{"id":"https://openalex.org/W3121891333","doi":"https://doi.org/10.1109/mmul.2021.3053774","title":"State Representation Learning With Adjacent State Consistency Loss for Deep Reinforcement Learning","display_name":"State Representation Learning With Adjacent State Consistency Loss for Deep Reinforcement Learning","publication_year":2021,"publication_date":"2021-01-26","ids":{"openalex":"https://openalex.org/W3121891333","doi":"https://doi.org/10.1109/mmul.2021.3053774","mag":"3121891333"},"language":"en","primary_location":{"id":"doi:10.1109/mmul.2021.3053774","is_oa":false,"landing_page_url":"https://doi.org/10.1109/mmul.2021.3053774","pdf_url":null,"source":{"id":"https://openalex.org/S72873717","display_name":"IEEE Multimedia","issn_l":"1070-986X","issn":["1070-986X","1941-0166"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310320439","host_organization_name":"IEEE Computer Society","host_organization_lineage":["https://openalex.org/P4310320439","https://openalex.org/P4310319808"],"host_organization_lineage_names":["IEEE Computer Society","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 MultiMedia","raw_type":"journal-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/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, Electronic Engineering and Information Science Department, University of Science and Technology of China, Hefei, China"],"raw_orcid":"https://orcid.org/0000-0003-3210-611X","affiliations":[{"raw_affiliation_string":"CAS Key Laboratory of GIPAS, Electronic Engineering and Information Science Department, University of Science and Technology of China, Hefei, China","institution_ids":["https://openalex.org/I126520041"]}]},{"author_position":"middle","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, Electronic Engineering and Information Science Department, University of Science and Technology of China, Hefei, China"],"raw_orcid":"https://orcid.org/0000-0003-4895-990X","affiliations":[{"raw_affiliation_string":"CAS Key Laboratory of GIPAS, Electronic Engineering and Information Science Department, University of Science and Technology of China, Hefei, 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, Electronic Engineering and Information Science Department, University of Science and Technology of China, Hefei, China"],"raw_orcid":"https://orcid.org/0000-0003-1690-9836","affiliations":[{"raw_affiliation_string":"CAS Key Laboratory of GIPAS, Electronic Engineering and Information Science Department, University of Science and Technology of China, Hefei, China","institution_ids":["https://openalex.org/I126520041"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101550975","display_name":"Yun Zhou","orcid":"https://orcid.org/0000-0002-7466-4593"},"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, Electronic Engineering and Information Science Department, University of Science and Technology of China, Hefei, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"CAS Key Laboratory of GIPAS, Electronic Engineering and Information Science Department, University of Science and Technology of China, Hefei, 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, Electronic Engineering and Information Science Department, University of Science and Technology of China, Hefei, China"],"raw_orcid":"https://orcid.org/0000-0003-2188-3028","affiliations":[{"raw_affiliation_string":"CAS Key Laboratory of GIPAS, Electronic Engineering and Information Science Department, University of Science and Technology of China, Hefei, 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":0.5459,"has_fulltext":false,"cited_by_count":4,"citation_normalized_percentile":{"value":0.7062812,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":97},"biblio":{"volume":"28","issue":"3","first_page":"117","last_page":"127"},"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":0.9908000230789185,"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/T11099","display_name":"Autonomous Vehicle Technology and Safety","score":0.9789000153541565,"subfield":{"id":"https://openalex.org/subfields/2203","display_name":"Automotive 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/reinforcement-learning","display_name":"Reinforcement learning","score":0.8651837110519409},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7939562797546387},{"id":"https://openalex.org/keywords/consistency","display_name":"Consistency (knowledge bases)","score":0.668149471282959},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.6391679048538208},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.5957506895065308},{"id":"https://openalex.org/keywords/exploit","display_name":"Exploit","score":0.5661588311195374},{"id":"https://openalex.org/keywords/feature-learning","display_name":"Feature