{"id":"https://openalex.org/W4386883554","doi":"https://doi.org/10.1109/rcar58764.2023.10249999","title":"D2SR: Transferring Dense Reward Function to Sparse by Network Resetting","display_name":"D2SR: Transferring Dense Reward Function to Sparse by Network Resetting","publication_year":2023,"publication_date":"2023-07-17","ids":{"openalex":"https://openalex.org/W4386883554","doi":"https://doi.org/10.1109/rcar58764.2023.10249999"},"language":"en","primary_location":{"id":"doi:10.1109/rcar58764.2023.10249999","is_oa":false,"landing_page_url":"https://doi.org/10.1109/rcar58764.2023.10249999","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2023 IEEE International Conference on Real-time Computing and Robotics (RCAR)","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/A5058229499","display_name":"Yongle Luo","orcid":"https://orcid.org/0000-0001-9933-3611"},"institutions":[{"id":"https://openalex.org/I4210099079","display_name":"Institute of Intelligent Machines","ror":"https://ror.org/00w0qep84","country_code":"CN","type":"facility","lineage":["https://openalex.org/I19820366","https://openalex.org/I2802624667","https://openalex.org/I4210099079"]},{"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":true,"raw_author_name":"Yongle Luo","raw_affiliation_strings":["Hefei Institute of Physical Science, CAS,Institute of Intelligent Machines,Hefei,China,230031","University of Science and Technology of China, Hefei, China"],"affiliations":[{"raw_affiliation_string":"Hefei Institute of Physical Science, CAS,Institute of Intelligent Machines,Hefei,China,230031","institution_ids":["https://openalex.org/I4210099079"]},{"raw_affiliation_string":"University of Science and Technology of China, Hefei, China","institution_ids":["https://openalex.org/I126520041"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100427485","display_name":"Yuxin Wang","orcid":"https://orcid.org/0009-0001-7121-3578"},"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"]},{"id":"https://openalex.org/I4210099079","display_name":"Institute of Intelligent Machines","ror":"https://ror.org/00w0qep84","country_code":"CN","type":"facility","lineage":["https://openalex.org/I19820366","https://openalex.org/I2802624667","https://openalex.org/I4210099079"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yuxin Wang","raw_affiliation_strings":["Hefei Institute of Physical Science, CAS,Institute of Intelligent Machines,Hefei,China,230031","University of Science and Technology of China, Hefei, China"],"affiliations":[{"raw_affiliation_string":"Hefei Institute of Physical Science, CAS,Institute of Intelligent Machines,Hefei,China,230031","institution_ids":["https://openalex.org/I4210099079"]},{"raw_affiliation_string":"University of Science and Technology of China, Hefei, China","institution_ids":["https://openalex.org/I126520041"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101958555","display_name":"Kun Dong","orcid":"https://orcid.org/0000-0002-5440-185X"},"institutions":[{"id":"https://openalex.org/I4210099079","display_name":"Institute of Intelligent Machines","ror":"https://ror.org/00w0qep84","country_code":"CN","type":"facility","lineage":["https://openalex.org/I19820366","https://openalex.org/I2802624667","https://openalex.org/I4210099079"]},{"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":"Kun Dong","raw_affiliation_strings":["Hefei Institute of Physical Science, CAS,Institute of Intelligent Machines,Hefei,China,230031","University of Science and Technology of China, Hefei, China"],"affiliations":[{"raw_affiliation_string":"Hefei Institute of Physical Science, CAS,Institute of Intelligent Machines,Hefei,China,230031","institution_ids":["https://openalex.org/I4210099079"]},{"raw_affiliation_string":"University of Science and Technology of China, Hefei, China","institution_ids":["https://openalex.org/I126520041"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5104305408","display_name":"Yu Liu","orcid":"https://orcid.org/0009-0004-8537-2256"},"institutions":[{"id":"https://openalex.org/I4210099079","display_name":"Institute of Intelligent Machines","ror":"https://ror.org/00w0qep84","country_code":"CN","type":"facility","lineage":["https://openalex.org/I19820366","https://openalex.org/I2802624667","https://openalex.org/I4210099079"]},{"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":"Yu Liu","raw_affiliation_strings":["Hefei Institute of Physical Science, CAS,Institute of Intelligent Machines,Hefei,China,230031","University of Science and Technology of China, Hefei, China"],"affiliations":[{"raw_affiliation_string":"Hefei Institute of Physical Science, CAS,Institute of Intelligent Machines,Hefei,China,230031","institution_ids":["https://openalex.org/I4210099079"]},{"raw_affiliation_string":"University of Science and Technology of China, Hefei, China","institution_ids":["https://openalex.org/I126520041"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101727179","display_name":"Zhiyong Sun","orcid":"https://orcid.org/0000-0001-9510-4897"},"institutions":[{"id":"https://openalex.org/I4210099079","display_name":"Institute of Intelligent Machines","ror":"https://ror.org/00w0qep84","country_code":"CN","type":"facility","lineage":["https://openalex.org/I19820366","https://openalex.org/I2802624667","https://openalex.org/I4210099079"]},{"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":"Zhiyong