{"id":"https://openalex.org/W2149860990","doi":"https://doi.org/10.5591/978-1-57735-516-8/ijcai11-441","title":"Reinforcement learning to adjust robot movements to new situations","display_name":"Reinforcement learning to adjust robot movements to new situations","publication_year":2011,"publication_date":"2011-07-16","ids":{"openalex":"https://openalex.org/W2149860990","doi":"https://doi.org/10.5591/978-1-57735-516-8/ijcai11-441","mag":"2149860990"},"language":"en","primary_location":{"id":"pmh:oai:escidoc.org:escidoc:1788042","is_oa":true,"landing_page_url":"http://hdl.handle.net/11858/00-001M-0000-0013-BA64-3","pdf_url":"http://www.roboticsproceedings.org/rss06/p05.pdf","source":{"id":"https://openalex.org/S7407052962","display_name":"Max Planck Digital Library","issn_l":null,"issn":[],"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":"","raw_type":"info:eu-repo/semantics/conferenceObject"},"type":"article","indexed_in":[],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"http://www.roboticsproceedings.org/rss06/p05.pdf","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5035229829","display_name":"Jens Kober","orcid":"https://orcid.org/0000-0001-7257-5434"},"institutions":[],"countries":[],"is_corresponding":true,"raw_author_name":"Jens Kober","raw_affiliation_strings":["MPI T\u00fcbingen, Germany#TAB#"],"raw_orcid":"https://orcid.org/0000-0001-7257-5434","affiliations":[{"raw_affiliation_string":"MPI T\u00fcbingen, Germany#TAB#","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5018729334","display_name":"Erhan \u00d6ztop","orcid":"https://orcid.org/0000-0002-3051-6038"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Erhan \u00d6ztop","raw_affiliation_strings":["ATR, CMC, Japan#TAB#"],"raw_orcid":"https://orcid.org/0000-0002-3051-6038","affiliations":[{"raw_affiliation_string":"ATR, CMC, Japan#TAB#","institution_ids":[]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5071367253","display_name":"Jan Peters","orcid":"https://orcid.org/0000-0002-5266-8091"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Jan Peters","raw_affiliation_strings":["MPI T\u00fcbingen, Germany#TAB#"],"raw_orcid":"https://orcid.org/0000-0002-5266-8091","affiliations":[{"raw_affiliation_string":"MPI T\u00fcbingen, Germany#TAB#","institution_ids":[]}]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5035229829"],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":8.7697,"has_fulltext":true,"cited_by_count":90,"citation_normalized_percentile":{"value":0.97712409,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":90,"max":100},"biblio":{"volume":null,"issue":null,"first_page":"2650","last_page":"2655"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10462","display_name":"Reinforcement Learning in Robotics","score":0.9983999729156494,"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":0.9983999729156494,"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":0.9939000010490417,"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/T11975","display_name":"Evolutionary Algorithms and Applications","score":0.9846000075340271,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/reinforcement-learning","display_name":"Reinforcement learning","score":0.7911348342895508},{"id":"https://openalex.org/keywords/robot","display_name":"Robot","score":0.7472200393676758},{"id":"https://openalex.org/keywords/generalization","display_name":"Generalization","score":0.680790901184082},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6657420992851257},{"id":"https://openalex.org/keywords/throwing","display_name":"Throwing","score":0.6330530047416687},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5999009013175964},{"id":"https://openalex.org/keywords/representation","display_name":"Representation (politics)","score":0.5062826871871948},{"id":"https://openalex.org/keywords/movement","display_name":"Movement (music)","score":0.4822276532649994},{"id":"https://openalex.org/keywords/robot-learning","display_name":"Robot learning","score":0.46512389183044434},{"id":"https://openalex.org/keywords/motor-skill","display_name":"Motor skill","score":0.42499545216560364},{"id":"https://openalex.org/keywords/plan","display_name":"Plan (archaeology)","score":0.4181007444858551},{"id":"https://openalex.org/keywords/motor-learning","display_name":"Motor learning","score":0.41100096702575684},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.3444841504096985},{"id":"https://openalex.org/keywords/mobile-robot","display_name":"Mobile