{"id":"https://openalex.org/W4401414341","doi":"https://doi.org/10.1109/icra57147.2024.10611330","title":"Effective Representation Learning is More Effective in Reinforcement Learning than You Think","display_name":"Effective Representation Learning is More Effective in Reinforcement Learning than You Think","publication_year":2024,"publication_date":"2024-05-13","ids":{"openalex":"https://openalex.org/W4401414341","doi":"https://doi.org/10.1109/icra57147.2024.10611330"},"language":"en","primary_location":{"id":"doi:10.1109/icra57147.2024.10611330","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icra57147.2024.10611330","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2024 IEEE International Conference on Robotics and Automation (ICRA)","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/A5101407604","display_name":"Jiawei Zheng","orcid":"https://orcid.org/0000-0002-5381-2729"},"institutions":[{"id":"https://openalex.org/I87445476","display_name":"Xi'an Jiaotong University","ror":"https://ror.org/017zhmm22","country_code":"CN","type":"education","lineage":["https://openalex.org/I87445476"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jiawei Zheng","raw_affiliation_strings":["Xi’an Jiaotong University,School of Software Engineering,Shaanxi,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Xi’an Jiaotong University,School of Software Engineering,Shaanxi,China","institution_ids":["https://openalex.org/I87445476"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5110814145","display_name":"Yonghong Song","orcid":"https://orcid.org/0000-0001-5978-3781"},"institutions":[{"id":"https://openalex.org/I87445476","display_name":"Xi'an Jiaotong University","ror":"https://ror.org/017zhmm22","country_code":"CN","type":"education","lineage":["https://openalex.org/I87445476"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yonghong Song","raw_affiliation_strings":["Xi’an Jiaotong University,School of Software Engineering,Shaanxi,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Xi’an Jiaotong University,School of Software Engineering,Shaanxi,China","institution_ids":["https://openalex.org/I87445476"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I87445476"],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":2,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"9176","last_page":"9182"},"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/T10646","display_name":"Experimental Behavioral Economics Studies","score":0.9469000101089478,"subfield":{"id":"https://openalex.org/subfields/3311","display_name":"Safety Research"},"field":{"id":"https://openalex.org/fields/33","display_name":"Social 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":0.8338940739631653},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7064371109008789},{"id":"https://openalex.org/keywords/representation","display_name":"Representation (politics)","score":0.5250703692436218},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4462793171405792},{"id":"https://openalex.org/keywords/reinforcement","display_name":"Reinforcement","score":0.4171954393386841},{"id":"https://openalex.org/keywords/human\u2013computer-interaction","display_name":"Human\u2013computer interaction","score":0.34124115109443665},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.3212314248085022},{"id":"https://openalex.org/keywords/psychology","display_name":"Psychology","score":0.11106988787651062},{"id":"https://openalex.org/keywords/social-psychology","display_name":"Social psychology","score":0.04625535011291504}],"concepts":[{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.8338940739631653},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7064371109008789},{"id":"https://openalex.org/C2776359362","wikidata":"https://www.wikidata.org/wiki/Q2145286","display_name":"Representation (politics)","level":3,"score":0.5250703692436218},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4462793171405792},{"id":"https://openalex.org/C67203356","wikidata":"https://www.wikidata.org/wiki/Q1321905","display_name":"Reinforcement","level":2,"score":0.4171954393386841},{"id":"https://openalex.org/C107457646","wikidata":"https://www.wikidata.org/wiki/Q207434","display_name":"Human\u2013computer interaction","level":1,"score":0.34124115109443665},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.3212314248085022},{"id":"https://openalex.org/C15744967","wikidata":"https://www.wikidata.org/wiki/Q9418","display_name":"Psychology","level":0,"score":0.11106988787651062},{"id":"https://openalex.org/C77805123","wikidata":"https://www.wikidata.org/wiki/Q161272","display_name":"Social psychology","level":1,"score":0.04625535011291504},{"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/C199539241","wikidata":"https://www.wikidata.org/wiki/Q7748","display_name":"Law","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}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icra57147.2024.10611330","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icra57147.2024.10611330","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2024 