learning","score":0.5560742616653442},{"id":"https://openalex.org/keywords/representation","display_name":"Representation (politics)","score":0.5525097846984863},{"id":"https://openalex.org/keywords/feature-extraction","display_name":"Feature extraction","score":0.5272038578987122},{"id":"https://openalex.org/keywords/state","display_name":"State (computer science)","score":0.4535830616950989},{"id":"https://openalex.org/keywords/sampling","display_name":"Sampling (signal processing)","score":0.4530413746833801},{"id":"https://openalex.org/keywords/state-space","display_name":"State space","score":0.4528133273124695},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.4428364932537079},{"id":"https://openalex.org/keywords/scheme","display_name":"Scheme (mathematics)","score":0.43006598949432373},{"id":"https://openalex.org/keywords/extractor","display_name":"Extractor","score":0.4162454903125763},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.36767417192459106},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.21073505282402039},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.13918906450271606},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.10172373056411743},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.06177738308906555}],"concepts":[{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.8651837110519409},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7939562797546387},{"id":"https://openalex.org/C2776436953","wikidata":"https://www.wikidata.org/wiki/Q5163215","display_name":"Consistency (knowledge bases)","level":2,"score":0.668149471282959},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6391679048538208},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.5957506895065308},{"id":"https://openalex.org/C165696696","wikidata":"https://www.wikidata.org/wiki/Q11287","display_name":"Exploit","level":2,"score":0.5661588311195374},{"id":"https://openalex.org/C59404180","wikidata":"https://www.wikidata.org/wiki/Q17013334","display_name":"Feature learning","level":2,"score":0.5560742616653442},{"id":"https://openalex.org/C2776359362","wikidata":"https://www.wikidata.org/wiki/Q2145286","display_name":"Representation (politics)","level":3,"score":0.5525097846984863},{"id":"https://openalex.org/C52622490","wikidata":"https://www.wikidata.org/wiki/Q1026626","display_name":"Feature extraction","level":2,"score":0.5272038578987122},{"id":"https://openalex.org/C48103436","wikidata":"https://www.wikidata.org/wiki/Q599031","display_name":"State (computer science)","level":2,"score":0.4535830616950989},{"id":"https://openalex.org/C140779682","wikidata":"https://www.wikidata.org/wiki/Q210868","display_name":"Sampling (signal processing)","level":3,"score":0.4530413746833801},{"id":"https://openalex.org/C72434380","wikidata":"https://www.wikidata.org/wiki/Q230930","display_name":"State space","level":2,"score":0.4528133273124695},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.4428364932537079},{"id":"https://openalex.org/C77618280","wikidata":"https://www.wikidata.org/wiki/Q1155772","display_name":"Scheme (mathematics)","level":2,"score":0.43006598949432373},{"id":"https://openalex.org/C117978034","wikidata":"https://www.wikidata.org/wiki/Q5422192","display_name":"Extractor","level":2,"score":0.4162454903125763},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.36767417192459106},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.21073505282402039},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.13918906450271606},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.10172373056411743},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.06177738308906555},{"id":"https://openalex.org/C38652104","wikidata":"https://www.wikidata.org/wiki/Q3510521","display_name":"Computer security","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/C94625758","wikidata":"https://www.wikidata.org/wiki/Q7163","display_name":"Politics","level":2,"score":0.0},{"id":"https://openalex.org/C134306372","wikidata":"https://www.wikidata.org/wiki/Q7754","display_name":"Mathematical analysis","level":1,"score":0.0},{"id":"https://openalex.org/C106131492","wikidata":"https://www.wikidata.org/wiki/Q3072260","display_name":"Filter (signal processing)","level":2,"score":0.0},{"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/C17744445","wikidata":"https://www.wikidata.org/wiki/Q36442","display_name":"Political