{"id":"https://openalex.org/W3206084438","doi":"https://doi.org/10.1109/icra48506.2021.9561740","title":"DIMSAN: Fast Exploration with the Synergy between Density-based Intrinsic Motivation and Self-adaptive Action Noise","display_name":"DIMSAN: Fast Exploration with the Synergy between Density-based Intrinsic Motivation and Self-adaptive Action Noise","publication_year":2021,"publication_date":"2021-05-30","ids":{"openalex":"https://openalex.org/W3206084438","doi":"https://doi.org/10.1109/icra48506.2021.9561740","mag":"3206084438"},"language":"en","primary_location":{"id":"doi:10.1109/icra48506.2021.9561740","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icra48506.2021.9561740","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2021 IEEE International Conference on Robotics and Automation (ICRA)","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/A5100446472","display_name":"Jiayi Li","orcid":"https://orcid.org/0000-0001-9416-5575"},"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/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"]},{"id":"https://openalex.org/I4210100255","display_name":"Beijing Academy of Artificial Intelligence","ror":"https://ror.org/016a74861","country_code":"CN","type":"other","lineage":["https://openalex.org/I4210100255"]},{"id":"https://openalex.org/I4210094879","display_name":"Shandong Institute of Automation","ror":"https://ror.org/00qdtba35","country_code":"CN","type":"facility","lineage":["https://openalex.org/I4210094879","https://openalex.org/I4210142748"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Jiayi Li","raw_affiliation_strings":["University of Chinese Academy of Sciences,School of Artificial Intelligence,Beijing,China","State Key Laboratory of Management and Control for Complex Systems, Institute of Automation, Chinese Academy of Sciences, Beijing, China","School of Artificial Intelligence, University of Chinese Academy of Sciences, Beijing, China"],"affiliations":[{"raw_affiliation_string":"University of Chinese Academy of Sciences,School of Artificial Intelligence,Beijing,China","institution_ids":["https://openalex.org/I4210165038"]},{"raw_affiliation_string":"State Key Laboratory of Management and Control for Complex Systems, Institute of Automation, Chinese Academy of Sciences, Beijing, China","institution_ids":["https://openalex.org/I4210094879","https://openalex.org/I19820366"]},{"raw_affiliation_string":"School of Artificial Intelligence, University of Chinese Academy of Sciences, Beijing, China","institution_ids":["https://openalex.org/I4210100255","https://openalex.org/I4210165038"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5103101761","display_name":"Boyao Li","orcid":"https://orcid.org/0000-0002-1220-2756"},"institutions":[{"id":"https://openalex.org/I68581759","display_name":"China Academy of Launch Vehicle Technology","ror":"https://ror.org/012z62f48","country_code":"CN","type":"facility","lineage":["https://openalex.org/I68581759"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Boyao Li","raw_affiliation_strings":["China Academy of Launch Vehicle Technology,Research and Development Department,Beijing,China","Research and Development Department, China Academy of Launch Vehicle Technology, Beijing, China"],"affiliations":[{"raw_affiliation_string":"China Academy of Launch Vehicle Technology,Research and Development Department,Beijing,China","institution_ids":["https://openalex.org/I68581759"]},{"raw_affiliation_string":"Research and Development Department, China Academy of Launch Vehicle Technology, Beijing, China","institution_ids":["https://openalex.org/I68581759"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5111683010","display_name":"Tao Lu","orcid":"https://orcid.org/0000-0003-3374-5845"},"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/I4210094879","display_name":"Shandong Institute of Automation","ror":"https://ror.org/00qdtba35","country_code":"CN","type":"facility","lineage":["https://openalex.org/I4210094879","https://openalex.org/I4210142748"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Tao Lu","raw_affiliation_strings":["Institute of Automation, Chinese Academy of Sciences,State Key Laboratory of Management and Control for Complex Systems,Beijing,China","State Key Laboratory of Management and Control for Complex Systems, Institute of Automation, Chinese Academy of Sciences, Beijing, China"],"affiliations":[{"raw_affiliation_string":"Institute of Automation, Chinese Academy of Sciences,State Key Laboratory of Management and Control for Complex Systems,Beijing,China","institution_ids":["https://openalex.org/I4210094879","https://openalex.org/I19820366"]},{"raw_affiliation_string":"State Key Laboratory of Management and Control for Complex Systems, Institute of Automation, Chinese Academy of Sciences, Beijing, China","institution_ids":["https://openalex.org/I4210094879","https://openalex.org/I19820366"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5044483334","display_name":"Ning