IEEE International Conference on Robotics and Automation (ICRA)","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"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":46,"referenced_works":["https://openalex.org/W2150468603","https://openalex.org/W2194775991","https://openalex.org/W2781585732","https://openalex.org/W2920362155","https://openalex.org/W2950872548","https://openalex.org/W2952867909","https://openalex.org/W2963009616","https://openalex.org/W2995298643","https://openalex.org/W3021708257","https://openalex.org/W3035524453","https://openalex.org/W3093210455","https://openalex.org/W3159481202","https://openalex.org/W3175558129","https://openalex.org/W3186672455","https://openalex.org/W3211614623","https://openalex.org/W4220769332","https://openalex.org/W4221154300","https://openalex.org/W4225796248","https://openalex.org/W4252279978","https://openalex.org/W4285600734","https://openalex.org/W4287811291","https://openalex.org/W4287824506","https://openalex.org/W4288320194","https://openalex.org/W4297808394","https://openalex.org/W4306177946","https://openalex.org/W4318906185","https://openalex.org/W4378711596","https://openalex.org/W6729556111","https://openalex.org/W6731293529","https://openalex.org/W6747387971","https://openalex.org/W6747473740","https://openalex.org/W6760405395","https://openalex.org/W6765242767","https://openalex.org/W6771217966","https://openalex.org/W6775277072","https://openalex.org/W6776556448","https://openalex.org/W6776867236","https://openalex.org/W6776901495","https://openalex.org/W6796848067","https://openalex.org/W6799458897","https://openalex.org/W6810212583","https://openalex.org/W6810343060","https://openalex.org/W6844194202","https://openalex.org/W6846005265","https://openalex.org/W6849299767","https://openalex.org/W6852559736"],"related_works":["https://openalex.org/W2920061524","https://openalex.org/W4310083477","https://openalex.org/W2328553770","https://openalex.org/W1977959518","https://openalex.org/W2038908348","https://openalex.org/W2107890255","https://openalex.org/W2106552856","https://openalex.org/W2145821588","https://openalex.org/W2086122291","https://openalex.org/W1987513656"],"abstract_inverted_index":{"In":[0],"reinforcement":[1,225],"learning":[2,4,42,62,86,121,149,220,226],"(RL),":[3],"directly":[5],"from":[6],"pixels,":[7],"is":[8,221],"commonly":[9],"known":[10],"as":[11,129],"vision-based":[12,23,35,76,182],"RL.":[13,24,64,123],"Effective":[14],"state":[15,31,203],"representations":[16,82],"are":[17],"crucial":[18],"for":[19,210],"high":[20],"performance":[21],"in":[22,26,49,140,181,205,224],"However,":[25],"order":[27],"to":[28,47,95,107,110,126,168],"learn":[29,66],"effective":[30,57,75,116,218,223],"representations,":[32],"most":[33],"current":[34],"RL":[36,77,198],"methods":[37,186,199],"based":[38,200],"on":[39,187,201],"contrastive":[40,85,141],"unsupervised":[41,142],"use":[43],"auxiliary":[44],"tasks":[45],"similar":[46],"those":[48],"computer":[50],"vision,":[51],"which":[52],"does":[53],"not":[54],"guarantee":[55],"the":[56,81,88,92,98,104,111,157,165],"information":[58,117],"interaction":[59],"between":[60,119],"representation":[61,120,148,219],"and":[63,74,91,122,162,170,190],"To":[65],"more":[67,173,222],"efficient":[68,174],"states,":[69],"we":[70],"propose":[71],"a":[72,153,172],"simple":[73],"method.":[78],"It":[79,151],"leverages":[80],"acquired":[83],"through":[84],"by":[87],"Teacher":[89,112,166],"Encoder":[90,94],"Student":[93],"collaboratively":[96],"estimate":[97,155],"Q-function.":[99],"This":[100,214],"cooperative":[101],"process":[102],"utilizes":[103],"TD":[105],"error":[106],"steer":[108],"updates":[109],"Encoder,":[113],"thereby":[114],"ensuring":[115],"exchange":[118],"We":[124],"refer":[125],"this":[127],"approach":[128],"Reinforcement":[130],"Learning":[131],"with":[132,146,159],"Teacher-Student":[133],"Collaboration":[134],"(RLTSC).":[135],"RLTSC":[136,176,195],"incorporates":[137],"recent":[138],"advancements":[139],"learning,":[143],"endowing":[144],"it":[145],"potent":[147],"capabilities.":[150],"provides":[152],"robust":[154],"of":[156,207],"Q-function":[158],"minimal":[160],"variance":[161],"effectively":[163],"guides":[164],"Ecoder":[167],"update":[169],"acquire":[171],"representation.":[175],"substantially":[177],"enhances":[178],"data":[179,208],"efficiency":[180,209],"RL,":[183],"surpassing":[184],"state-of-the-art":[185],"various":[188],"continuous":[189,211],"discrete":[191],"control":[192,212],"benchmarks.":[193,213],"Remarkably,":[194],"even":[196],"outperforms":[197],"physical":[202],"features":[204],"terms":[206],"may":[215],"enlighten":[216],"us:":[217],"than":[227],"you":[228],"think!":[229]},"counts_by_year":[{"year":2025,"cited_by_count":2}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}