{"id":"https://openalex.org/W4225568555","doi":"https://doi.org/10.1109/robio54168.2021.9739340","title":"Training a Robotic Arm Movement with Deep Reinforcement Learning","display_name":"Training a Robotic Arm Movement with Deep Reinforcement Learning","publication_year":2021,"publication_date":"2021-12-27","ids":{"openalex":"https://openalex.org/W4225568555","doi":"https://doi.org/10.1109/robio54168.2021.9739340"},"language":"en","primary_location":{"id":"doi:10.1109/robio54168.2021.9739340","is_oa":false,"landing_page_url":"https://doi.org/10.1109/robio54168.2021.9739340","pdf_url":null,"source":{"id":"https://openalex.org/S4363607846","display_name":"2021 IEEE International Conference on Robotics and Biomimetics (ROBIO)","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":"2021 IEEE International Conference on Robotics and Biomimetics (ROBIO)","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/A5086080320","display_name":"Xiaohan Ni","orcid":null},"institutions":[{"id":"https://openalex.org/I150744194","display_name":"Waseda University","ror":"https://ror.org/00ntfnx83","country_code":"JP","type":"education","lineage":["https://openalex.org/I150744194"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Xiaohan Ni","raw_affiliation_strings":["Waseda University,Graduate School of Information, Production and Systems,Fukuoka,Japan","Graduate School of Information, Production and Systems, Waseda University, Fukuoka, Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Waseda University,Graduate School of Information, Production and Systems,Fukuoka,Japan","institution_ids":["https://openalex.org/I150744194"]},{"raw_affiliation_string":"Graduate School of Information, Production and Systems, Waseda University, Fukuoka, Japan","institution_ids":["https://openalex.org/I150744194"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5032967539","display_name":"Xin He","orcid":"https://orcid.org/0000-0003-1026-5902"},"institutions":[{"id":"https://openalex.org/I150744194","display_name":"Waseda University","ror":"https://ror.org/00ntfnx83","country_code":"JP","type":"education","lineage":["https://openalex.org/I150744194"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Xin He","raw_affiliation_strings":["Waseda University,Graduate School of Information, Production and Systems,Fukuoka,Japan","Graduate School of Information, Production and Systems, Waseda University, Fukuoka, Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Waseda University,Graduate School of Information, Production and Systems,Fukuoka,Japan","institution_ids":["https://openalex.org/I150744194"]},{"raw_affiliation_string":"Graduate School of Information, Production and Systems, Waseda University, Fukuoka, Japan","institution_ids":["https://openalex.org/I150744194"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5005634226","display_name":"Takafumi Matsumaru","orcid":"https://orcid.org/0000-0001-7776-2984"},"institutions":[{"id":"https://openalex.org/I150744194","display_name":"Waseda University","ror":"https://ror.org/00ntfnx83","country_code":"JP","type":"education","lineage":["https://openalex.org/I150744194"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Takafumi Matsumaru","raw_affiliation_strings":["Waseda University,Graduate School of Information, Production and Systems,Fukuoka,Japan","Graduate School of Information, Production and Systems, Waseda University, Fukuoka, Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Waseda University,Graduate School of Information, Production and Systems,Fukuoka,Japan","institution_ids":["https://openalex.org/I150744194"]},{"raw_affiliation_string":"Graduate School of Information, Production and Systems, Waseda University, Fukuoka, Japan","institution_ids":["https://openalex.org/I150744194"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.2537,"has_fulltext":false,"cited_by_count":3,"citation_normalized_percentile":{"value":0.55157116,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":95},"biblio":{"volume":null,"issue":null,"first_page":"595","last_page":"600"},"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":0.9944999814033508,"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/T12794","display_name":"Adaptive Dynamic Programming Control","score":0.9757000207901001,"subfield":{"id":"https://openalex.org/subfields/1703","display_name":"Computational Theory and Mathematics"},"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":0.8174867033958435},{"id":"https://openalex.org/keywords/robotic-arm","display_name":"Robotic arm","score":0.7616361379623413},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.7172659039497375},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7008174061775208},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5619126558303833},{"id":"https://openalex.org/keywords/robot-manipulator","display_name":"Robot manipulator","score":0.5394521355628967},{"id":"https://openalex.org/keywords/control","display_name":"Control (management)","score":0.5138087868690491},{"id":"https://openalex.org/keywords/scheme","display_name":"Scheme (mathematics)","score":0.49540722370147705},{"id":"https://openalex.org/keywords/robot","display_name":"Robot","score":0.43445825576782227},{"id":"https://openalex.org/keywords/simulation","display_name":"Simulation","score":0.3797062635421753},{"id":"https://openalex.org/keywords/control-engineering","display_name":"Control engineering","score":0.3675025701522827},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.17078116536140442},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.0729086697101593}],"concepts":[{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.8174867033958435},{"id":"https://openalex.org/C150415221","wikidata":"https://www.wikidata.org/wiki/Q40687","display_name":"Robotic arm","level":2,"score":0.7616361379623413},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.7172659039497375},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7008174061775208},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5619126558303833},{"id":"https://openalex.org/C2985527887","wikidata":"https://www.wikidata.org/wiki/Q1587588","display_name":"Robot manipulator","level":3,"score":0.5394521355628967},{"id":"https://openalex.org/C2775924081","wikidata":"https://www.wikidata.org/wiki/Q55608371","display_name":"Control (management)","level":2,"score":0.5138087868690491},{"id":"https://openalex.org/C77618280","wikidata":"https://www.wikidata.org/wiki/Q1155772","display_name":"Scheme (mathematics)","level":2,"score":0.49540722370147705},{"id":"https://openalex.org/C90509273","wikidata":"https://www.wikidata.org/wiki/Q11012","display_name":"Robot","level":2,"score":0.43445825576782227},{"id":"https://openalex.org/C44154836","wikidata":"https://www.wikidata.org/wiki/Q45045","display_name":"Simulation","level":1,"score":0.3797062635421753},{"id":"https://openalex.org/C133731056","wikidata":"https://www.wikidata.org/wiki/Q4917288","display_name":"Control engineering","level":1,"score":0.3675025701522827},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.17078116536140442},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.0729086697101593},{"id":"https://openalex.org/C134306372","wikidata":"https://www.wikidata.org/wiki/Q7754","display_name":"Mathematical analysis","level":1,"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/robio54168.2021.9739340","is_oa":false,"landing_page_url":"https://doi.org/10.1109/robio54168.2021.9739340","pdf_url":null,"source":{"id":"https://openalex.org/S4363607846","display_name":"2021 IEEE International Conference on Robotics and Biomimetics (ROBIO)","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":"2021 IEEE International Conference on Robotics and Biomimetics (ROBIO)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.5899999737739563,"display_name":"Life in Land","id":"https://metadata.un.org/sdg/15"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":14,"referenced_works":["https://openalex.org/W2257979135","https://openalex.org/W2346736747","https://openalex.org/W2575705757","https://openalex.org/W2603266952","https://openalex.org/W2754517384","https://openalex.org/W2890326782","https://openalex.org/W2909718913","https://openalex.org/W2953364219","https://openalex.org/W2963864421","https://openalex.org/W3003524200","https://openalex.org/W4214717370","https://openalex.org/W6684921986","https://openalex.org/W6735506055","https://openalex.org/W6754787993"],"related_works":["https://openalex.org/W4321204549","https://openalex.org/W4293149836","https://openalex.org/W4225854080","https://openalex.org/W2146701564","https://openalex.org/W2980824095","https://openalex.org/W2893404461","https://openalex.org/W2913425172","https://openalex.org/W3042010185","https://openalex.org/W2216263703","https://openalex.org/W4308068298"],"abstract_inverted_index":{"This":[0],"paper":[1,45,74],"introduces":[2],"a":[3,92],"general":[4],"experimental":[5,68],"design":[6,69,83],"scheme":[7],"for":[8,33,52,79,87],"conditions":[9],"and":[10,57,84,94],"parameter":[11,85],"settings":[12,86],"of":[13,67],"robotic":[14,31,53],"arm":[15,32,54],"control":[16,36,55,61],"under":[17],"the":[18,30,35,40,65,96],"specific":[19],"task":[20],"when":[21],"using":[22,88],"Deep":[23],"Deterministic":[24],"Policy":[25],"Gradient(DDPG)":[26],"algorithm":[27],"to":[28,63,90],"train":[29,91],"completing":[34],"task.":[37],"Based":[38],"on":[39],"Coppelia":[41],"simulation":[42],"tool,":[43],"this":[44,73],"builds":[46],"an":[47,76],"interactive":[48],"reinforcement":[49],"learning":[50],"environment":[51],"tasks,":[56],"designs":[58],"two":[59],"different":[60],"tasks":[62],"verify":[64],"validity":[66],"schemes.":[70],"Conclusions":[71],"in":[72],"provide":[75],"important":[77],"reference":[78],"finding":[80],"suitable":[81],"environmental":[82],"DDPG":[89],"manipulator":[93],"improving":[95],"training":[97],"effect.":[98]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2023,"cited_by_count":1},{"year":2022,"cited_by_count":1}],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2025-10-10T00:00:00"}