{"id":"https://openalex.org/W4299134566","doi":"https://doi.org/10.1109/aim52237.2022.9863259","title":"Balance Between Efficient and Effective Learning: Dense2Sparse Reward Shaping for Robot Manipulation with Environment Uncertainty","display_name":"Balance Between Efficient and Effective Learning: Dense2Sparse Reward Shaping for Robot Manipulation with Environment Uncertainty","publication_year":2022,"publication_date":"2022-07-11","ids":{"openalex":"https://openalex.org/W4299134566","doi":"https://doi.org/10.1109/aim52237.2022.9863259"},"language":"en","primary_location":{"id":"doi:10.1109/aim52237.2022.9863259","is_oa":false,"landing_page_url":"https://doi.org/10.1109/aim52237.2022.9863259","pdf_url":null,"source":{"id":"https://openalex.org/S4363608109","display_name":"2022 IEEE/ASME International Conference on Advanced Intelligent Mechatronics (AIM)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2022 IEEE/ASME International Conference on Advanced Intelligent Mechatronics (AIM)","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/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/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/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":"Kun Dong","raw_affiliation_strings":["Chinese Academy of Sciences,Institute of Intelligent Machines, HFIPS,Hefei,China","University of Science and Technology of China, Hefei, China","Institute of Intelligent Machines, HFIPS, Chinese Academy of Sciences, Hefei, China"],"affiliations":[{"raw_affiliation_string":"Chinese Academy of Sciences,Institute of Intelligent Machines, HFIPS,Hefei,China","institution_ids":["https://openalex.org/I4210099079","https://openalex.org/I19820366"]},{"raw_affiliation_string":"University of Science and Technology of China, Hefei, China","institution_ids":["https://openalex.org/I126520041"]},{"raw_affiliation_string":"Institute of Intelligent Machines, HFIPS, Chinese Academy of Sciences, Hefei, China","institution_ids":["https://openalex.org/I4210099079","https://openalex.org/I19820366"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5058229499","display_name":"Yongle Luo","orcid":"https://orcid.org/0000-0001-9933-3611"},"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/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/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":"Yongle Luo","raw_affiliation_strings":["Chinese Academy of Sciences,Institute of Intelligent Machines, HFIPS,Hefei,China","Institute of Intelligent Machines, HFIPS, Chinese Academy of Sciences, Hefei, China","University of Science and Technology of China, Hefei, China"],"affiliations":[{"raw_affiliation_string":"Chinese Academy of Sciences,Institute of Intelligent Machines, HFIPS,Hefei,China","institution_ids":["https://openalex.org/I4210099079","https://openalex.org/I19820366"]},{"raw_affiliation_string":"Institute of Intelligent Machines, HFIPS, Chinese Academy of Sciences, Hefei, China","institution_ids":["https://openalex.org/I4210099079","https://openalex.org/I19820366"]},{"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/A5059137735","display_name":"Erkang Cheng","orcid":"https://orcid.org/0000-0001-7941-6911"},"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/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":"Erkang Cheng","raw_affiliation_strings":["Chinese Academy of Sciences,Institute of Intelligent Machines, HFIPS,Hefei,China","Institute of Intelligent Machines, HFIPS, Chinese Academy of Sciences, Hefei, China"],"affiliations":[{"raw_affiliation_string":"Chinese Academy of Sciences,Institute of Intelligent Machines, HFIPS,Hefei,China","institution_ids":["https://openalex.org/I4210099079","https://openalex.org/I19820366"]},{"raw_affiliation_string":"Institute of Intelligent Machines, HFIPS, Chinese Academy of Sciences, Hefei, China","institution_ids":["https://openalex.org/I4210099079","https://openalex.org/I19820366"]}]},{"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/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":"Zhiyong Sun","raw_affiliation_strings":["Chinese Academy of Sciences,Institute of Intelligent Machines, HFIPS,Hefei,China","Institute of Intelligent Machines, HFIPS, Chinese Academy of Sciences, Hefei, China"],"affiliations":[{"raw_affiliation_string":"Chinese Academy of Sciences,Institute of Intelligent Machines, HFIPS,Hefei,China","institution_ids":["https://openalex.org/I4210099079","https://openalex.org/I19820366"]},{"raw_affiliation_string":"Institute of Intelligent Machines, HFIPS, Chinese Academy of Sciences, Hefei, China","institution_ids":["https://openalex.org/I4210099079","https://openalex.org/I19820366"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5102841027","display_name":"Lili Zhao","orcid":"https://orcid.org/0000-0002-0634-0482"},"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/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":"Lili Zhao","raw_affiliation_strings":["Chinese Academy of Sciences,Institute of Intelligent Machines, HFIPS,Hefei,China","Institute of Intelligent Machines, HFIPS, Chinese Academy of Sciences, Hefei, China"],"affiliations":[{"raw_affiliation_string":"Chinese Academy of Sciences,Institute of Intelligent Machines, HFIPS,Hefei,China","institution_ids":["https://openalex.org/I4210099079","https://openalex.org/I19820366"]},{"raw_affiliation_string":"Institute