{"id":"https://openalex.org/W3034321388","doi":"https://doi.org/10.1109/access.2020.3001130","title":"A Reinforcement Learning-Based Framework for Robot Manipulation Skill Acquisition","display_name":"A Reinforcement Learning-Based Framework for Robot Manipulation Skill Acquisition","publication_year":2020,"publication_date":"2020-01-01","ids":{"openalex":"https://openalex.org/W3034321388","doi":"https://doi.org/10.1109/access.2020.3001130","mag":"3034321388"},"language":"en","primary_location":{"id":"doi:10.1109/access.2020.3001130","is_oa":true,"landing_page_url":"https://doi.org/10.1109/access.2020.3001130","pdf_url":"https://ieeexplore.ieee.org/ielx7/6287639/8948470/09112186.pdf","source":{"id":"https://openalex.org/S2485537415","display_name":"IEEE Access","issn_l":"2169-3536","issn":["2169-3536"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Access","raw_type":"journal-article"},"type":"article","indexed_in":["crossref","doaj"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://ieeexplore.ieee.org/ielx7/6287639/8948470/09112186.pdf","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5100407529","display_name":"Dong Liu","orcid":"https://orcid.org/0000-0003-3988-7879"},"institutions":[{"id":"https://openalex.org/I27357992","display_name":"Dalian University of Technology","ror":"https://ror.org/023hj5876","country_code":"CN","type":"education","lineage":["https://openalex.org/I27357992"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Dong Liu","raw_affiliation_strings":["Jiangsu Research Institute Company, Ltd., Dalian University of Technology, Changzhou, China","School of Mechanical Engineering, Dalian University of Technology, Dalian, China"],"raw_orcid":"https://orcid.org/0000-0003-3988-7879","affiliations":[{"raw_affiliation_string":"Jiangsu Research Institute Company, Ltd., Dalian University of Technology, Changzhou, China","institution_ids":["https://openalex.org/I27357992"]},{"raw_affiliation_string":"School of Mechanical Engineering, Dalian University of Technology, Dalian, China","institution_ids":["https://openalex.org/I27357992"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5056771192","display_name":"Zitu Wang","orcid":null},"institutions":[{"id":"https://openalex.org/I27357992","display_name":"Dalian University of Technology","ror":"https://ror.org/023hj5876","country_code":"CN","type":"education","lineage":["https://openalex.org/I27357992"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zitu Wang","raw_affiliation_strings":["School of Mechanical Engineering, Dalian University of Technology, Dalian, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Mechanical Engineering, Dalian University of Technology, Dalian, China","institution_ids":["https://openalex.org/I27357992"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5063857264","display_name":"Binpeng Lu","orcid":"https://orcid.org/0000-0002-3211-7401"},"institutions":[{"id":"https://openalex.org/I27357992","display_name":"Dalian University of Technology","ror":"https://ror.org/023hj5876","country_code":"CN","type":"education","lineage":["https://openalex.org/I27357992"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Binpeng Lu","raw_affiliation_strings":["School of Mechanical Engineering, Dalian University of Technology, Dalian, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Mechanical Engineering, Dalian University of Technology, Dalian, China","institution_ids":["https://openalex.org/I27357992"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5083968188","display_name":"Ming Cong","orcid":"https://orcid.org/0000-0002-8305-9352"},"institutions":[{"id":"https://openalex.org/I27357992","display_name":"Dalian University of Technology","ror":"https://ror.org/023hj5876","country_code":"CN","type":"education","lineage":["https://openalex.org/I27357992"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Ming Cong","raw_affiliation_strings":["School of Mechanical Engineering, Dalian University of Technology, Dalian, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Mechanical Engineering, Dalian University of Technology, Dalian, China","institution_ids":["https://openalex.org/I27357992"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5042003426","display_name":"Honghua