Lu","orcid":"https://orcid.org/0000-0003-1944-5096"},"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/I4210100255","display_name":"Beijing Academy of Artificial Intelligence","ror":"https://ror.org/016a74861","country_code":"CN","type":"other","lineage":["https://openalex.org/I4210100255"]},{"id":"https://openalex.org/I4210094879","display_name":"Shandong Institute of Automation","ror":"https://ror.org/00qdtba35","country_code":"CN","type":"facility","lineage":["https://openalex.org/I4210094879","https://openalex.org/I4210142748"]},{"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":"Ning Lu","raw_affiliation_strings":["University of Chinese Academy of Sciences,School of Artificial Intelligence,Beijing,China","State Key Laboratory of Management and Control for Complex Systems, Institute of Automation, Chinese Academy of Sciences, Beijing, China","School of Artificial Intelligence, University of Chinese Academy of Sciences, Beijing, China"],"affiliations":[{"raw_affiliation_string":"University of Chinese Academy of Sciences,School of Artificial Intelligence,Beijing,China","institution_ids":["https://openalex.org/I4210165038"]},{"raw_affiliation_string":"State Key Laboratory of Management and Control for Complex Systems, Institute of Automation, Chinese Academy of Sciences, Beijing, China","institution_ids":["https://openalex.org/I4210094879","https://openalex.org/I19820366"]},{"raw_affiliation_string":"School of Artificial Intelligence, University of Chinese Academy of Sciences, Beijing, China","institution_ids":["https://openalex.org/I4210100255","https://openalex.org/I4210165038"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5103021731","display_name":"Yinghao Cai","orcid":"https://orcid.org/0000-0003-3024-2943"},"institutions":[{"id":"https://openalex.org/I4210094879","display_name":"Shandong Institute of Automation","ror":"https://ror.org/00qdtba35","country_code":"CN","type":"facility","lineage":["https://openalex.org/I4210094879","https://openalex.org/I4210142748"]},{"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":false,"raw_author_name":"Yinghao Cai","raw_affiliation_strings":["Institute of Automation, Chinese Academy of Sciences,State Key Laboratory of Management and Control for Complex Systems,Beijing,China","State Key Laboratory of Management and Control for Complex Systems, Institute of Automation, Chinese Academy of Sciences, Beijing, China"],"affiliations":[{"raw_affiliation_string":"Institute of Automation, Chinese Academy of Sciences,State Key Laboratory of Management and Control for Complex Systems,Beijing,China","institution_ids":["https://openalex.org/I4210094879","https://openalex.org/I19820366"]},{"raw_affiliation_string":"State Key Laboratory of Management and Control for Complex Systems, Institute of Automation, Chinese Academy of Sciences, Beijing, China","institution_ids":["https://openalex.org/I4210094879","https://openalex.org/I19820366"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5100639215","display_name":"Shuo Wang","orcid":"https://orcid.org/0000-0002-1390-9219"},"institutions":[{"id":"https://openalex.org/I4210100255","display_name":"Beijing Academy of Artificial Intelligence","ror":"https://ror.org/016a74861","country_code":"CN","type":"other","lineage":["https://openalex.org/I4210100255"]},{"id":"https://openalex.org/I4210094879","display_name":"Shandong Institute of Automation","ror":"https://ror.org/00qdtba35","country_code":"CN","type":"facility","lineage":["https://openalex.org/I4210094879","https://openalex.org/I4210142748"]},{"id":"https://openalex.org/I4210097554","display_name":"Center for Excellence in Brain Science and Intelligence Technology","ror":"https://ror.org/00vpwhm04","country_code":"CN","type":"education","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210097554"]},{"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/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":"Shuo Wang","raw_affiliation_strings":["University of Chinese Academy of Sciences,School of Artificial Intelligence,Beijing,China","Center for Excellence in Brain Science and Intelligence Technology, Chinese Academy of Sciences, Shanghai, China","State Key Laboratory of Management and Control for Complex Systems, Institute of Automation, Chinese Academy of Sciences, Beijing, China","School of Artificial Intelligence, University of Chinese Academy of Sciences, Beijing, China"],"affiliations":[{"raw_affiliation_string":"University of Chinese Academy of Sciences,School of Artificial Intelligence,Beijing,China","institution_ids":["https://openalex.org/I4210165038"]},{"raw_affiliation_string":"Center for Excellence in Brain Science and Intelligence Technology, Chinese Academy of Sciences, Shanghai, China","institution_ids":["https://openalex.org/I4210097554","https://openalex.org/I19820366"]},{"raw_affiliation_string":"State Key Laboratory of Management and Control for