},{"raw_affiliation_string":"University of Chinese Academy of Sciences, School of Artificial Intelligence","institution_ids":["https://openalex.org/I4210165038"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5101572310","display_name":"Guoliang Fan","orcid":"https://orcid.org/0000-0003-2724-2432"},"institutions":[{"id":"https://openalex.org/I19820366","display_name":"Chinese Academy of Sciences","ror":"https://ror.org/034t30j35","country_code":"CN","type":"government","lineage":["https://openalex.org/I19820366"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Guoliang Fan","raw_affiliation_strings":["Institute of Automation, Chinese Academy of Sciences"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Institute of Automation, Chinese Academy of Sciences","institution_ids":["https://openalex.org/I19820366"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.2076,"has_fulltext":false,"cited_by_count":2,"citation_normalized_percentile":{"value":0.41457726,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":94},"biblio":{"volume":"abs 1510 2173","issue":null,"first_page":"1","last_page":"6"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10462","display_name":"Reinforcement Learning in Robotics","score":0.9998999834060669,"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":0.9998999834060669,"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/T11574","display_name":"Artificial Intelligence in Games","score":0.9904000163078308,"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":0.9649999737739563,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8162292242050171},{"id":"https://openalex.org/keywords/reinforcement-learning","display_name":"Reinforcement learning","score":0.8141651153564453},{"id":"https://openalex.org/keywords/bottleneck","display_name":"Bottleneck","score":0.7817736864089966},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.6427040696144104},{"id":"https://openalex.org/keywords/representation","display_name":"Representation (politics)","score":0.601380467414856},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.559906542301178},{"id":"https://openalex.org/keywords/feature-learning","display_name":"Feature learning","score":0.5502772331237793},{"id":"https://openalex.org/keywords/curse-of-dimensionality","display_name":"Curse of dimensionality","score":0.4996767044067383},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.4834795594215393},{"id":"https://openalex.org/keywords/encoder","display_name":"Encoder","score":0.48244720697402954},{"id":"https://openalex.org/keywords/extractor","display_name":"Extractor","score":0.4748808741569519},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.43797844648361206},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.06811141967773438}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8162292242050171},{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.8141651153564453},{"id":"https://openalex.org/C2780513914","wikidata":"https://www.wikidata.org/wiki/Q18210350","display_name":"Bottleneck","level":2,"score":0.7817736864089966},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6427040696144104},{"id":"https://openalex.org/C2776359362","wikidata":"https://www.wikidata.org/wiki/Q2145286","display_name":"Representation (politics)","level":3,"score":0.601380467414856},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.559906542301178},{"id":"https://openalex.org/C59404180","wikidata":"https://www.wikidata.org/wiki/Q17013334","display_name":"Feature learning","level":2,"score":0.5502772331237793},{"id":"https://openalex.org/C111030470","wikidata":"https://www.wikidata.org/wiki/Q1430460","display_name":"Curse of dimensionality","level":2,"score":0.4996767044067383},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.4834795594215393},{"id":"https://openalex.org/C118505674","wikidata":"https://www.wikidata.org/wiki/Q42586063","display_name":"Encoder","level":2,"score":0.48244720697402954},{"id":"https://openalex.org/C117978034","wikidata":"https://www.wikidata.org/wiki/Q5422192","display_name":"Extractor","level":2,"score":0.4748808741569519},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.43797844648361206},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.06811141967773438},{"id":"https://openalex.org/C21880701","wikidata":"https://www.wikidata.org/wiki/Q2144042","display_name":"Process engineering","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/C199539241","wikidata":"https://www.wikidata.org/wiki/Q7748","display_name":"Law","level":1,"score":0.0},{"id":"https://openalex.org/C17744445","wikidata":"https://www.wikidata.org/wiki/Q36442","display_name":"Political