{"id":"https://openalex.org/W2121294372","doi":"https://doi.org/10.1007/s00422-009-0295-8","title":"Learning to reach by reinforcement learning using a receptive field based function approximation approach with continuous actions","display_name":"Learning to reach by reinforcement learning using a receptive field based function approximation approach with continuous actions","publication_year":2009,"publication_date":"2009-02-19","ids":{"openalex":"https://openalex.org/W2121294372","doi":"https://doi.org/10.1007/s00422-009-0295-8","mag":"2121294372","pmid":"https://pubmed.ncbi.nlm.nih.gov/19229556"},"language":"en","primary_location":{"id":"doi:10.1007/s00422-009-0295-8","is_oa":true,"landing_page_url":"https://doi.org/10.1007/s00422-009-0295-8","pdf_url":"https://link.springer.com/content/pdf/10.1007/s00422-009-0295-8.pdf","source":{"id":"https://openalex.org/S87357125","display_name":"Biological Cybernetics","issn_l":"0340-1200","issn":["0340-1200","1432-0770"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319900","host_organization_name":"Springer Science+Business Media","host_organization_lineage":["https://openalex.org/P4310319900","https://openalex.org/P4310319965"],"host_organization_lineage_names":["Springer Science+Business Media","Springer Nature"],"type":"journal"},"license":"cc-by-nc","license_id":"https://openalex.org/licenses/cc-by-nc","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Biological Cybernetics","raw_type":"journal-article"},"type":"article","indexed_in":["crossref","pubmed"],"open_access":{"is_oa":true,"oa_status":"hybrid","oa_url":"https://link.springer.com/content/pdf/10.1007/s00422-009-0295-8.pdf","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5026724617","display_name":"Minija Tamo\u0161i\u016bnait\u0117","orcid":"https://orcid.org/0000-0003-2996-3612"},"institutions":[{"id":"https://openalex.org/I188730046","display_name":"Vytautas Magnus University","ror":"https://ror.org/04y7eh037","country_code":"LT","type":"education","lineage":["https://openalex.org/I188730046"]},{"id":"https://openalex.org/I4210087171","display_name":"Bernstein Center for Computational Neuroscience G\u00f6ttingen","ror":"https://ror.org/003g6b432","country_code":"DE","type":"government","lineage":["https://openalex.org/I4210087171","https://openalex.org/I4210092532"]}],"countries":["DE","LT"],"is_corresponding":false,"raw_author_name":"Minija Tamosiunaite","raw_affiliation_strings":["Bernstein Centre for Computational Neuroscience, University of G\u00f6ttingen, Bunsenstrasse 10, G\u00f6ttingen, Germany. m.tamosiunaite@if.vdu.lt","University of G\u00f6ttingen, Bernstein Centre for Computational Neuroscience, Bunsenstr. 10, 37073, G\u00f6ttingen, Germany and Vytautas Magnus University, Department of Informatics, Vileikos ...#TAB#"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Bernstein Centre for Computational Neuroscience, University of G\u00f6ttingen, Bunsenstrasse 10, G\u00f6ttingen, Germany. m.tamosiunaite@if.vdu.lt","institution_ids":["https://openalex.org/I4210087171"]},{"raw_affiliation_string":"University of G\u00f6ttingen, Bernstein Centre for Computational Neuroscience, Bunsenstr. 10, 37073, G\u00f6ttingen, Germany and Vytautas Magnus University, Department of Informatics, Vileikos ...#TAB#","institution_ids":["https://openalex.org/I188730046"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5012730104","display_name":"Tamim Asfour","orcid":"https://orcid.org/0000-0003-4879-7680"},"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":"Tamim Asfour","raw_affiliation_strings":["Institute for Computer Science and Engineering, Universit\u00e4t Karlsruhe (TH), Karlsruhe, Germany","Universit\u00e4t Karlsruhe (TH), Institute for Computer Science and Engineering, Karlsruhe, Germany#TAB#"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Institute for Computer Science and Engineering, Universit\u00e4t Karlsruhe (TH), Karlsruhe, Germany","institution_ids":["https://openalex.org/I102335020"]},{"raw_affiliation_string":"Universit\u00e4t Karlsruhe (TH), Institute for Computer Science and Engineering, Karlsruhe, Germany#TAB#","institution_ids":["https://openalex.org/I102335020"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5023811677","display_name":"Florentin W\u00f6rg\u00f6tter","orcid":null},"institutions":[{"id":"https://openalex.org/I4210087171","display_name":"Bernstein