{"id":"https://openalex.org/W2743627787","doi":"https://doi.org/10.1109/urai.2017.7992767","title":"Three-link planar arm control using reinforcement learning","display_name":"Three-link planar arm control using reinforcement learning","publication_year":2017,"publication_date":"2017-06-01","ids":{"openalex":"https://openalex.org/W2743627787","doi":"https://doi.org/10.1109/urai.2017.7992767","mag":"2743627787"},"language":"en","primary_location":{"id":"doi:10.1109/urai.2017.7992767","is_oa":false,"landing_page_url":"https://doi.org/10.1109/urai.2017.7992767","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2017 14th International Conference on Ubiquitous Robots and Ambient Intelligence (URAI)","raw_type":"proceedings-article"},"type":"conference-paper","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/A5088068728","display_name":"Wonchul Kim","orcid":"https://orcid.org/0000-0003-2476-1827"},"institutions":[{"id":"https://openalex.org/I139264467","display_name":"Seoul National University","ror":"https://ror.org/04h9pn542","country_code":"KR","type":"education","lineage":["https://openalex.org/I139264467"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"Wonchul Kim","raw_affiliation_strings":["Department of Mechanical and Aerospace Engineering, Seoul National University, Seoul, Korea"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Mechanical and Aerospace Engineering, Seoul National University, Seoul, Korea","institution_ids":["https://openalex.org/I139264467"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100329542","display_name":"Taewan Kim","orcid":"https://orcid.org/0000-0003-3319-7797"},"institutions":[{"id":"https://openalex.org/I139264467","display_name":"Seoul National University","ror":"https://ror.org/04h9pn542","country_code":"KR","type":"education","lineage":["https://openalex.org/I139264467"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"Taewan Kim","raw_affiliation_strings":["Department of Mechanical and Aerospace Engineering, Seoul National University, Seoul, Korea"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Mechanical and Aerospace Engineering, Seoul National University, Seoul, Korea","institution_ids":["https://openalex.org/I139264467"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5011485782","display_name":"H. Jin Kim","orcid":null},"institutions":[{"id":"https://openalex.org/I139264467","display_name":"Seoul National University","ror":"https://ror.org/04h9pn542","country_code":"KR","type":"education","lineage":["https://openalex.org/I139264467"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"H. Jin Kim","raw_affiliation_strings":["Department of Mechanical and Aerospace Engineering, Seoul National University, Seoul, Korea"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Mechanical and Aerospace Engineering, Seoul National University, Seoul, Korea","institution_ids":["https://openalex.org/I139264467"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5100602545","display_name":"Sungwan Kim","orcid":"https://orcid.org/0000-0002-9318-849X"},"institutions":[{"id":"https://openalex.org/I2802835388","display_name":"Seoul National University Hospital","ror":"https://ror.org/01z4nnt86","country_code":"KR","type":"healthcare","lineage":["https://openalex.org/I139264467","https://openalex.org/I2802835388"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"Sungwan Kim","raw_affiliation_strings":["Department of Biomedical Engineering, Seoul National University Hospital, Seoul, Korea"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Biomedical Engineering, Seoul National University Hospital, Seoul, Korea","institution_ids":["https://openalex.org/I2802835388"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":8,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"424","last_page":"428"},"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/T12794","display_name":"Adaptive Dynamic Programming Control","score":0.9779999852180481,"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"}},{"id":"https://openalex.org/T10791","display_name":"Advanced Control Systems Optimization","score":0.9772999882698059,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/reinforcement-learning","display_name":"Reinforcement learning","score":0.8708282709121704},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6603824496269226},{"id":"https://openalex.org/keywords/robot","display_name":"Robot","score":0.5728693008422852},{"id":"https://openalex.org/keywords/state","display_name":"State (computer science)","score":0.5074512362480164},{"id":"https://openalex.org/keywords/robot-end-effector","display_name":"Robot end effector","score":0.4822900593280792},{"id":"https://openalex.org/keywords/temporal-difference-learning","display_name":"Temporal difference learning","score":0.4467594027519226},{"id":"https://openalex.org/keywords/robotic-arm","display_name":"Robotic arm","score":0.4379216432571411},{"id":"https://openalex.org/keywords/planar","display_name":"Planar","score":0.42427805066108704},{"id":"https://openalex.org/keywords/control-theory","display_name":"Control theory (sociology)","score":0.4222193956375122},{"id":"https://openalex.org/keywords/link","display_name":"Link (geometry)","score":0.4143370985984802},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4051016569137573},{"id":"https://openalex.org/keywords/control","display_name":"Control (management)","score":0.3833770751953125},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.32577604055404663}],"concepts":[{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.8708282709121704},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6603824496269226},{"id":"https://openalex.org/C90509273","wikidata":"https://www.wikidata.org/wiki/Q11012","display_name":"Robot","level":2,"score":0.5728693008422852},{"id":"https://openalex.org/C48103436","wikidata":"https://www.wikidata.org/wiki/Q599031","display_name":"State (computer science)","level":2,"score":0.5074512362480164},{"id":"https://openalex.org/C8652668","wikidata":"https://www.wikidata.org/wiki/Q1340324","display_name":"Robot end effector","level":3,"score":0.4822900593280792},{"id":"https://openalex.org/C196340769","wikidata":"https://www.wikidata.org/wiki/Q7698910","display_name":"Temporal difference learning","level":3,"score":0.4467594027519226},{"id":"https://openalex.org/C150415221","wikidata":"https://www.wikidata.org/wiki/Q40687","display_name":"Robotic arm","level":2,"score":0.4379216432571411},{"id":"https://openalex.org/C134786449","wikidata":"https://www.wikidata.org/wiki/Q3391255","display_name":"Planar","level":2,"score":0.42427805066108704},{"id":"https://openalex.org/C47446073","wikidata":"https://www.wikidata.org/wiki/Q5165890","display_name":"Control theory (sociology)","level":3,"score":0.4222193956375122},{"id":"https://openalex.org/C2778753846","wikidata":"https://www.wikidata.org/wiki/Q6554239","display_name":"Link (geometry)","level":2,"score":0.4143370985984802},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4051016569137573},{"id":"https://openalex.org/C2775924081","wikidata":"https://www.wikidata.org/wiki/Q55608371","display_name":"Control (management)","level":2,"score":0.3833770751953125},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.32577604055404663},{"id":"https://openalex.org/C31258907","wikidata":"https://www.wikidata.org/wiki/Q1301371","display_name":"Computer network","level":1,"score":0.0},{"id":"https://openalex.org/C121684516","wikidata":"https://www.wikidata.org/wiki/Q7600677","display_name":"Computer graphics (images)","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/urai.2017.7992767","is_oa":false,"landing_page_url":"https://doi.org/10.1109/urai.2017.7992767","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2017 14th International Conference on Ubiquitous Robots and Ambient Intelligence (URAI)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.46000000834465027,"id":"https://metadata.un.org/sdg/16","display_name":"Peace, Justice and strong institutions"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":9,"referenced_works":["https://openalex.org/W32403112","https://openalex.org/W1560074431","https://openalex.org/W1966805688","https://openalex.org/W1977655452","https://openalex.org/W3041202696","https://openalex.org/W3148280926","https://openalex.org/W4214717370","https://openalex.org/W6633472260","https://openalex.org/W6683659000"],"related_works":["https://openalex.org/W4400868993","https://openalex.org/W2145363145","https://openalex.org/W2341346307","https://openalex.org/W129737916","https://openalex.org/W4226385867","https://openalex.org/W2154399718","https://openalex.org/W4321463377","https://openalex.org/W4384574988","https://openalex.org/W2768629321","https://openalex.org/W2966461000"],"abstract_inverted_index":{"In":[0,22],"this":[1],"paper,":[2],"we":[3,79,112],"apply":[4],"reinforcement":[5],"learning(RL)":[6],"to":[7,24,124],"control":[8,25],"a":[9,53,114,125],"3-Dof":[10],"manipulator.":[11],"Learning":[12],"is":[13],"achieved":[14],"by":[15,40,50],"using":[16],"an":[17,87],"on-policy":[18],"temporal":[19],"difference(TD)":[20],"learning.":[21],"order":[23],"the":[26,28,35,38,47,56,63,68,75,96,99,110,122,138,141,145,148],"manipulator,":[27],"TD":[29],"agents":[30],"are":[31],"in":[32,147],"charge":[33],"of":[34,37,74,98],"movements":[36],"robot":[39,139],"adjusting":[41],"each":[42],"angle.":[43],"We":[44,94],"first":[45],"implement":[46],"SARSA":[48],"algorithm":[49,102],"repeatedly":[51],"updating":[52],"hash-table":[54],"with":[55,86,106,144],"current":[57],"and":[58,62,89,103,129],"next":[59],"state-action":[60],"values,":[61],"received":[64],"rewards.":[65],"However,":[66],"since":[67],"conventional":[69],"RL":[70,81,101],"algorithms":[71,82],"have":[72],"issues":[73],"heavy":[76],"computational":[77,149],"load,":[78],"propose":[80],"applying":[83],"multi-agents":[84],"approach":[85],"assumption":[88],"vector":[90],"values":[91],"for":[92,118],"states.":[93],"state":[95],"result":[97],"classical":[100],"compare":[104],"it":[105],"our":[107],"approach.":[108],"For":[109],"simulation,":[111],"test":[113],"three-link":[115],"planar":[116],"arm":[117],"two":[119],"cases:":[120],"positioning":[121],"end-effector":[123],"fixed":[126],"goal":[127,131],"point":[128],"random":[130],"points.":[132],"The":[133],"simulation":[134],"results":[135],"show":[136],"that":[137],"completes":[140],"mission":[142],"successfully":[143],"improvement":[146],"load.":[150]},"counts_by_year":[{"year":2024,"cited_by_count":2},{"year":2023,"cited_by_count":1},{"year":2021,"cited_by_count":2},{"year":2020,"cited_by_count":1},{"year":2019,"cited_by_count":1},{"year":2018,"cited_by_count":1}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}