science","level":0,"score":0.0},{"id":"https://openalex.org/C149635348","wikidata":"https://www.wikidata.org/wiki/Q193040","display_name":"Embedded system","level":1,"score":0.0},{"id":"https://openalex.org/C94625758","wikidata":"https://www.wikidata.org/wiki/Q7163","display_name":"Politics","level":2,"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}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icme52920.2022.9859768","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icme52920.2022.9859768","pdf_url":null,"source":{"id":"https://openalex.org/S4363607799","display_name":"2022 IEEE International Conference on Multimedia and Expo (ICME)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2022 IEEE International Conference on Multimedia and Expo (ICME)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/4","display_name":"Quality Education","score":0.47999998927116394}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":44,"referenced_works":["https://openalex.org/W834081922","https://openalex.org/W1686946872","https://openalex.org/W1771410628","https://openalex.org/W1811843574","https://openalex.org/W2145339207","https://openalex.org/W2179072710","https://openalex.org/W2194775991","https://openalex.org/W2531409750","https://openalex.org/W2618530766","https://openalex.org/W2736601468","https://openalex.org/W2746553466","https://openalex.org/W2754517384","https://openalex.org/W2787666871","https://openalex.org/W2803832867","https://openalex.org/W2842511635","https://openalex.org/W2924131335","https://openalex.org/W2950872548","https://openalex.org/W2963446712","https://openalex.org/W2963523627","https://openalex.org/W2963987720","https://openalex.org/W2964043796","https://openalex.org/W2964282857","https://openalex.org/W2982316857","https://openalex.org/W3010568443","https://openalex.org/W3021034371","https://openalex.org/W3175558129","https://openalex.org/W4287637675","https://openalex.org/W4293469690","https://openalex.org/W4297808394","https://openalex.org/W6623316541","https://openalex.org/W6637108112","https://openalex.org/W6638018090","https://openalex.org/W6685755111","https://openalex.org/W6692846177","https://openalex.org/W6728184133","https://openalex.org/W6729556111","https://openalex.org/W6729906282","https://openalex.org/W6741002519","https://openalex.org/W6752051073","https://openalex.org/W6753417141","https://openalex.org/W6760724441","https://openalex.org/W6774303775","https://openalex.org/W6776556448","https://openalex.org/W6784458062"],"related_works":["https://openalex.org/W2062543035","https://openalex.org/W3136048210","https://openalex.org/W2154997814","https://openalex.org/W2742143911","https://openalex.org/W4309430181","https://openalex.org/W4226165671","https://openalex.org/W4224303442","https://openalex.org/W4293518564","https://openalex.org/W3006486727","https://openalex.org/W3023676446"],"abstract_inverted_index":{"Recent":[0],"years":[1],"have":[2,21],"witnessed":[3],"an":[4,59],"increasing":[5],"application":[6],"of":[7,84],"deep":[8],"reinforcement":[9],"learning":[10,53],"(DRL)":[11],"on":[12,119],"video":[13,122],"games.":[14],"While":[15],"deeper":[16],"and":[17,29],"wider":[18],"neural":[19,69],"networks":[20,50,70],"played":[22],"a":[23,54,76],"crucial":[24],"role":[25],"in":[26,37,91],"computer":[27],"vision":[28],"natural":[30],"language":[31],"processing,":[32],"such":[33],"capacity":[34],"remain":[35],"under-explored":[36],"most":[38],"DRL":[39],"works.":[40],"Under":[41],"the":[42,81,99,104],"fact":[43],"that":[44,66],"feature":[45],"propagation":[46],"together":[47],"with":[48,71,110],"large":[49,68],"contributes":[51],"to":[52,74,89,102],"good":[55],"representation,":[56],"we":[57,97,107,124],"propose":[58],"end-to-end":[60],"Large":[61],"Feature":[62],"Extractor":[63],"Network":[64],"(LFENet)":[65],"uses":[67],"dense":[72],"connections":[73],"train":[75],"high-capacity":[77],"encoder.":[78],"Even":[79],"though":[80],"increased":[82],"dimensionality":[83],"input":[85],"is":[86],"usually":[87],"thought":[88],"result":[90],"poor":[92],"performance":[93],"for":[94],"RL":[95],"agents,":[96],"introduce":[98],"information":[100],"bottleneck":[101],"alleviate":[103],"problem.":[105],"Finally,":[106],"combine":[108],"LFENet":[109],"Proximal":[111],"Policy":[112],"Optimization":[113],"(PPO)":[114],"algorithm.":[115],"Through":[116],"numerical":[117],"experiments":[118],"Atari":[120],"2600":[121],"games,":[123],"demonstrate":[125],"our":[126],"method":[127],"matches":[128],"or":[129],"outperforms":[130],"state-of-the-art":[131],"algorithms.":[132]},"counts_by_year":[{"year":2024,"cited_by_count":1},{"year":2023,"cited_by_count":1}],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2025-10-10T00:00:00"}