science","level":0,"score":0.0},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","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/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/mmul.2021.3053774","is_oa":false,"landing_page_url":"https://doi.org/10.1109/mmul.2021.3053774","pdf_url":null,"source":{"id":"https://openalex.org/S72873717","display_name":"IEEE Multimedia","issn_l":"1070-986X","issn":["1070-986X","1941-0166"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310320439","host_organization_name":"IEEE Computer Society","host_organization_lineage":["https://openalex.org/P4310320439","https://openalex.org/P4310319808"],"host_organization_lineage_names":["IEEE Computer Society","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 MultiMedia","raw_type":"journal-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G2262853887","display_name":null,"funder_award_id":"61836011","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G4052041763","display_name":null,"funder_award_id":"2018497","funder_id":"https://openalex.org/F4320322847","funder_display_name":"Youth Innovation Promotion Association of the Chinese Academy of Sciences"}],"funders":[{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"},{"id":"https://openalex.org/F4320322847","display_name":"Youth Innovation Promotion Association of the Chinese Academy of Sciences","ror":"https://ror.org/031141b54"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":26,"referenced_works":["https://openalex.org/W2063471043","https://openalex.org/W2145339207","https://openalex.org/W2155968351","https://openalex.org/W2158782408","https://openalex.org/W2173564293","https://openalex.org/W2174803659","https://openalex.org/W2296673577","https://openalex.org/W2342840547","https://openalex.org/W2736601468","https://openalex.org/W2746553466","https://openalex.org/W2749928749","https://openalex.org/W2951799221","https://openalex.org/W2963125676","https://openalex.org/W2963313316","https://openalex.org/W2963477884","https://openalex.org/W2964043796","https://openalex.org/W2969880113","https://openalex.org/W3015437096","https://openalex.org/W3034359401","https://openalex.org/W3115293622","https://openalex.org/W6685444567","https://openalex.org/W6687681856","https://openalex.org/W6692846177","https://openalex.org/W6704559304","https://openalex.org/W6741002519","https://openalex.org/W6743802245"],"related_works":["https://openalex.org/W1496222301","https://openalex.org/W3207760230","https://openalex.org/W4225571923","https://openalex.org/W3212257828","https://openalex.org/W2999580272","https://openalex.org/W4297873223","https://openalex.org/W2350784623","https://openalex.org/W2126211886","https://openalex.org/W3009457412","https://openalex.org/W2992629954"],"abstract_inverted_index":{"Through":[0],"well-designed":[1],"optimization":[2],"paradigm":[3],"and":[4,21,125,142],"deep":[5,11],"neural":[6],"networks":[7],"as":[8,109,132,134],"feature":[9,40,48,123],"extractor,":[10],"reinforcement":[12],"learning":[13,49,68],"(DRL)":[14],"algorithms":[15,131],"learn":[16],"optimal":[17],"policy":[18],"on":[19,81,128,139],"discrete":[20],"continuous":[22,144],"action":[23],"space.":[24],"However,":[25],"such":[26],"capability":[27],"is":[28,50,79,90],"restricted":[29],"by":[30],"the":[31,37,53,82,85,116,121,148],"low":[32],"sampling":[33,57],"efficiency.":[34],"By":[35],"inspecting":[36],"importance":[38],"of":[39,52,94,112,150],"extraction":[41],"in":[42,100,115],"DRL,":[43],"we":[44,62],"find":[45],"that":[46,84,93],"state":[47,66,72,122],"one":[51],"key":[54],"obstacles":[55],"for":[56],"efficiently.":[58],"To":[59],"this":[60],"end,":[61],"propose":[63],"a":[64],"new":[65],"representation":[67],"scheme":[69],"with":[70],"adjacent":[71,88],"consistency":[73],"loss":[74,78,108,114],"(ASC":[75],"loss).":[76],"The":[77],"based":[80],"hypothesis":[83],"distance":[86],"between":[87],"states":[89],"smaller":[91],"than":[92],"far":[95],"apart":[96],"ones":[97],"since":[98],"scenes":[99],"videos":[101],"generally":[102],"evolve":[103],"smoothly.":[104],"We":[105],"exploit":[106],"ASC":[107],"an":[110],"assistant":[111],"RL":[113],"training":[117],"phase":[118],"to":[119],"boost":[120],"learning,":[124],"make":[126],"evaluation":[127],"existing":[129],"DRL":[130],"well":[133],"behavioral":[135],"cloning":[136],"algorithm.":[137],"Experiments":[138],"Atari":[140],"games":[141],"MuJoCo":[143],"control":[145],"tasks":[146],"demonstrate":[147],"effectiveness":[149],"our":[151],"scheme.":[152]},"counts_by_year":[{"year":2023,"cited_by_count":1},{"year":2022,"cited_by_count":3}],"updated_date":"2026-03-27T05:58:40.876381","created_date":"2025-10-10T00:00:00"}