Complex Systems, Institute of Automation, Chinese Academy of Sciences, Beijing, China","institution_ids":["https://openalex.org/I4210094879","https://openalex.org/I19820366"]},{"raw_affiliation_string":"School of Artificial Intelligence, University of Chinese Academy of Sciences, Beijing, China","institution_ids":["https://openalex.org/I4210100255","https://openalex.org/I4210165038"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":6,"corresponding_author_ids":["https://openalex.org/A5100446472"],"corresponding_institution_ids":["https://openalex.org/I19820366","https://openalex.org/I4210094879","https://openalex.org/I4210100255","https://openalex.org/I4210165038"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":1,"citation_normalized_percentile":{"value":0.14725006,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":91,"max":95},"biblio":{"volume":null,"issue":null,"first_page":"6422","last_page":"6428"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10462","display_name":"Reinforcement Learning in Robotics","score":0.9968000054359436,"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":0.9968000054359436,"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/T10581","display_name":"Neural dynamics and brain function","score":0.9927999973297119,"subfield":{"id":"https://openalex.org/subfields/2805","display_name":"Cognitive Neuroscience"},"field":{"id":"https://openalex.org/fields/28","display_name":"Neuroscience"},"domain":{"id":"https://openalex.org/domains/1","display_name":"Life Sciences"}},{"id":"https://openalex.org/T10241","display_name":"Functional Brain Connectivity Studies","score":0.9236999750137329,"subfield":{"id":"https://openalex.org/subfields/2805","display_name":"Cognitive Neuroscience"},"field":{"id":"https://openalex.org/fields/28","display_name":"Neuroscience"},"domain":{"id":"https://openalex.org/domains/1","display_name":"Life Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/noise","display_name":"Noise (video)","score":0.6229448318481445},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.5994134545326233},{"id":"https://openalex.org/keywords/action","display_name":"Action (physics)","score":0.5852037072181702},{"id":"https://openalex.org/keywords/intrinsic-motivation","display_name":"Intrinsic motivation","score":0.44949010014533997},{"id":"https://openalex.org/keywords/physics","display_name":"Physics","score":0.21107962727546692},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.1915827989578247},{"id":"https://openalex.org/keywords/psychology","display_name":"Psychology","score":0.1548415720462799},{"id":"https://openalex.org/keywords/social-psychology","display_name":"Social psychology","score":0.08193102478981018}],"concepts":[{"id":"https://openalex.org/C99498987","wikidata":"https://www.wikidata.org/wiki/Q2210247","display_name":"Noise (video)","level":3,"score":0.6229448318481445},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5994134545326233},{"id":"https://openalex.org/C2780791683","wikidata":"https://www.wikidata.org/wiki/Q846785","display_name":"Action (physics)","level":2,"score":0.5852037072181702},{"id":"https://openalex.org/C2985564149","wikidata":"https://www.wikidata.org/wiki/Q644302","display_name":"Intrinsic motivation","level":2,"score":0.44949010014533997},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.21107962727546692},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.1915827989578247},{"id":"https://openalex.org/C15744967","wikidata":"https://www.wikidata.org/wiki/Q9418","display_name":"Psychology","level":0,"score":0.1548415720462799},{"id":"https://openalex.org/C77805123","wikidata":"https://www.wikidata.org/wiki/Q161272","display_name":"Social psychology","level":1,"score":0.08193102478981018},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.0},{"id":"https://openalex.org/C62520636","wikidata":"https://www.wikidata.org/wiki/Q944","display_name":"Quantum mechanics","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icra48506.2021.9561740","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icra48506.2021.9561740","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2021 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"},{"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":91,"referenced_works":["https://openalex.org/W32403112","https://openalex.org/W41554520","https://openalex.org/W567721252","https://openalex.org/W779494576","https://openalex.org/W1191599655","https://openalex.org/W1602154927","https://openalex.org/W1771410628","https://openalex.org/W1988526405","https://openalex.org/W2014268383","https://openalex.org/W2101524054","https://openalex.org/W2107726111","https://openalex.org/W2118688707","https://openalex.org/W2121863487","https://openalex.org/W2123327324","https://openalex.org/W2141559645","https://openalex.org/W2145339207","https://openalex.org/W2158782408","https://openalex.org/W2201581102","https://openalex.org/W2280163991","https