Yu","orcid":"https://orcid.org/0000-0002-0782-346X"},"institutions":[{"id":"https://openalex.org/I27357992","display_name":"Dalian University of Technology","ror":"https://ror.org/023hj5876","country_code":"CN","type":"education","lineage":["https://openalex.org/I27357992"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Honghua Yu","raw_affiliation_strings":["School of Mechanical Engineering, Dalian University of Technology, Dalian, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Mechanical Engineering, Dalian University of Technology, Dalian, China","institution_ids":["https://openalex.org/I27357992"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5053023376","display_name":"Qiang Zou","orcid":"https://orcid.org/0000-0002-6651-1554"},"institutions":[{"id":"https://openalex.org/I27357992","display_name":"Dalian University of Technology","ror":"https://ror.org/023hj5876","country_code":"CN","type":"education","lineage":["https://openalex.org/I27357992"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Qiang Zou","raw_affiliation_strings":["Jiangsu Research Institute Company, Ltd., Dalian University of Technology, Changzhou, China","School of Mechanical Engineering, Dalian University of Technology, Dalian, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Jiangsu Research Institute Company, Ltd., Dalian University of Technology, Changzhou, China","institution_ids":["https://openalex.org/I27357992"]},{"raw_affiliation_string":"School of Mechanical Engineering, Dalian University of Technology, Dalian, China","institution_ids":["https://openalex.org/I27357992"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I27357992"],"apc_list":{"value":1850,"currency":"USD","value_usd":1850},"apc_paid":{"value":1850,"currency":"USD","value_usd":1850},"fwci":1.5645,"has_fulltext":true,"cited_by_count":28,"citation_normalized_percentile":{"value":0.86744289,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":99},"biblio":{"volume":"8","issue":null,"first_page":"108429","last_page":"108437"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10462","display_name":"Reinforcement Learning in Robotics","score":0.9998000264167786,"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":0.9998000264167786,"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":0.9968000054359436,"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/T10586","display_name":"Robotic Path Planning Algorithms","score":0.979200005531311,"subfield":{"id":"https://openalex.org/subfields/1707","display_name":"Computer Vision and Pattern Recognition"},"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/reinforcement-learning","display_name":"Reinforcement learning","score":0.8792559504508972},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7561845779418945},{"id":"https://openalex.org/keywords/robot-learning","display_name":"Robot learning","score":0.7263129949569702},{"id":"https://openalex.org/keywords/robot","display_name":"Robot","score":0.6698410511016846},{"id":"https://openalex.org/keywords/markov-decision-process","display_name":"Markov decision process","score":0.5698993802070618},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5626780390739441},{"id":"https://openalex.org/keywords/set","display_name":"Set (abstract data type)","score":0.5556125640869141},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.49601587653160095},{"id":"https://openalex.org/keywords/matching","display_name":"Matching (statistics)","score":0.4430762827396393},{"id":"https://openalex.org/keywords/q-learning","display_name":"Q-learning","score":0.42602866888046265},{"id":"https://openalex.org/keywords/object","display_name":"Object (grammar)","score":0.41030535101890564},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.33017057180404663},{"id":"https://openalex.org/keywords/markov-process","display_name":"Markov process","score":0.3027821183204651},{"id":"https://openalex.org/keywords/mobile-robot","display_name":"Mobile robot","score":0.2860157787799835},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.1322934627532959}],"concepts":[{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.8792559504508972},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7561845779418945},{"id":"https://openalex.org/C188888258","wikidata":"https://www.wikidata.org/wiki/Q7353390","display_name":"Robot