robot","score":0.24896955490112305},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.1451798677444458},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.14332333207130432},{"id":"https://openalex.org/keywords/psychology","display_name":"Psychology","score":0.09449693560600281}],"concepts":[{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.7911348342895508},{"id":"https://openalex.org/C90509273","wikidata":"https://www.wikidata.org/wiki/Q11012","display_name":"Robot","level":2,"score":0.7472200393676758},{"id":"https://openalex.org/C177148314","wikidata":"https://www.wikidata.org/wiki/Q170084","display_name":"Generalization","level":2,"score":0.680790901184082},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6657420992851257},{"id":"https://openalex.org/C207451115","wikidata":"https://www.wikidata.org/wiki/Q12898216","display_name":"Throwing","level":2,"score":0.6330530047416687},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5999009013175964},{"id":"https://openalex.org/C2776359362","wikidata":"https://www.wikidata.org/wiki/Q2145286","display_name":"Representation (politics)","level":3,"score":0.5062826871871948},{"id":"https://openalex.org/C2780226923","wikidata":"https://www.wikidata.org/wiki/Q929848","display_name":"Movement (music)","level":2,"score":0.4822276532649994},{"id":"https://openalex.org/C188888258","wikidata":"https://www.wikidata.org/wiki/Q7353390","display_name":"Robot learning","level":4,"score":0.46512389183044434},{"id":"https://openalex.org/C169976356","wikidata":"https://www.wikidata.org/wiki/Q13208902","display_name":"Motor skill","level":2,"score":0.42499545216560364},{"id":"https://openalex.org/C2776505523","wikidata":"https://www.wikidata.org/wiki/Q4785468","display_name":"Plan (archaeology)","level":2,"score":0.4181007444858551},{"id":"https://openalex.org/C107690735","wikidata":"https://www.wikidata.org/wiki/Q852461","display_name":"Motor learning","level":2,"score":0.41100096702575684},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.3444841504096985},{"id":"https://openalex.org/C19966478","wikidata":"https://www.wikidata.org/wiki/Q4810574","display_name":"Mobile robot","level":3,"score":0.24896955490112305},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.1451798677444458},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.14332333207130432},{"id":"https://openalex.org/C15744967","wikidata":"https://www.wikidata.org/wiki/Q9418","display_name":"Psychology","level":0,"score":0.09449693560600281},{"id":"https://openalex.org/C95457728","wikidata":"https://www.wikidata.org/wiki/Q309","display_name":"History","level":0,"score":0.0},{"id":"https://openalex.org/C17744445","wikidata":"https://www.wikidata.org/wiki/Q36442","display_name":"Political science","level":0,"score":0.0},{"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/C169760540","wikidata":"https://www.wikidata.org/wiki/Q207011","display_name":"Neuroscience","level":1,"score":0.0},{"id":"https://openalex.org/C78519656","wikidata":"https://www.wikidata.org/wiki/Q101333","display_name":"Mechanical engineering","level":1,"score":0.0},{"id":"https://openalex.org/C199539241","wikidata":"https://www.wikidata.org/wiki/Q7748","display_name":"Law","level":1,"score":0.0},{"id":"https://openalex.org/C166957645","wikidata":"https://www.wikidata.org/wiki/Q23498","display_name":"Archaeology","level":1,"score":0.0},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0},{"id":"https://openalex.org/C118552586","wikidata":"https://www.wikidata.org/wiki/Q7867","display_name":"Psychiatry","level":1,"score":0.0},{"id":"https://openalex.org/C107038049","wikidata":"https://www.wikidata.org/wiki/Q35986","display_name":"Aesthetics","level":1,"score":0.0},{"id":"https://openalex.org/C94625758","wikidata":"https://www.wikidata.org/wiki/Q7163","display_name":"Politics","level":2,"score":0.0}],"mesh":[],"locations_count":13,"locations":[{"id":"pmh:oai:escidoc.org:escidoc:1788042","is_oa":true,"landing_page_url":"http://hdl.handle.net/11858/00-001M-0000-0013-BA64-3","pdf_url":"http://www.roboticsproceedings.org/rss06/p05.pdf","source":{"id":"https://openalex.org/S7407052962","display_name":"Max Planck Digital Library","issn_l":null,"issn":[],"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":"","raw_type":"info:eu-repo/semantics/conferenceObject"},{"id":"pmh:oai:pure.mpg.de:item_1788042","is_oa":true,"landing_page_url":"https://hdl.handle.net/11858/00-001M-0000-0013-BA64-3","pdf_url":"http://hdl.handle.net/11858/00-001M-0000-0013-BA64-3","source":{"id":"https://openalex.org/S4306400654","display_name":"MPG.PuRe (Max Planck Society)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I149899117","host_organization_name":"Max