{"id":"https://openalex.org/W2004822561","doi":"https://doi.org/10.1109/icca.2010.5524384","title":"A new two-layer reinforcement learning approach the control of a 2DOF manipulator","display_name":"A new two-layer reinforcement learning approach the control of a 2DOF manipulator","publication_year":2010,"publication_date":"2010-06-01","ids":{"openalex":"https://openalex.org/W2004822561","doi":"https://doi.org/10.1109/icca.2010.5524384","mag":"2004822561"},"language":"en","primary_location":{"id":"doi:10.1109/icca.2010.5524384","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icca.2010.5524384","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE ICCA 2010","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/A5005025136","display_name":"Albert Albers","orcid":"https://orcid.org/0000-0001-5432-704X"},"institutions":[{"id":"https://openalex.org/I102335020","display_name":"Karlsruhe Institute of Technology","ror":"https://ror.org/04t3en479","country_code":"DE","type":"education","lineage":["https://openalex.org/I102335020","https://openalex.org/I1305996414"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"A. Albers","raw_affiliation_strings":["Institute of Product Development, Karlsruhe Institute of Technology, Karlsruhe, Germany","Institute of Product Development at Karlruhe Institute of Technology, 76131, Germany"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Institute of Product Development, Karlsruhe Institute of Technology, Karlsruhe, Germany","institution_ids":["https://openalex.org/I102335020"]},{"raw_affiliation_string":"Institute of Product Development at Karlruhe Institute of Technology, 76131, Germany","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5064537653","display_name":"S. Schillo","orcid":null},"institutions":[{"id":"https://openalex.org/I102335020","display_name":"Karlsruhe Institute of Technology","ror":"https://ror.org/04t3en479","country_code":"DE","type":"education","lineage":["https://openalex.org/I102335020","https://openalex.org/I1305996414"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"S. Schillo","raw_affiliation_strings":["Institute of Product Development, Karlsruhe Institute of Technology, Karlsruhe, Germany","Institute of Product Development at Karlruhe Institute of Technology, 76131, Germany"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Institute of Product Development, Karlsruhe Institute of Technology, Karlsruhe, Germany","institution_ids":["https://openalex.org/I102335020"]},{"raw_affiliation_string":"Institute of Product Development at Karlruhe Institute of Technology, 76131, Germany","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5059534777","display_name":"D. Sonnleithner","orcid":null},"institutions":[{"id":"https://openalex.org/I102335020","display_name":"Karlsruhe Institute of Technology","ror":"https://ror.org/04t3en479","country_code":"DE","type":"education","lineage":["https://openalex.org/I102335020","https://openalex.org/I1305996414"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"D. Sonnleithner","raw_affiliation_strings":["Institute of Product Development, Karlsruhe Institute of Technology, Karlsruhe, Germany","Institute of Product Development at Karlruhe Institute of Technology, 76131, Germany"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Institute of Product Development, Karlsruhe Institute of Technology, Karlsruhe, Germany","institution_ids":["https://openalex.org/I102335020"]},{"raw_affiliation_string":"Institute of Product Development at Karlruhe Institute of Technology, 76131, Germany","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5045857078","display_name":"M. Frietsch","orcid":null},"institutions":[{"id":"https://openalex.org/I102335020","display_name":"Karlsruhe Institute of Technology","ror":"https://ror.org/04t3en479","country_code":"DE","type":"education","lineage":["https://openalex.org/I102335020","https://openalex.org/I1305996414"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"M. Frietsch","raw_affiliation_strings":["Institute of Product Development, Karlsruhe Institute of Technology, Karlsruhe, Germany","Institute of Product Development at Karlruhe Institute of Technology, 76131, Germany"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Institute of Product Development, Karlsruhe Institute of Technology, Karlsruhe, Germany","institution_ids":["https://openalex.org/I102335020"]},{"raw_affiliation_string":"Institute of Product Development at Karlruhe Institute of Technology, 76131, Germany","institution_ids":[]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5038616868","display_name":"Peter H. Meckl","orcid":null},"institutions":[{"id":"https://openalex.org/I219193219","display_name":"Purdue University West