{"id":"https://openalex.org/W3034359401","doi":"https://doi.org/10.1109/icme46284.2020.9102924","title":"State Representation Learning For Effective Deep Reinforcement Learning","display_name":"State Representation Learning For Effective Deep Reinforcement Learning","publication_year":2020,"publication_date":"2020-06-09","ids":{"openalex":"https://openalex.org/W3034359401","doi":"https://doi.org/10.1109/icme46284.2020.9102924","mag":"3034359401"},"language":"en","primary_location":{"id":"doi:10.1109/icme46284.2020.9102924","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icme46284.2020.9102924","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2020 IEEE International Conference on Multimedia and Expo (ICME)","raw_type":"proceedings-article"},"type":"conference-paper","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/A5046073205","display_name":"Jian Zhao","orcid":"https://orcid.org/0000-0003-4895-990X"},"institutions":[{"id":"https://openalex.org/I126520041","display_name":"University of Science and Technology of China","ror":"https://ror.org/04c4dkn09","country_code":"CN","type":"education","lineage":["https://openalex.org/I126520041","https://openalex.org/I19820366"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jian Zhao","raw_affiliation_strings":["CAS Key Laboratory of GIPAS, University of Science and Technology of China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"CAS Key Laboratory of GIPAS, University of Science and Technology of China","institution_ids":["https://openalex.org/I126520041"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5046805800","display_name":"Wengang Zhou","orcid":"https://orcid.org/0000-0003-1690-9836"},"institutions":[{"id":"https://openalex.org/I126520041","display_name":"University of Science and Technology of China","ror":"https://ror.org/04c4dkn09","country_code":"CN","type":"education","lineage":["https://openalex.org/I126520041","https://openalex.org/I19820366"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Wengang Zhou","raw_affiliation_strings":["CAS Key Laboratory of GIPAS, University of Science and Technology of China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"CAS Key Laboratory of GIPAS, University of Science and Technology of China","institution_ids":["https://openalex.org/I126520041"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101622811","display_name":"Tianyu Zhao","orcid":"https://orcid.org/0000-0003-3210-611X"},"institutions":[{"id":"https://openalex.org/I126520041","display_name":"University of Science and Technology of China","ror":"https://ror.org/04c4dkn09","country_code":"CN","type":"education","lineage":["https://openalex.org/I126520041","https://openalex.org/I19820366"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Tianyu Zhao","raw_affiliation_strings":["CAS Key Laboratory of GIPAS, University of Science and Technology of China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"CAS Key Laboratory of GIPAS, University of Science and Technology of China","institution_ids":["https://openalex.org/I126520041"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101907040","display_name":"Yun Zhou","orcid":"https://orcid.org/0000-0002-2306-8986"},"institutions":[{"id":"https://openalex.org/I126520041","display_name":"University of Science and Technology of China","ror":"https://ror.org/04c4dkn09","country_code":"CN","type":"education","lineage":["https://openalex.org/I126520041","https://openalex.org/I19820366"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yun Zhou","raw_affiliation_strings":["CAS Key Laboratory of GIPAS, University of Science and Technology of China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"CAS Key Laboratory of GIPAS, University of Science and Technology of China","institution_ids":["https://openalex.org/I126520041"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5078141810","display_name":"Houqiang Li","orcid":"https://orcid.org/0000-0003-2188-3028"},"institutions":[{"id":"https://openalex.org/I126520041","display_name":"University of Science and Technology of China","ror":"https://ror.org/04c4dkn09","country_code":"CN","type":"education","lineage":["https://openalex.org/I126520041","https://openalex.org/I19820366"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Houqiang Li","raw_affiliation_strings":["CAS Key Laboratory of GIPAS, University of Science and Technology of China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"CAS