://openalex.org/W2417786368","https://openalex.org/W2596982695","https://openalex.org/W2623491082","https://openalex.org/W2724169821","https://openalex.org/W2736601468","https://openalex.org/W2738669288","https://openalex.org/W2781726626","https://openalex.org/W2788781499","https://openalex.org/W2810785043","https://openalex.org/W2823112946","https://openalex.org/W2885550588","https://openalex.org/W2895626374","https://openalex.org/W2905606790","https://openalex.org/W2906796853","https://openalex.org/W2909335861","https://openalex.org/W2948713108","https://openalex.org/W2949475445","https://openalex.org/W2953772919","https://openalex.org/W2955035422","https://openalex.org/W2962736495","https://openalex.org/W2963276097","https://openalex.org/W2963462732","https://openalex.org/W2963523627","https://openalex.org/W2963864421","https://openalex.org/W2964053353","https://openalex.org/W2964295739","https://openalex.org/W2970393539","https://openalex.org/W3000757491","https://openalex.org/W3007848632","https://openalex.org/W3035717769","https://openalex.org/W3046395471","https://openalex.org/W3086270667","https://openalex.org/W3090903721","https://openalex.org/W4289096618","https://openalex.org/W4289440819","https://openalex.org/W4293396018","https://openalex.org/W4293872189","https://openalex.org/W4300799055","https://openalex.org/W6616173779","https://openalex.org/W6622487243","https://openalex.org/W6627932998","https://openalex.org/W6638018090","https://openalex.org/W6677477928","https://openalex.org/W6684921986","https://openalex.org/W6687681856","https://openalex.org/W6695011786","https://openalex.org/W6716474083","https://openalex.org/W6717230150","https://openalex.org/W6730641667","https://openalex.org/W6735033012","https://openalex.org/W6739193204","https://openalex.org/W6740092555","https://openalex.org/W6740801417","https://openalex.org/W6741002519","https://openalex.org/W6747473740","https://openalex.org/W6748523217","https://openalex.org/W6748599296","https://openalex.org/W6753060773","https://openalex.org/W6753243525","https://openalex.org/W6753925943","https://openalex.org/W6755289019","https://openalex.org/W6757438168","https://openalex.org/W6757857725","https://openalex.org/W6758182352","https://openalex.org/W6758315252","https://openalex.org/W6760560886","https://openalex.org/W6762863188","https://openalex.org/W6763535664","https://openalex.org/W6765804866","https://openalex.org/W6767047803","https://openalex.org/W6774784542","https://openalex.org/W6780559895"],"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/W4402327032","https://openalex.org/W2382290278"],"abstract_inverted_index":{"Exploration":[0],"in":[1,10,177,186],"environments":[2],"with":[3,116,150],"sparse":[4],"rewards":[5],"remains":[6],"a":[7,22,49,75,83,109],"challenging":[8,165,187],"problem":[9],"Deep":[11],"Reinforcement":[12],"Learning":[13],"(DRL).":[14],"For":[15],"the":[16,29,98,117,124,141,145,158,163,174],"off-policy":[17,55],"method,":[18],"it":[19],"usually":[20],"needs":[21],"large":[23],"number":[24],"of":[25,32,179],"training":[26],"samples.":[27],"With":[28],"growing":[30],"dimensions":[31],"state":[33,146],"and":[34,41,62,96,103,137,147,162,182],"action":[35,130,148],"space,":[36],"this":[37,45],"method":[38,53,156,172],"becomes":[39],"more":[40,42],"sample-inefficient.":[43],"In":[44],"paper,":[46],"we":[47],"propose":[48,74,108],"novel":[50,102],"fast":[51],"exploration":[52,125],"for":[54],"reinforcement":[56],"learning,":[57],"called":[58],"Density-based":[59,76],"Intrinsic":[60,77],"Motivation":[61,78],"Self-adaptive":[63,110],"Action":[64,111],"Noise":[65,112],"(DIMSAN).":[66],"Our":[67],"main":[68],"contribution":[69],"is":[70],"twofold:":[71],"(1)":[72],"We":[73,107,153],"(DIM)":[79],"method.":[80],"It":[81],"introduces":[82],"new":[84],"intrinsic-reward":[85],"generation":[86],"mechanism":[87],"based":[88],"on":[89,157],"samples’":[90],"density":[91],"estimation":[92],"during":[93],"experience":[94],"replay":[95],"encourages":[97],"agent":[99,142],"to":[100,114,143],"seek":[101],"unfamiliar":[104],"states.":[105],"(2)":[106],"(SAN)":[113],"deal":[115],"exploration-exploitation":[118],"tradeoffs,":[119],"which":[120],"could":[121,139],"automatically":[122],"change":[123],"step":[126],"through":[127],"adding":[128],"adaptive":[129],"space":[131,149],"noise.":[132],"The":[133],"synergy":[134],"between":[135],"DIM":[136],"SAN":[138],"guide":[140],"search":[144],"high":[151],"efficiency.":[152],"evaluate":[154],"our":[155,171],"benchmark":[159],"manipulation":[160],"tasks":[161],"designed":[164],"ones.":[166],"Empirical":[167],"results":[168],"show":[169],"that":[170],"outperforms":[173],"existing":[175],"methods":[176],"terms":[178],"convergence":[180],"speed":[181],"sample":[183],"efficiency,":[184],"especially":[185],"tasks.":[188]},"counts_by_year":[{"year":2025,"cited_by_count":1}],"updated_date":"2026-01-13T01:12:25.745995","created_date":"2025-10-10T00:00:00"}