of Intelligent Machines, HFIPS, Chinese Academy of Sciences, Hefei, China","institution_ids":["https://openalex.org/I4210099079","https://openalex.org/I19820366"]}]},{"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/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":"Qiang Zhang","raw_affiliation_strings":["Chinese Academy of Sciences,Institute of Intelligent Machines, HFIPS,Hefei,China","Institute of Intelligent Machines, HFIPS, Chinese Academy of Sciences, Hefei, China"],"affiliations":[{"raw_affiliation_string":"Chinese Academy of Sciences,Institute of Intelligent Machines, HFIPS,Hefei,China","institution_ids":["https://openalex.org/I4210099079","https://openalex.org/I19820366"]},{"raw_affiliation_string":"Institute of Intelligent Machines, HFIPS, Chinese Academy of Sciences, Hefei, China","institution_ids":["https://openalex.org/I4210099079","https://openalex.org/I19820366"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5082035144","display_name":"Chao Zhou","orcid":"https://orcid.org/0000-0003-0219-4067"},"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/I4210114698","display_name":"Institute of Plasma Physics","ror":"https://ror.org/033cbzv42","country_code":"CN","type":"facility","lineage":["https://openalex.org/I19820366","https://openalex.org/I2802624667","https://openalex.org/I4210114698"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Chao Zhou","raw_affiliation_strings":["Chinese Academy of Sciences,Institute of Plasma Physics, HFIPS,Hefei,China","Institute of Plasma Physics, HFIPS, Chinese Academy of Sciences, Hefei, China"],"affiliations":[{"raw_affiliation_string":"Chinese Academy of Sciences,Institute of Plasma Physics, HFIPS,Hefei,China","institution_ids":["https://openalex.org/I4210114698","https://openalex.org/I19820366"]},{"raw_affiliation_string":"Institute of Plasma Physics, HFIPS, Chinese Academy of Sciences, Hefei, China","institution_ids":["https://openalex.org/I4210114698","https://openalex.org/I19820366"]}]},{"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/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/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":"Bo Song","raw_affiliation_strings":["Chinese Academy of Sciences,Institute of Intelligent Machines, HFIPS,Hefei,China","Institute of Intelligent Machines, HFIPS, Chinese Academy of Sciences, Hefei, China"],"affiliations":[{"raw_affiliation_string":"Chinese Academy of Sciences,Institute of Intelligent Machines, HFIPS,Hefei,China","institution_ids":["https://openalex.org/I4210099079","https://openalex.org/I19820366"]},{"raw_affiliation_string":"Institute of Intelligent Machines, HFIPS, Chinese Academy of Sciences, Hefei, China","institution_ids":["https://openalex.org/I4210099079","https://openalex.org/I19820366"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":8,"corresponding_author_ids":["https://openalex.org/A5101958555"],"corresponding_institution_ids":["https://openalex.org/I126520041","https://openalex.org/I19820366","https://openalex.org/I4210099079"],"apc_list":null,"apc_paid":null,"fwci":0.831,"has_fulltext":false,"cited_by_count":8,"citation_normalized_percentile":{"value":0.74375135,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":91,"max":98},"biblio":{"volume":null,"issue":null,"first_page":"1192","last_page":"1198"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10462","display_name":"Reinforcement Learning in Robotics","score":0.9955000281333923,"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":0.9955000281333923,"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/T10653","display_name":"Robot Manipulation and Learning","score":0.9853000044822693,"subfield":{"id":"https://openalex.org/subfields/2207","display_name":"Control and Systems 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/T11601","display_name":"Neuroscience and Neural Engineering","score":0.9761000275611877,"subfield":{"id":"https://openalex.org/subfields/2804","display_name":"Cellular and Molecular 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/computer-science","display_name":"Computer science","score":0.7271624207496643},{"id":"https://openalex.org/keywords/robot","display_name":"Robot","score":0.6676493883132935},{"id":"https://openalex.org/keywords/reinforcement-learning","display_name":"Reinforcement learning","score":0.6515902280807495},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.6320167183876038},{"id":"https://openalex.org/keywords/estimator","display_name":"Estimator","score":0.5318049192428589},{"id":"https://openalex.org/keywords/convergence","display_name":"Convergence (economics)","score":0.4511069059371948},{"id":"https://openalex.org/keywords/noise","display_name":"Noise (video)","score":0.43837568163871765},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.4334052801132202},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.08432769775390625}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7271624207496643},{"id":"https://openalex.org/C90509273","wikidata":"https://www.wikidata.org/wiki/Q11012","display_name":"Robot","level":2,"score":0.6676493883132935},{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.6515902280807495},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6320167183876038},{"id":"https://openalex.org/C185429906","wikidata":"https://www.wikidata.org/wiki/Q1130160","display_name":"Estimator","level":2,"score":0.5318049192428589},{"id":"https://openalex.org/C2777303404","wikidata":"https://www.wikidata.org/wiki/Q759757","display_name":"Convergence (economics)","level":2,"score":0.4511069059371948},{"id":"https://openalex.org/C99498987","wikidata":"https://www.wikidata.org/wiki/Q2210247","display_name":"Noise (video)","level":3,"score":0.43837568163871765},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.4334052801132202},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.08432769775390625},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.0},{"id":"https://openalex.org/C50522688","wikidata":"https://www.wikidata.org/wiki/Q189833","display_name":"Economic growth","level":1,"score":0.0},{"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/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/aim52237.2022.9863259","is_oa":false,"landing_page_url":"https://doi.org/10.1109/aim52237.2022.9863259","pdf_url":null,"source":{"id":"https://openalex.org/S4363608109","display_name":"2022 IEEE/ASME International Conference on Advanced Intelligent Mechatronics (AIM)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2022 IEEE/ASME International Conference on Advanced Intelligent Mechatronics (AIM)","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":39,"referenced_works":["https://openalex.org/W1686810756","https://openalex.org/W1777239053","https://openalex.org/W2158782408","https://openalex.org/W2163922914","https://openalex.org/W2302255633","https://openalex.org/W2575705757","https://openalex.org/W2605102758","https://openalex.org/W2741122588","https://openalex.org/W2787938642","https://openalex.org/W2798705390","https://openalex.org/W2810785043","https://openalex.org/W2823112946","https://openalex.org/W2895478303","https://openalex.org/W2899059606","https://openalex.org/W2913350117","https://openalex.org/W2938421504","https://openalex.org/W2950471160","https://openalex.org/W2963184939","https://openalex.org/W2963989568","https://openalex.org/W2968095426","https://openalex.org/W2990747716","https://openalex.org/W2994369162","https://openalex.org/W3091552533","https://openalex.org/W3130717831","https://openalex.org/W3164947292","https://openalex.org/W4300799055","https://openalex.org/W6637373629","https://openalex.org/W6638088447","https://openalex.org/W6696324988","https://openalex.org/W6740801417","https://openalex.org/W6742461812","https://openalex.org/W6748839928","https://openalex.org/W6753060773","https://openalex.org/W6753243525","https://openalex.org/W6755421158","https://openalex.org/W6755445836","https://openalex.org/W6759301632","https://openalex.org/W6764800732","https://openalex.org/W6766125988"],"related_works":["https://openalex.org/W4362501864","https://openalex.org/W4306904969","https://openalex.org/W4380318855","https://openalex.org/W4287880334","https://openalex.org/W4366700029","https://openalex.org/W2138720691","https://openalex.org/W2031695474","https://openalex.org/W4285230481","https://openalex.org/W2586732548","https://openalex.org/W3049728571"],"abstract_inverted_index":{"Efficient":[0],"and":[1,40,82,99,138,154,167],"effective":[2],"learning":[3,13,42,97],"is":[4,33,146],"one":[5],"of":[6,10,22,29,78,87,118,148],"the":[7,16,23,27,41,48,55,74,79,83,88,96,100,122,142,159],"ultimate":[8],"goals":[9],"deep":[11,123],"reinforcement":[12],"(DRL),":[14],"although":[15],"compromise":[17],"has":[18,170],"been":[19],"made":[20],"most":[21],"time,":[24],"especially":[25],"for":[26,36,106,174],"application":[28],"robot":[30,37,107,140],"manipulations.":[31],"Learning":[32],"always":[34],"expensive":[35],"manipulation":[38,108],"tasks":[39],"effectiveness":[43],"could":[44],"be":[45],"affected":[46],"by":[47],"system":[49,128,175],"uncertainty.":[50,129,176],"In":[51],"order":[52],"to":[53,91],"solve":[54],"above":[56],"challenges,":[57],"in":[58,135],"this":[59],"study,":[60],"we":[61],"proposed":[62,143],"a":[63,93,116,150,171],"simple":[64],"but":[65],"powerful":[66],"reward":[67,81,153],"shaping":[68],"method,":[69],"namely":[70],"Dense2Sparse.":[71],"It":[72],"combines":[73],"fast":[75],"convergence":[76],"advantage":[77],"dense":[80,163],"noise/uncertainty":[84],"isolation":[85],"merit":[86],"sparse":[89,165],"reward,":[90,166],"achieve":[92],"balance":[94],"between":[95],"efficiency":[98],"effectiveness,":[101],"which":[102],"makes":[103],"it":[104,168],"suitable":[105],"tasks.":[109],"We":[110],"evaluated":[111],"our":[112],"Dense2Sparse":[113,144],"method":[114,145],"with":[115,127,158],"series":[117],"ablation":[119],"experiments":[120],"using":[121,161],"learning-based":[124],"state":[125],"estimator":[126],"The":[130],"testing":[131],"results":[132],"show":[133],"that,":[134],"both":[136],"simulation":[137],"real":[139],"implementation,":[141],"capable":[147],"getting":[149],"higher":[151],"expected":[152],"success":[155],"rate":[156],"compared":[157],"ones":[160],"standalone":[162],"or":[164],"also":[169],"superior":[172],"tolerance":[173]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2024,"cited_by_count":4},{"year":2023,"cited_by_count":3}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}