Key Laboratory of GIPAS, University of Science and Technology of China","institution_ids":["https://openalex.org/I126520041"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I126520041"],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":4,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"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/T12794","display_name":"Adaptive Dynamic Programming Control","score":0.9927999973297119,"subfield":{"id":"https://openalex.org/subfields/1703","display_name":"Computational Theory and Mathematics"},"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":0.9602000117301941,"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/reinforcement-learning","display_name":"Reinforcement learning","score":0.9110088348388672},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7746955752372742},{"id":"https://openalex.org/keywords/representation","display_name":"Representation (politics)","score":0.7038515210151672},{"id":"https://openalex.org/keywords/consistency","display_name":"Consistency (knowledge bases)","score":0.6919622421264648},{"id":"https://openalex.org/keywords/feature-learning","display_name":"Feature learning","score":0.6727080345153809},{"id":"https://openalex.org/keywords/exploit","display_name":"Exploit","score":0.6696081161499023},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.6316781640052795},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.6283234357833862},{"id":"https://openalex.org/keywords/focus","display_name":"Focus (optics)","score":0.5852060317993164},{"id":"https://openalex.org/keywords/state","display_name":"State (computer science)","score":0.5483312606811523},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.48800912499427795},{"id":"https://openalex.org/keywords/obstacle","display_name":"Obstacle","score":0.47305694222450256},{"id":"https://openalex.org/keywords/variety","display_name":"Variety (cybernetics)","score":0.43937286734580994},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.10163488984107971},{"id":"https://openalex.org/keywords/computer-security","display_name":"Computer security","score":0.06007269024848938}],"concepts":[{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.9110088348388672},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7746955752372742},{"id":"https://openalex.org/C2776359362","wikidata":"https://www.wikidata.org/wiki/Q2145286","display_name":"Representation (politics)","level":3,"score":0.7038515210151672},{"id":"https://openalex.org/C2776436953","wikidata":"https://www.wikidata.org/wiki/Q5163215","display_name":"Consistency (knowledge bases)","level":2,"score":0.6919622421264648},{"id":"https://openalex.org/C59404180","wikidata":"https://www.wikidata.org/wiki/Q17013334","display_name":"Feature learning","level":2,"score":0.6727080345153809},{"id":"https://openalex.org/C165696696","wikidata":"https://www.wikidata.org/wiki/Q11287","display_name":"Exploit","level":2,"score":0.6696081161499023},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.6316781640052795},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6283234357833862},{"id":"https://openalex.org/C192209626","wikidata":"https://www.wikidata.org/wiki/Q190909","display_name":"Focus (optics)","level":2,"score":0.5852060317993164},{"id":"https://openalex.org/C48103436","wikidata":"https://www.wikidata.org/wiki/Q599031","display_name":"State (computer science)","level":2,"score":0.5483312606811523},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.48800912499427795},{"id":"https://openalex.org/C2776650193","wikidata":"https://www.wikidata.org/wiki/Q264661","display_name":"Obstacle","level":2,"score":0.47305694222450256},{"id":"https://openalex.org/C136197465","wikidata":"https://www.wikidata.org/wiki/Q1729295","display_name":"Variety (cybernetics)","level":2,"score":0.43937286734580994},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.10163488984107971},{"id":"https://openalex.org/C38652104","wikidata":"https://www.wikidata.org/wiki/Q3510521","display_name":"Computer security","level":1,"score":0.06007269024848938},{"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/C199539241","wikidata":"https://www.wikidata.org/wiki/Q7748","display_name":"Law","level":1,"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/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"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/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/icme46284.2020.9102924","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icme46284.2020.9102924","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2020 