Lafayette","ror":"https://ror.org/02dqehb95","country_code":"US","type":"education","lineage":["https://openalex.org/I219193219"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"P. Meckl","raw_affiliation_strings":["Department of Mechanical Engineering, Purdue University, West Lafayette, IN, USA","Department of Mechanical Engineering, Purdue University, West Lafayette, IN, 47907, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Mechanical Engineering, Purdue University, West Lafayette, IN, USA","institution_ids":["https://openalex.org/I219193219"]},{"raw_affiliation_string":"Department of Mechanical Engineering, Purdue University, West Lafayette, IN, 47907, USA","institution_ids":["https://openalex.org/I219193219"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.5449,"has_fulltext":false,"cited_by_count":3,"citation_normalized_percentile":{"value":0.62242781,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":94},"biblio":{"volume":"8","issue":null,"first_page":"546","last_page":"551"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10462","display_name":"Reinforcement Learning in Robotics","score":0.9991999864578247,"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":0.9991999864578247,"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":0.9887999892234802,"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":0.9860000014305115,"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":0.924544632434845},{"id":"https://openalex.org/keywords/lookup-table","display_name":"Lookup table","score":0.704484224319458},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6932316422462463},{"id":"https://openalex.org/keywords/q-learning","display_name":"Q-learning","score":0.6033720970153809},{"id":"https://openalex.org/keywords/table","display_name":"Table (database)","score":0.535818874835968},{"id":"https://openalex.org/keywords/robot","display_name":"Robot","score":0.5264407396316528},{"id":"https://openalex.org/keywords/action","display_name":"Action (physics)","score":0.4817662239074707},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4788122773170471},{"id":"https://openalex.org/keywords/layer","display_name":"Layer (electronics)","score":0.47326019406318665},{"id":"https://openalex.org/keywords/state","display_name":"State (computer science)","score":0.44114863872528076},{"id":"https://openalex.org/keywords/process","display_name":"Process (computing)","score":0.43416842818260193},{"id":"https://openalex.org/keywords/markov-decision-process","display_name":"Markov decision process","score":0.41970789432525635},{"id":"https://openalex.org/keywords/control-theory","display_name":"Control theory (sociology)","score":0.3257264494895935},{"id":"https://openalex.org/keywords/control","display_name":"Control (management)","score":0.29956984519958496},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.10703611373901367},{"id":"https://openalex.org/keywords/markov-process","display_name":"Markov process","score":0.09970268607139587},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.07671505212783813}],"concepts":[{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.924544632434845},{"id":"https://openalex.org/C134835016","wikidata":"https://www.wikidata.org/wiki/Q690265","display_name":"Lookup table","level":2,"score":0.704484224319458},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6932316422462463},{"id":"https://openalex.org/C188116033","wikidata":"https://www.wikidata.org/wiki/Q2664563","display_name":"Q-learning","level":3,"score":0.6033720970153809},{"id":"https://openalex.org/C45235069","wikidata":"https://www.wikidata.org/wiki/Q278425","display_name":"Table (database)","level":2,"score":0.535818874835968},{"id":"https://openalex.org/C90509273","wikidata":"https://www.wikidata.org/wiki/Q11012","display_name":"Robot","level":2,"score":0.5264407396316528},{"id":"https://openalex.org/C2780791683","wikidata":"https://www.wikidata.org/wiki/Q846785","display_name":"Action (physics)","level":2,"score":0.4817662239074707},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4788122773170471},{"id":"https://openalex.org/C2779227376","wikidata":"https://www.wikidata.org/wiki/Q6505497","display_name":"Layer (electronics)","level":2,"score":0.47326019406318665},{"id":"https://openalex.org/C48103436","wikidata":"https://www.wikidata.org/wiki/Q599031","display_name":"State (computer science)","level":2,"score":0.44114863872528076},{"id":"https://openalex.org/C98045186","wikidata":"https://www.wikidata.org/wiki/Q205663","display_name":"Process (computing)","level":2,"score":0.43416842818260193},{"id":"https://openalex.org/C106189395","wikidata":"https://www.wikidata.org/wiki/Q176789","display_name":"Markov decision process","level":3,"score":0.41970789432525635},{"id":"https://openalex.org/C47446073","wikidata":"https://www.wikidata.org/wiki/Q5165890","display_name":"Control theory (sociology)","level":3,"score":0.3257264494895935},{"id":"https://openalex.org/C2775924081","wikidata":"https://www.wikidata.org/wiki/Q55608371","display_name":"Control (management)","level":2,"score":0.29956984519958496},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.10703611373901367},{"id":"https://openalex.org/C159886148","wikidata":"https://www.wikidata.org/wiki/Q176645","display_name":"Markov process","level":2,"score":0.09970268607139587},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.07671505212783813},{"id":"https://openalex.org/C178790620","wikidata":"https://www.wikidata.org/wiki/Q11351","display_name":"Organic chemistry","level":1,"score":0.0},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.0},{"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/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.0},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"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/C62520636","wikidata":"https://www.wikidata.org/wiki/Q944","display_name":"Quantum mechanics","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icca.2010.5524384","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icca.2010.5524384","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE ICCA 2010","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Peace, Justice and strong institutions","id":"https://metadata.un.org/sdg/16","score":0.6100000143051147}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":21,"referenced_works":["https://openalex.org/W1554663460","https://openalex.org/W1576452626","https://openalex.org/W1952489873","https://openalex.org/W1980516134","https://openalex.org/W2041367235","https://openalex.org/W2082287757","https://openalex.org/W2107726111","https://openalex.org/W2114882146","https://openalex.org/W2121863487","https://openalex.org/W2124175081","https://openalex.org/W2172968643","https://openalex.org/W2589661838","https://openalex.org/W3011120880","https://openalex.org/W4214717370","https://openalex.org/W4285719527","https://openalex.org/W4307347247","https://openalex.org/W4388297464","https://openalex.org/W6634528131","https://openalex.org/W6640954454","https://openalex.org/W6678114464","https://openalex.org/W6734036667"],"related_works":["https://openalex.org/W2386410636","https://openalex.org/W1985560493","https://openalex.org/W1626977535","https://openalex.org/W4284974072","https://openalex.org/W2341346307","https://openalex.org/W3096874164","https://openalex.org/W2357975469","https://openalex.org/W2937181779","https://openalex.org/W2145363145","https://openalex.org/W3168977894"],"abstract_inverted_index":{"This":[0],"paper":[1],"presents":[2],"a":[3,14,47,88,111,121,142,168],"new":[4,112],"machine":[5],"learning":[6,27,105,184],"approach,":[7,120],"based":[8],"on":[9],"reinforcement":[10,183],"learning,":[11],"to":[12,92,140],"control":[13],"highly":[15],"nonlinear":[16],"robot":[17,37],"demonstrator.":[18],"Learning":[19],"is":[20,90,116,126,173],"achieved":[21],"using":[22,66],"an":[23,54],"on-policy":[24],"temporal":[25],"difference":[26],"agent":[28,31,154],"framework.":[29],"The":[30,50,132,149],"controls":[32],"the":[33,36,59,62,67,71,75,81,100,104,129,137,152,157,164,177,181],"movements":[34],"of":[35,61,84,107,123,151,159,166],"by":[38,65,180],"choosing":[39],"torques":[40],"for":[41,145],"each":[42],"joint":[43],"and":[44,74,95],"immediately":[45],"receives":[46],"feedback":[48],"signal.":[49],"implemented":[51],"SARSA-agent":[52],"uses":[53],"update":[55],"rule":[56],"that":[57,156],"calculates":[58],"estimate":[60],"current":[63,68],"state-action":[64,69,77,85],"value,":[70],"received":[72],"reward":[73],"following":[76],"value.":[78],"To":[79,102],"handle":[80],"high":[82],"number":[83],"value":[86],"pairs,":[87],"hash-table":[89],"used":[91],"efficiently":[93],"store":[94],"access":[96],"these":[97],"values":[98],"inside":[99],"lookup-table.":[101],"accelerate":[103],"process":[106],"more":[108,146],"complex":[109,147],"motions,":[110],"second":[113,133],"layer":[114],"approach":[115],"introduced.":[117],"In":[118],"this":[119],"library":[122],"simple":[124],"motions":[125],"created":[127],"in":[128],"first":[130],"layer.":[131],"layer-agent":[134],"then":[135],"combines":[136],"gathered":[138],"experiences":[139],"achieve":[141],"faster":[143],"solution":[144,172,178],"motions.":[148],"evaluation":[150],"two-layer":[153],"shows":[155],"combination":[158],"both":[160],"layers":[161],"dramatically":[162],"increases":[163],"speed":[165],"finding":[167],"solution.":[169],"Additionally,":[170],"its":[171],"often":[174],"better":[175],"than":[176],"found":[179],"pure":[182],"agent.":[185]},"counts_by_year":[{"year":2014,"cited_by_count":1},{"year":2013,"cited_by_count":1}],"updated_date":"2026-07-29T14:22:42.915294","created_date":"2025-10-10T00:00:00"}