Planck Society","host_organization_lineage":["https://openalex.org/I149899117"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Robotics: Science and Systems VI","raw_type":"info:eu-repo/semantics/conferenceObject"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.165.8302","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.165.8302","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://www.roboticsproceedings.org/rss06/p05.pdf","raw_type":"text"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.423.140","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.423.140","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://roboticsproceedings.org/rss06/p05.pdf","raw_type":"text"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.698.4793","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.698.4793","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://www.ausy.informatik.tu-darmstadt.de/publications/Kober_IJCAI_2011.pdf","raw_type":"text"},{"id":"pmh:oai:edoc.mpg.de:548311","is_oa":false,"landing_page_url":"http://edoc.mpg.de/548311","pdf_url":null,"source":{"id":"https://openalex.org/S4406922265","display_name":"Max Planck Institute for Plasma Physics","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":"Robotics: Science and Systems VI, 1-8 (2010)","raw_type":"Conference-Paper"},{"id":"pmh:oai:edoc.mpg.de:596570","is_oa":false,"landing_page_url":"http://edoc.mpg.de/596570","pdf_url":null,"source":{"id":"https://openalex.org/S4406922265","display_name":"Max Planck Institute for Plasma Physics","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":"2010 Robotics: Science and Systems Conference (RSS 2010), 33-40 (2011)","raw_type":"Conference-Paper"},{"id":"pmh:oai:edoc.mpg.de:596820","is_oa":false,"landing_page_url":"http://edoc.mpg.de/596820","pdf_url":null,"source":{"id":"https://openalex.org/S4406922265","display_name":"Max Planck Institute for Plasma Physics","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":"Twenty-Second International Joint Conference on Artificial Intelligence (IJCAI 2011), 2650-2655 (2011)","raw_type":"Conference-Paper"},{"id":"pmh:oai:escidoc.org:escidoc:1788142","is_oa":false,"landing_page_url":"http://hdl.handle.net/11858/00-001M-0000-0013-BB2C-A","pdf_url":null,"source":{"id":"https://openalex.org/S7407052962","display_name":"Max Planck Digital Library","issn_l":null,"issn":[],"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":"","raw_type":"info:eu-repo/semantics/conferenceObject"},{"id":"pmh:oai:pure.mpg.de:item_1577472","is_oa":false,"landing_page_url":"http://hdl.handle.net/11858/00-001M-0000-0010-4C66-3","pdf_url":null,"source":{"id":"https://openalex.org/S4306400654","display_name":"MPG.PuRe (Max Planck Society)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I149899117","host_organization_name":"Max Planck Society","host_organization_lineage":["https://openalex.org/I149899117"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"2010 Robotics: Science and Systems Conference (RSS 2010)","raw_type":"info:eu-repo/semantics/conferenceObject"},{"id":"pmh:oai:pure.mpg.de:item_1577506","is_oa":false,"landing_page_url":"http://hdl.handle.net/11858/00-001M-0000-0010-4CA9-D","pdf_url":null,"source":{"id":"https://openalex.org/S4306400654","display_name":"MPG.PuRe (Max Planck Society)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I149899117","host_organization_name":"Max Planck Society","host_organization_lineage":["https://openalex.org/I149899117"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Twenty-Second International Joint Conference on Artificial Intelligence (IJCAI 2011)","raw_type":"info:eu-repo/semantics/conferenceObject"},{"id":"pmh:oai:pure.mpg.de:item_1788142","is_oa":false,"landing_page_url":"https://hdl.handle.net/11858/00-001M-0000-0013-BB2C-A","pdf_url":null,"source":{"id":"https://openalex.org/S4306400654","display_name":"MPG.PuRe (Max Planck Society)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I149899117","host_organization_name":"Max Planck Society","host_organization_lineage":["https://openalex.org/I149899117"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Twenty-Second International Joint Conference on Artificial Intelligence (IJCAI 2011)","raw_type":"info:eu-repo/semantics/conferenceObject"},{"id":"mag:2149860990","is_oa":false,"landing_page_url":"http://is.tuebingen.mpg.de/fileadmin/user_upload/files/publications/2011/IJCAL-2011-Kober.pdf","pdf_url":null,"source":{"id":"https://openalex.org/S4306419999","display_name":"International Joint Conference on Artificial