IEEE International Conference on Multimedia and Expo (ICME)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Peace, Justice and strong institutions","score":0.550000011920929,"id":"https://metadata.un.org/sdg/16"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":48,"referenced_works":["https://openalex.org/W32403112","https://openalex.org/W219040644","https://openalex.org/W834081922","https://openalex.org/W1164749991","https://openalex.org/W1532499126","https://openalex.org/W1771410628","https://openalex.org/W2099397840","https://openalex.org/W2100799972","https://openalex.org/W2103285838","https://openalex.org/W2137766593","https://openalex.org/W2145339207","https://openalex.org/W2148112459","https://openalex.org/W2155027007","https://openalex.org/W2155968351","https://openalex.org/W2158782408","https://openalex.org/W2163605009","https://openalex.org/W2173248099","https://openalex.org/W2567455162","https://openalex.org/W2736601468","https://openalex.org/W2746553466","https://openalex.org/W2761873684","https://openalex.org/W2807228161","https://openalex.org/W2962699241","https://openalex.org/W2963125676","https://openalex.org/W2963430173","https://openalex.org/W2963864421","https://openalex.org/W2964043796","https://openalex.org/W2964291307","https://openalex.org/W2964371010","https://openalex.org/W2964767089","https://openalex.org/W2966687395","https://openalex.org/W2966757921","https://openalex.org/W2971040589","https://openalex.org/W2998202787","https://openalex.org/W4288320194","https://openalex.org/W4312558117","https://openalex.org/W6623316541","https://openalex.org/W6631637103","https://openalex.org/W6638018090","https://openalex.org/W6680313055","https://openalex.org/W6683204974","https://openalex.org/W6684191040","https://openalex.org/W6684921986","https://openalex.org/W6692846177","https://openalex.org/W6741002519","https://openalex.org/W6752374788","https://openalex.org/W6765242767","https://openalex.org/W6780559895"],"related_works":["https://openalex.org/W17155033","https://openalex.org/W3207760230","https://openalex.org/W1496222301","https://openalex.org/W1590307681","https://openalex.org/W2536018345","https://openalex.org/W4312814274","https://openalex.org/W4285370786","https://openalex.org/W2296488620","https://openalex.org/W2358353312","https://openalex.org/W2353836703"],"abstract_inverted_index":{"Recent":[0],"years":[1],"have":[2],"witnessed":[3],"the":[4,47,52,87,124,129],"great":[5],"success":[6],"of":[7,15,58,99,120],"deep":[8],"reinforcement":[9],"learning":[10,50,71],"(DRL)":[11],"on":[12,39,86,136],"a":[13,67],"variety":[14],"vision":[16],"games.":[17],"Although":[18],"DNN":[19],"has":[20],"demonstrated":[21],"strong":[22],"power":[23],"in":[24,31,105,123],"representation":[25,70],"learning,":[26],"such":[27],"capacity":[28],"is":[29,37,51,83,149],"under-explored":[30],"most":[32],"DRL":[33,59],"works":[34],"whose":[35],"focus":[36],"usually":[38],"optimization":[40],"solvers.":[41],"In":[42,110],"fact,":[43],"we":[44,65,113],"discover":[45],"that":[46,89,98,146],"state":[48,69,130],"feature":[49,131],"main":[53],"obstacle":[54],"for":[55],"further":[56],"improvement":[57],"algorithms.":[60],"To":[61],"address":[62],"this":[63,111],"issue,":[64],"propose":[66],"new":[68],"scheme":[72],"with":[73],"our":[74,147],"Adjacent":[75],"State":[76],"Consistency":[77],"Loss":[78],"(ASC":[79],"Loss).":[80],"The":[81],"loss":[82,116,122],"defined":[84],"based":[85],"hypothesis":[88],"there":[90],"are":[91],"fewer":[92],"changes":[93],"between":[94],"adjacent":[95],"states":[96],"than":[97],"far":[100],"apart":[101],"ones,":[102],"since":[103],"scenes":[104],"videos":[106],"generally":[107],"evolve":[108],"smoothly.":[109],"paper,":[112],"exploit":[114],"ASC":[115],"as":[117],"an":[118],"assistant":[119],"RL":[121],"training":[125],"phase":[126],"to":[127,151],"boost":[128],"learning.":[132],"We":[133],"conduct":[134],"evaluation":[135],"Atari":[137],"games":[138],"and":[139],"MuJoCo":[140],"continuous":[141],"control":[142],"tasks,":[143],"which":[144],"demonstrates":[145],"method":[148],"superior":[150],"OpenAI":[152],"baselines.":[153]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":1},{"year":2021,"cited_by_count":2}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}