learning","level":4,"score":0.7263129949569702},{"id":"https://openalex.org/C90509273","wikidata":"https://www.wikidata.org/wiki/Q11012","display_name":"Robot","level":2,"score":0.6698410511016846},{"id":"https://openalex.org/C106189395","wikidata":"https://www.wikidata.org/wiki/Q176789","display_name":"Markov decision process","level":3,"score":0.5698993802070618},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5626780390739441},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.5556125640869141},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.49601587653160095},{"id":"https://openalex.org/C165064840","wikidata":"https://www.wikidata.org/wiki/Q1321061","display_name":"Matching (statistics)","level":2,"score":0.4430762827396393},{"id":"https://openalex.org/C188116033","wikidata":"https://www.wikidata.org/wiki/Q2664563","display_name":"Q-learning","level":3,"score":0.42602866888046265},{"id":"https://openalex.org/C2781238097","wikidata":"https://www.wikidata.org/wiki/Q175026","display_name":"Object (grammar)","level":2,"score":0.41030535101890564},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.33017057180404663},{"id":"https://openalex.org/C159886148","wikidata":"https://www.wikidata.org/wiki/Q176645","display_name":"Markov process","level":2,"score":0.3027821183204651},{"id":"https://openalex.org/C19966478","wikidata":"https://www.wikidata.org/wiki/Q4810574","display_name":"Mobile robot","level":3,"score":0.2860157787799835},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.1322934627532959},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.0},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","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},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/access.2020.3001130","is_oa":true,"landing_page_url":"https://doi.org/10.1109/access.2020.3001130","pdf_url":"https://ieeexplore.ieee.org/ielx7/6287639/8948470/09112186.pdf","source":{"id":"https://openalex.org/S2485537415","display_name":"IEEE Access","issn_l":"2169-3536","issn":["2169-3536"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Access","raw_type":"journal-article"},{"id":"pmh:oai:doaj.org/article:37b561cf8f4d4c53acb4096a4e930909","is_oa":true,"landing_page_url":"https://doaj.org/article/37b561cf8f4d4c53acb4096a4e930909","pdf_url":null,"source":{"id":"https://openalex.org/S4306401280","display_name":"DOAJ (DOAJ: Directory of Open Access Journals)","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":"repository"},"license":"cc-by-sa","license_id":"https://openalex.org/licenses/cc-by-sa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"IEEE Access, Vol 8, Pp 108429-108437 (2020)","raw_type":"article"}],"best_oa_location":{"id":"doi:10.1109/access.2020.3001130","is_oa":true,"landing_page_url":"https://doi.org/10.1109/access.2020.3001130","pdf_url":"https://ieeexplore.ieee.org/ielx7/6287639/8948470/09112186.pdf","source":{"id":"https://openalex.org/S2485537415","display_name":"IEEE Access","issn_l":"2169-3536","issn":["2169-3536"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Access","raw_type":"journal-article"},"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/4","display_name":"Quality Education","score":0.5799999833106995}],"awards":[{"id":"https://openalex.org/G2508542662","display_name":null,"funder_award_id":"BK20180190","funder_id":"https://openalex.org/F4320322769","funder_display_name":"Natural Science Foundation of Jiangsu Province"},{"id":"https://openalex.org/G3558407796","display_name":null,"funder_award_id":"DUT19JC56","funder_id":"https://openalex.org/F4320335787","funder_display_name":"Fundamental Research Funds for the Central Universities"},{"id":"https://openalex.org/G4271958271","display_name":null,"funder_award_id":"61873045","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"}],"funders":[{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"},{"id":"https://openalex.org/F4320321605","display_name":"Government of Jiangsu Province","ror":"https://ror.org/004svx814"},{"id":"https://openalex.org/F4320322769","display_name":"Natural