Center for Computational Neuroscience G\u00f6ttingen","ror":"https://ror.org/003g6b432","country_code":"DE","type":"government","lineage":["https://openalex.org/I4210087171","https://openalex.org/I4210092532"]},{"id":"https://openalex.org/I74656192","display_name":"University of G\u00f6ttingen","ror":"https://ror.org/01y9bpm73","country_code":"DE","type":"education","lineage":["https://openalex.org/I74656192"]}],"countries":["DE"],"is_corresponding":true,"raw_author_name":"Florentin W\u00f6rg\u00f6tter","raw_affiliation_strings":["Bernstein Centre for Computational Neuroscience, University of G\u00f6ttingen, Bunsenstr. 10, 37073, G\u00f6ttingen, Germany","University of G\u00f6ttingen, Bernstein Centre for Computational Neuroscience, Bunsenstr. 10, 37073, G\u00f6ttingen, Germany#TAB#"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Bernstein Centre for Computational Neuroscience, University of G\u00f6ttingen, Bunsenstr. 10, 37073, G\u00f6ttingen, Germany","institution_ids":["https://openalex.org/I4210087171","https://openalex.org/I74656192"]},{"raw_affiliation_string":"University of G\u00f6ttingen, Bernstein Centre for Computational Neuroscience, Bunsenstr. 10, 37073, G\u00f6ttingen, Germany#TAB#","institution_ids":["https://openalex.org/I74656192"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5023811677"],"corresponding_institution_ids":["https://openalex.org/I4210087171","https://openalex.org/I74656192"],"apc_list":{"value":3590,"currency":"USD","value_usd":3590},"apc_paid":{"value":3590,"currency":"USD","value_usd":3590},"fwci":3.6637,"has_fulltext":true,"cited_by_count":14,"citation_normalized_percentile":{"value":0.93360399,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":89,"max":97},"biblio":{"volume":"100","issue":"3","first_page":"249","last_page":"260"},"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/T10142","display_name":"Formal Methods in Verification","score":0.9585999846458435,"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/T10653","display_name":"Robot Manipulation and Learning","score":0.9509000182151794,"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":0.8146553039550781},{"id":"https://openalex.org/keywords/state-space","display_name":"State space","score":0.6564268469810486},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.6109107732772827},{"id":"https://openalex.org/keywords/action","display_name":"Action (physics)","score":0.6064355969429016},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.566505491733551},{"id":"https://openalex.org/keywords/space","display_name":"Space (punctuation)","score":0.5482419729232788},{"id":"https://openalex.org/keywords/function","display_name":"Function (biology)","score":0.5259835124015808},{"id":"https://openalex.org/keywords/field","display_name":"Field (mathematics)","score":0.4856913983821869},{"id":"https://openalex.org/keywords/function-approximation","display_name":"Function approximation","score":0.48414546251296997},{"id":"https://openalex.org/keywords/reinforcement","display_name":"Reinforcement","score":0.44264519214630127},{"id":"https://openalex.org/keywords/robot","display_name":"Robot","score":0.43935689330101013},{"id":"https://openalex.org/keywords/robotics","display_name":"Robotics","score":0.4274235665798187},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.3756293058395386},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.25800347328186035},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.2562964856624603},{"id":"https://openalex.org/keywords/psychology","display_name":"Psychology","score":0.09025838971138}],"concepts":[{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.8146553039550781},{"id":"https://openalex.org/C72434380","wikidata":"https://www.wikidata.org/wiki/Q230930","display_name":"State space","level":2,"score":0.6564268469810486},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6109107732772827},{"id":"https://openalex.org/C2780791683","wikidata":"https://www.wikidata.org/wiki/Q846785","display_name":"Action (physics)","level":2,"score":0.6064355969429016},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.566505491733551},{"id":"https://openalex.org/C2778572836","wikidata":"https://www.wikidata.org/wiki/Q380933","display_name":"Space (punctuation)","level":2,"score":0.5482419729232788},{"id":"https://openalex.org/C14036430","wikidata":"https://www.wikidata.org/wiki/Q3736076","display_name":"Function (biology)","level":2,"score":0.5259835124015808},{"id":"https://openalex.org/C9652623","wikidata":"https://www.wikidata.org/wiki/Q190109","display_name":"Field (mathematics)","level":2,"score":0.4856913983821869},{"id":"https://openalex.org/C91873725","wikidata":"https://www.wikidata.org/wiki/Q3445816","display_name":"Function approximation","level":3,"score":0.48414546251296997},{"id":"https://openalex.org/C67203356","wikidata":"https://www.wikidata.org/wiki/Q1321905","display_name":"Reinforcement","level":2,"score":0.44264519214630127},{"id":"https://openalex.org/C90509273","wikidata":"https://www.wikidata.org/wiki/Q11012","display_name":"Robot","level":2,"score":0.43935689330101013},{"id":"https://openalex.org/C34413123","wikidata":"https://www.wikidata.org/wiki/Q170978","display_name":"Robotics","level":3,"score":0.4274235665798187},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.3756293058395386},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.25800347328186035},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.2562964856624603},{"id":"https://openalex.org/C15744967","wikidata":"https://www.wikidata.org/wiki/Q9418","display_name":"Psychology","level":0,"score":0.09025838971138},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"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/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.0},{"id":"https://openalex.org/C78458016","wikidata":"https://www.wikidata.org/wiki/Q840400","display_name":"Evolutionary biology","level":1,"score":0.0},{"id":"https://openalex.org/C62520636","wikidata":"https://www.wikidata.org/wiki/Q944","display_name":"Quantum mechanics","level":1,"score":0.0},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.0},{"id":"https://openalex.org/C202444582","wikidata":"https://www.wikidata.org/wiki/Q837863","display_name":"Pure mathematics","level":1,"score":0.0},{"id":"https://openalex.org/C77805123","wikidata":"https://www.wikidata.org/wiki/Q161272","display_name":"Social psychology","level":1,"score":0.0}],"mesh":[{"descriptor_ui":"D004867","descriptor_name":"Equipment Design","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D004867","descriptor_name":"Equipment Design","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D004867","descriptor_name":"Equipment Design","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D007858","descriptor_name":"Learning","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D007858","descriptor_name":"Learning","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D007858","descriptor_name":"Learning","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D012371","descriptor_name":"Robotics","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D012371","descriptor_name":"Robotics","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D012371","descriptor_name":"Robotics","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false}],"locations_count":6,"locations":[{"id":"doi:10.1007/s00422-009-0295-8","is_oa":true,"landing_page_url":"https://doi.org/10.1007/s00422-009-0295-8","pdf_url":"https://link.springer.com/content/pdf/10.1007/s00422-009-0295-8.pdf","source":{"id":"https://openalex.org/S87357125","display_name":"Biological Cybernetics","issn_l":"0340-1200","issn":["0340-1200","1432-0770"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319900","host_organization_name":"Springer Science+Business Media","host_organization_lineage":["https://openalex.org/P4310319900","https://openalex.org/P4310319965"],"host_organization_lineage_names":["Springer Science+Business Media","Springer Nature"],"type":"journal"},"license":"cc-by-nc","license_id":"https://openalex.org/licenses/cc-by-nc","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Biological Cybernetics","raw_type":"journal-article"},{"id":"pmid:19229556","is_oa":false,"landing_page_url":"https://pubmed.ncbi.nlm.nih.gov/19229556","pdf_url":null,"source":{"id":"https://openalex.org/S4306525036","display_name":"PubMed","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I1299303238","host_organization_name":"National Institutes of Health","host_organization_lineage":["https://openalex.org/I1299303238"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Biological