Sun","raw_affiliation_strings":["Hefei Institute of Physical Science, CAS,Institute of Intelligent Machines,Hefei,China,230031","University of Science and Technology of China, Hefei, China"],"affiliations":[{"raw_affiliation_string":"Hefei Institute of Physical Science, CAS,Institute of Intelligent Machines,Hefei,China,230031","institution_ids":["https://openalex.org/I4210099079"]},{"raw_affiliation_string":"University of Science and Technology of China, Hefei, China","institution_ids":["https://openalex.org/I126520041"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100381999","display_name":"Qiang Zhang","orcid":"https://orcid.org/0000-0003-3776-9799"},"institutions":[{"id":"https://openalex.org/I4210099079","display_name":"Institute of Intelligent Machines","ror":"https://ror.org/00w0qep84","country_code":"CN","type":"facility","lineage":["https://openalex.org/I19820366","https://openalex.org/I2802624667","https://openalex.org/I4210099079"]},{"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":"Qiang Zhang","raw_affiliation_strings":["Hefei Institute of Physical Science, CAS,Institute of Intelligent Machines,Hefei,China,230031","University of Science and Technology of China, Hefei, China"],"affiliations":[{"raw_affiliation_string":"Hefei Institute of Physical Science, CAS,Institute of Intelligent Machines,Hefei,China,230031","institution_ids":["https://openalex.org/I4210099079"]},{"raw_affiliation_string":"University of Science and Technology of China, Hefei, China","institution_ids":["https://openalex.org/I126520041"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5060524697","display_name":"Bo Song","orcid":"https://orcid.org/0000-0003-2307-8524"},"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"]},{"id":"https://openalex.org/I4210099079","display_name":"Institute of Intelligent Machines","ror":"https://ror.org/00w0qep84","country_code":"CN","type":"facility","lineage":["https://openalex.org/I19820366","https://openalex.org/I2802624667","https://openalex.org/I4210099079"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Bo Song","raw_affiliation_strings":["Hefei Institute of Physical Science, CAS,Institute of Intelligent Machines,Hefei,China,230031","Jianghuai Frontier Technology Coordination and Innovation Center, Hefei, China","University of Science and Technology of China, Hefei, China"],"affiliations":[{"raw_affiliation_string":"Hefei Institute of Physical Science, CAS,Institute of Intelligent Machines,Hefei,China,230031","institution_ids":["https://openalex.org/I4210099079"]},{"raw_affiliation_string":"Jianghuai Frontier Technology Coordination and Innovation Center, Hefei, China","institution_ids":[]},{"raw_affiliation_string":"University of Science and Technology of China, Hefei, China","institution_ids":["https://openalex.org/I126520041"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":7,"corresponding_author_ids":["https://openalex.org/A5058229499"],"corresponding_institution_ids":["https://openalex.org/I126520041","https://openalex.org/I4210099079"],"apc_list":null,"apc_paid":null,"fwci":1.3986,"has_fulltext":false,"cited_by_count":8,"citation_normalized_percentile":{"value":0.85107528,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":96,"max":98},"biblio":{"volume":null,"issue":null,"first_page":"906","last_page":"911"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T12611","display_name":"Neural Networks and Reservoir Computing","score":0.9980999827384949,"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/T12611","display_name":"Neural Networks and Reservoir Computing","score":0.9980999827384949,"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/T10502","display_name":"Advanced Memory and Neural Computing","score":0.9962999820709229,"subfield":{"id":"https://openalex.org/subfields/2208","display_name":"Electrical and Electronic Engineering"},"field":{"id":"https://openalex.org/fields/22","display_name":"Engineering"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T10462","display_name":"Reinforcement Learning in Robotics","score":0.9937000274658203,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.743981122970581},{"id":"https://openalex.org/keywords/reinforcement-learning","display_name":"Reinforcement learning","score":0.7062859535217285},{"id":"https://openalex.org/keywords/robustness","display_name":"Robustness (evolution)","score":0.6692915558815002},{"id":"https://openalex.org/keywords/function","display_name":"Function (biology)","score":0.5533379316329956},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.48076388239860535},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4514370262622833},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.11482506990432739}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.743981122970581},{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.7062859535217285},{"id":"https://openalex.org/C63479239","wikidata":"https://www.wikidata.org/wiki/Q7353546","display_name":"Robustness (evolution)","level":3,"score":0.6692915558815002},{"id":"https://openalex.org/C14036430","wikidata":"https://www.wikidata.org/wiki/Q3736076","display_name":"Function (biology)","level":2,"score":0.5533379316329956},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.48076388239860535},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4514370262622833},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.11482506990432739},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.0},{"id":"https://openalex.org/C55493867","wikidata":"https://www.wikidata.org/wiki/Q7094","display_name":"Biochemistry","level":1,"score":0.0},{"id":"https://openalex.org/C78458016","wikidata":"https://www.wikidata.org/wiki/Q840400","display_name":"Evolutionary biology","level":1,"score":0.0},{"id":"https://openalex.org/C104317684","wikidata":"https://www.wikidata.org/wiki/Q7187","display_name":"Gene","level":2,"score":0.0},{"id":"https://openalex.org/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","level":0,"score":0.0},{"id":"https://openalex.org/C201995342","wikidata":"https://www.wikidata.org/wiki/Q682496","display_name":"Systems engineering","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/rcar58764.2023.10249999","is_oa":false,"landing_page_url":"https://doi.org/10.1109/rcar58764.2023.10249999","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2023 IEEE International Conference on Real-time Computing and Robotics (RCAR)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":41,"referenced_works":["https://openalex.org/W1777239053","https://openalex.org/W2100677568","https://openalex.org/W2158782408","https://openalex.org/W2198041288","https://openalex.org/W2736601468","https://openalex.org/W2741122588","https://openalex.org/W2787938642","https://openalex.org/W2904246096","https://openalex.org/W2952867909","https://openalex.org/W2963375351","https://openalex.org/W2973229164","https://openalex.org/W2990747716","https://openalex.org/W2998116579","https://openalex.org/W3041880230","https://openalex.org/W3114551027","https://openalex.org/W3135286130","https://openalex.org/W3208335691","https://openalex.org/W4224301188","https://openalex.org/W4286374783","https://openalex.org/W4287025449","https://openalex.org/W4293872189","https://openalex.org/W4298857966","https://openalex.org/W4299134566","https://openalex.org/W4300799055","https://openalex.org/W4302304532","https://openalex.org/W6637967152","https://openalex.org/W6638088447","https://openalex.org/W6740801417","https://openalex.org/W6741002519","https://openalex.org/W6742461812","https://openalex.org/W6748599296","https://openalex.org/W6748839928","https://openalex.org/W6750453880","https://openalex.org/W6757592117","https://openalex.org/W6780448625","https://openalex.org/W6780559895","https://openalex.org/W6800530116","https://openalex.org/W6810653233","https://openalex.org/W6838667504","https://openalex.org/W6844961931","https://openalex.org/W6922480057"],"related_works":["https://openalex.org/W4362501864","https://openalex.org/W4306904969","https://openalex.org/W4380318855","https://openalex.org/W2138720691","https://openalex.org/W2031695474","https://openalex.org/W2586732548","https://openalex.org/W3049728571","https://openalex.org/W20361778","https://openalex.org/W2024136090","https://openalex.org/W2964765435"],"abstract_inverted_index":{"In":[0,30,148],"Reinforcement":[1],"Learning":[2],"(RL),":[3],"most":[4],"algorithms":[5],"use":[6],"a":[7,32,46,58,152],"fixed":[8],"reward":[9,17,25,35,67,104,172],"function,":[10],"and":[11,61,74,106,131,180],"few":[12],"studies":[13],"discuss":[14],"transferring":[15,132],"the":[16,38,43,51,69,77,100,107,113,118,142,145,168],"function":[18,36,60,173],"during":[19],"learning.":[20],"Actually,":[21],"different":[22,28],"types":[23],"of":[24,40,53,71,102,109,144,154,170],"functions":[26,105],"have":[27],"characteristics.":[29],"general,":[31],"shaped":[33],"dense":[34,103,125,171],"has":[37,50,68],"advantage":[39],"quickly":[41],"guiding":[42],"agent":[44,119],"to":[45,56,63,134],"high-value":[47],"state":[48],"but":[49,79],"disadvantage":[52],"being":[54,72,121],"difficult":[55],"design":[57],"well-shaped":[59],"susceptible":[62],"noise.":[64],"The":[65],"sparse":[66,110,135],"advantages":[70],"robust":[73],"consistent":[75],"with":[76,184],"task,":[78],"less":[80],"efficient":[81],"in":[82,141,182],"early":[83],"exploration.":[84],"Therefore,":[85],"this":[86,149],"paper":[87],"proposes":[88],"an":[89],"algorithm":[90],"called":[91],"Dense2Sparse":[92],"by":[93,123,127],"Network":[94],"Resetting":[95],"(D2SR),":[96],"which":[97,175],"simultaneously":[98],"satisfies":[99],"efficiency":[101,179],"robustness":[108],"rewards.":[111,186],"Specifically,":[112],"D2SR":[114,165],"method":[115],"can":[116,166,176],"rescue":[117],"from":[120],"misled":[122],"suboptimal":[124],"rewards":[126],"network":[128],"resetting":[129],"parameters":[130],"experience":[133],"rewards,":[136],"thereby":[137],"achieving":[138],"significant":[139],"improvements":[140],"direction":[143],"global":[146],"optimum.":[147],"study,":[150],"through":[151],"series":[153],"ablation":[155],"experiments":[156],"on":[157],"challenging":[158],"robot":[159],"manipulation":[160],"tasks,":[161],"we":[162],"find":[163],"that":[164],"reduce":[167],"requirement":[169],"design,":[174],"also":[177],"balance":[178],"performance":[181],"tasks":[183],"noisy":[185]},"counts_by_year":[{"year":2025,"cited_by_count":3},{"year":2024,"cited_by_count":5}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}