Science Foundation of Jiangsu Province","ror":"https://ror.org/01h0zpd94"},{"id":"https://openalex.org/F4320335787","display_name":"Fundamental Research Funds for the Central Universities","ror":null}],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W3034321388.pdf","grobid_xml":"https://content.openalex.org/works/W3034321388.grobid-xml"},"referenced_works_count":44,"referenced_works":["https://openalex.org/W163528269","https://openalex.org/W1976027761","https://openalex.org/W1977655452","https://openalex.org/W2107726111","https://openalex.org/W2137549137","https://openalex.org/W2142964003","https://openalex.org/W2145339207","https://openalex.org/W2155007355","https://openalex.org/W2167903421","https://openalex.org/W2277684984","https://openalex.org/W2367922714","https://openalex.org/W2528489519","https://openalex.org/W2575705757","https://openalex.org/W2610395436","https://openalex.org/W2726187156","https://openalex.org/W2736601468","https://openalex.org/W2810785043","https://openalex.org/W2893889064","https://openalex.org/W2902143777","https://openalex.org/W2912757816","https://openalex.org/W2949248709","https://openalex.org/W2962889474","https://openalex.org/W2963161674","https://openalex.org/W2963190967","https://openalex.org/W2963484919","https://openalex.org/W2963780790","https://openalex.org/W2964043796","https://openalex.org/W2964161785","https://openalex.org/W2964177756","https://openalex.org/W2964250417","https://openalex.org/W2966477667","https://openalex.org/W2978070926","https://openalex.org/W4293864724","https://openalex.org/W4295837424","https://openalex.org/W6682849425","https://openalex.org/W6692846177","https://openalex.org/W6718738585","https://openalex.org/W6737327832","https://openalex.org/W6740222838","https://openalex.org/W6741002519","https://openalex.org/W6744935223","https://openalex.org/W6748972340","https://openalex.org/W6753243525","https://openalex.org/W6756714161"],"related_works":["https://openalex.org/W2386410636","https://openalex.org/W1985560493","https://openalex.org/W1626977535","https://openalex.org/W4284974072","https://openalex.org/W3096874164","https://openalex.org/W2357975469","https://openalex.org/W2937181779","https://openalex.org/W2145363145","https://openalex.org/W3168977894","https://openalex.org/W3127551068"],"abstract_inverted_index":{"This":[0],"paper":[1],"studies":[2],"robot":[3,60,76,104,129,135],"manipulation":[4,87,136],"skill":[5,120,152],"acquisition":[6],"based":[7,39],"on":[8,40],"a":[9,24,34],"proposed":[10,96],"reinforcement":[11,105,148],"learning":[12,26,106,149],"framework.":[13,107],"Robot":[14],"can":[15],"learn":[16,116],"policy":[17],"autonomously":[18],"by":[19],"interacting":[20],"with":[21,23,86,111],"environment":[22,125],"better":[25],"efficiency.":[27],"Aiming":[28],"at":[29],"the":[30,68,72,90,98,103,112,119,127,142,147],"manipulator":[31,77],"operation":[32],"task,":[33],"reward":[35,70],"function":[36],"design":[37],"method":[38],"objects":[41],"configuration":[42],"matching":[43],"(OCM)":[44],"is":[45,48,78,95,130],"proposed.":[46],"It":[47],"simple":[49],"and":[50,55,61,67,117,133,144],"suitable":[51],"for":[52,151],"most":[53],"Pick":[54],"Place":[56],"skills":[57],"learning.":[58],"Integrating":[59],"object":[62],"state,":[63],"high-level":[64],"action":[65],"set":[66,88,131],"designed":[69,139],"function,":[71],"Markov":[73,113],"model":[74,114],"of":[75,92,146],"built.":[79],"An":[80],"improved":[81],"Proximal":[82],"Policy":[83],"Optimize":[84],"algorithm":[85],"as":[89,97,126],"output":[91],"Actor":[93],"(MAPPO)":[94],"main":[99],"structure":[100],"to":[101,115,140],"construct":[102],"The":[108],"framework":[109,150],"combines":[110],"optimize":[118],"policy.":[121],"A":[122],"same":[123],"simulation":[124],"real":[128],"up,":[132],"three":[134],"tasks":[137],"are":[138],"verify":[141],"effectiveness":[143],"feasibility":[145],"acquisition.":[153]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":7},{"year":2024,"cited_by_count":8},{"year":2023,"cited_by_count":4},{"year":2022,"cited_by_count":3},{"year":2021,"cited_by_count":4},{"year":2020,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}