cybernetics","raw_type":null},{"id":"pmh:oai:goescholar:1/3528","is_oa":true,"landing_page_url":"http://resolver.sub.uni-goettingen.de/purl?goescholar/3528","pdf_url":null,"source":{"id":"https://openalex.org/S4306401634","display_name":"GoeScholar  The Publication Server of the Georg-August-Universit\u00e4t G\u00f6ttingen (Georg-August-Universit\u00e4t G\u00f6ttingen)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I4210122495","host_organization_name":"Asklepios Klinik St. Georg","host_organization_lineage":["https://openalex.org/I4210122495"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"journalArticle"},{"id":"pmh:oai:publications.goettingen-research-online.de:2/17214","is_oa":true,"landing_page_url":"https://resolver.sub.uni-goettingen.de/purl?goescholar/3528","pdf_url":null,"source":{"id":"https://openalex.org/S4306401634","display_name":"GoeScholar  The Publication Server of the Georg-August-Universit\u00e4t G\u00f6ttingen (Georg-August-Universit\u00e4t G\u00f6ttingen)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I4210122495","host_organization_name":"Asklepios Klinik St. Georg","host_organization_lineage":["https://openalex.org/I4210122495"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"journal_article"},{"id":"pmh:oai:pubmedcentral.nih.gov:2798030","is_oa":true,"landing_page_url":"https://www.ncbi.nlm.nih.gov/pmc/articles/2798030","pdf_url":null,"source":{"id":"https://openalex.org/S2764455111","display_name":"PubMed Central","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I1299303238","host_organization_name":"National Institutes of Health","host_organization_lineage":["https://openalex.org/I1299303238"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Biol Cybern","raw_type":"Text"},{"id":"pmh:oai:vdu.lt:20.500.12259/54371","is_oa":false,"landing_page_url":"https://hdl.handle.net/20.500.12259/54371","pdf_url":null,"source":{"id":"https://openalex.org/S7407055361","display_name":"Vytautas Magnus University","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":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"research article"}],"best_oa_location":{"id":"doi:10.1007/s00422-009-0295-8","is_oa":true,"landing_page_url":"https://doi.org/10.1007/s00422-009-0295-8","pdf_url":"https://link.springer.com/content/pdf/10.1007/s00422-009-0295-8.pdf","source":{"id":"https://openalex.org/S87357125","display_name":"Biological Cybernetics","issn_l":"0340-1200","issn":["0340-1200","1432-0770"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319900","host_organization_name":"Springer Science+Business Media","host_organization_lineage":["https://openalex.org/P4310319900","https://openalex.org/P4310319965"],"host_organization_lineage_names":["Springer Science+Business Media","Springer Nature"],"type":"journal"},"license":"cc-by-nc","license_id":"https://openalex.org/licenses/cc-by-nc","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Biological Cybernetics","raw_type":"journal-article"},"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/16","score":0.7400000095367432,"display_name":"Peace, Justice and strong institutions"}],"awards":[],"funders":[{"id":"https://openalex.org/F4320320300","display_name":"European Commission","ror":"https://ror.org/00k4n6c32"}],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W2121294372.pdf","grobid_xml":"https://content.openalex.org/works/W2121294372.grobid-xml"},"referenced_works_count":62,"referenced_works":["https://openalex.org/W1443478967","https://openalex.org/W1539439741","https://openalex.org/W1557517019","https://openalex.org/W1570020663","https://openalex.org/W1588149505","https://openalex.org/W1595146801","https://openalex.org/W1820996291","https://openalex.org/W1834928574","https://openalex.org/W1851410152","https://openalex.org/W1857080389","https://openalex.org/W1866328951","https://openalex.org/W1872794911","https://openalex.org/W1889541222","https://openalex.org/W1958088497","https://openalex.org/W1967097499","https://openalex.org/W2001584605","https://openalex.org/W2028160701","https://openalex.org/W2033771479","https://openalex.org/W2082991751","https://openalex.org/W2096969611","https://openalex.org/W2100677568","https://openalex.org/W2101539915","https://openalex.org/W2107977784","https://openalex.org/W2109158177","https://openalex.org/W2110771465","https://openalex.org/W2111691855","https://openalex.org/W2112542282","https://openalex.org/W2112783345","https://openalex.org/W2115921331","https://openalex.org/W2119717200","https://openalex.org/W2120982017","https://openalex.org/W2121863487","https://openalex.org/W2122879428","https://openalex.org/W2123727571","https://openalex.org/W2123955331","https://openalex.org/W2124758444","https://openalex.org/W2125612430","https://openalex.org/W2126137955","https://openalex.org/W2127107099","https://openalex.org/W2128103053","https://openalex.org/W2128477394","https://openalex.org/W2131600418","https://openalex.org/W2135396350","https://openalex.org/W2136621137","https://openalex.org/W2137466452","https://openalex.org/W2141763580","https://openalex.org/W2146922385","https://openalex.org/W2155027007","https://openalex.org/W2158559683","https://openalex.org/W2159642572","https://openalex.org/W2160863137","https://openalex.org/W2161505441","https://openalex.org/W2162138792","https://openalex.org/W2163555676","https://openalex.org/W2167501464","https://openalex.org/W2307448102","https://openalex.org/W2540104143","https://openalex.org/W2787259794","https://openalex.org/W3011120880","https://openalex.org/W4214717370","https://openalex.org/W4247206283","https://openalex.org/W4248304976"],"related_works":["https://openalex.org/W4310083477","https://openalex.org/W4225571923","https://openalex.org/W3212257828","https://openalex.org/W2999580272","https://openalex.org/W4297873223","https://openalex.org/W3009457412","https://openalex.org/W2350784623","https://openalex.org/W2126211886","https://openalex.org/W3021988786","https://openalex.org/W3099311996"],"abstract_inverted_index":{"Reinforcement":[0],"learning":[1,55,206],"methods":[2],"can":[3,197],"be":[4,35,183,198,208],"used":[5],"in":[6,59,81,175,200],"robotics":[7],"applications":[8],"especially":[9],"for":[10,14,64,121,192],"specific":[11],"target-oriented":[12],"problems,":[13],"example":[15],"the":[16,69,105,149,157],"reward-based":[17],"recalibration":[18],"of":[19,40,71,111,115,141,146,171,205],"goal":[20,39],"directed":[21],"actions.":[22],"To":[23],"this":[24,41,176],"end":[25],"still":[26],"relatively":[27],"large":[28,144],"and":[29,104,148],"continuous":[30,134,150],"state-action":[31,106],"spaces":[32],"need":[33],"to":[34,45,159,185],"efficiently":[36],"handled.":[37],"The":[38,169],"paper":[42],"is,":[43],"thus,":[44],"develop":[46],"a":[47,76,85,142,161,189],"novel,":[48],"rather":[49,143],"simple":[50],"method":[51,173],"which":[52],"uses":[53],"reinforcement":[54],"with":[56,61,90],"function":[57],"approximation":[58,95],"conjunction":[60],"different":[62],"reward-strategies":[63],"solving":[65],"such":[66],"problems.":[67],"For":[68],"testing":[70],"our":[72,172],"method,":[73],"we":[74],"use":[75,186],"four":[77],"degree-of-freedom":[78],"reaching":[79],"problem":[80],"3D-space":[82],"simulated":[83],"by":[84],"two-joint":[86],"robot":[87,191],"arm":[88],"system":[89,158],"two":[91],"DOF":[92],"each.":[93],"Function":[94],"is":[96,137],"based":[97],"on":[98,188],"4D,":[99],"overlapping":[100],"kernels":[101],"(receptive":[102],"fields)":[103],"space":[107,136,152],"contains":[108],"about":[109,166],"10,000":[110],"these.":[112],"Different":[113],"types":[114,204],"reward":[116],"structures":[117],"are":[118,131],"being":[119],"compared,":[120],"example,":[122],"reward-on-":[123],"touching-only":[124],"against":[125],"reward-on-approach.":[126],"Furthermore,":[127],"forbidden":[128],"joint":[129],"configurations":[130],"punished.":[132],"A":[133],"action":[135,151],"used.":[138],"In":[139],"spite":[140],"number":[145],"states":[147],"these":[153],"reward/punishment":[154],"strategies":[155],"allow":[156],"find":[160],"good":[162],"solution":[163],"usually":[164],"within":[165],"20":[167],"trials.":[168],"efficiency":[170],"demonstrated":[174],"test":[177],"scenario":[178],"suggests":[179],"that":[180],"it":[181,187],"might":[182,207],"possible":[184],"real":[190],"problems":[193],"where":[194,202],"mixed":[195],"rewards":[196],"defined":[199],"situations":[201],"other":[203],"difficult.":[209]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2023,"cited_by_count":1},{"year":2020,"cited_by_count":1},{"year":2017,"cited_by_count":3},{"year":2015,"cited_by_count":1},{"year":2012,"cited_by_count":2}],"updated_date":"2026-07-23T08:03:31.855105","created_date":"2025-10-10T00:00:00"}