Intelligence","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":null,"is_accepted":false,"is_published":null,"raw_source_name":"International Joint Conference on Artificial Intelligence","raw_type":null}],"best_oa_location":{"id":"pmh:oai:escidoc.org:escidoc:1788042","is_oa":true,"landing_page_url":"http://hdl.handle.net/11858/00-001M-0000-0013-BA64-3","pdf_url":"http://www.roboticsproceedings.org/rss06/p05.pdf","source":{"id":"https://openalex.org/S7407052962","display_name":"Max Planck Digital Library","issn_l":null,"issn":[],"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":"","raw_type":"info:eu-repo/semantics/conferenceObject"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W2149860990.pdf","grobid_xml":"https://content.openalex.org/works/W2149860990.grobid-xml"},"referenced_works_count":25,"referenced_works":["https://openalex.org/W1516801383","https://openalex.org/W1530191702","https://openalex.org/W1592847719","https://openalex.org/W1663973292","https://openalex.org/W1746819321","https://openalex.org/W1965218672","https://openalex.org/W2004382882","https://openalex.org/W2012392077","https://openalex.org/W2080039641","https://openalex.org/W2095676919","https://openalex.org/W2109169869","https://openalex.org/W2111597213","https://openalex.org/W2119717200","https://openalex.org/W2123967136","https://openalex.org/W2127107099","https://openalex.org/W2141853154","https://openalex.org/W2143435603","https://openalex.org/W2144576818","https://openalex.org/W2149192758","https://openalex.org/W2155307968","https://openalex.org/W2156974606","https://openalex.org/W2161598696","https://openalex.org/W2343637401","https://openalex.org/W2591436094","https://openalex.org/W2913340405"],"related_works":["https://openalex.org/W2161395589","https://openalex.org/W1499669280","https://openalex.org/W2964161785","https://openalex.org/W2136719407","https://openalex.org/W2121863487","https://openalex.org/W2123967136","https://openalex.org/W2116226448","https://openalex.org/W1986014385","https://openalex.org/W1977655452","https://openalex.org/W2140135625","https://openalex.org/W2016765487","https://openalex.org/W2591436094","https://openalex.org/W2128677288","https://openalex.org/W2012587148","https://openalex.org/W2012204020","https://openalex.org/W1982803779","https://openalex.org/W2140801763","https://openalex.org/W2012392077","https://openalex.org/W1746819321","https://openalex.org/W2110304639"],"abstract_inverted_index":{"Abstract\u2014Many":[0],"complex":[1],"robot":[2,30,128],"motor":[3,19,43],"skills":[4],"can":[5,154],"be":[6,155],"represented":[7],"using":[8,21,82,158],"elementary":[9,37,60],"movements,":[10],"and":[11,23,113,142,160],"there":[12],"exist":[13],"efficient":[14],"techniques":[15],"for":[16],"learning":[17,90],"parametrized":[18,42],"plans":[20],"demonstrations":[22],"self-improvement.":[24],"However,":[25],"in":[26,119,140,146],"many":[27],"cases,":[28],"the":[29,59,63,98,131,135],"currently":[31],"needs":[32],"to":[33,74,80,105,121],"learn":[34,75],"a":[35,41,48,53,94,110],"new":[36],"movement":[38,61],"even":[39],"if":[40],"plan":[44],"exists":[45],"that":[46,57,115,151],"covers":[47],"similar,":[49],"related":[50],"situation.":[51],"Clearly,":[52],"method":[54],"is":[55],"needed":[56],"modulates":[58],"through":[62],"meta-parameters":[64,81],"of":[65,97,130,137,143],"its":[66],"representation.":[67],"In":[68],"this":[69,103],"paper,":[70],"we":[71,125],"show":[72,114,126,150],"how":[73],"such":[76],"mappings":[77],"from":[78],"circumstances":[79],"reinforcement":[83,89],"learning.":[84],"We":[85,101,149],"introduce":[86],"an":[87],"appropriate":[88],"algorithm":[91,104],"based":[92],"on":[93,109],"kernelized":[95],"version":[96],"reward-weighted":[99],"regression.":[100],"compare":[102],"several":[106],"previous":[107],"methods":[108],"toy":[111],"example":[112],"it":[116],"performs":[117],"well":[118],"comparison":[120],"standard":[122],"algorithms.":[123],"Subsequently,":[124],"two":[127],"applications":[129],"presented":[132],"setup;":[133],"i.e.,":[134],"generalization":[136],"throwing":[138],"movements":[139,145],"darts,":[141],"hitting":[144],"table":[147],"tennis.":[148],"both":[152],"tasks":[153],"learned":[156],"successfully":[157],"simulated":[159],"real":[161],"robots.":[162],"I.":[163]},"counts_by_year":[{"year":2023,"cited_by_count":1},{"year":2022,"cited_by_count":3},{"year":2021,"cited_by_count":11},{"year":2020,"cited_by_count":9},{"year":2019,"cited_by_count":14},{"year":2018,"cited_by_count":6},{"year":2017,"cited_by_count":8},{"year":2016,"cited_by_count":11},{"year":2015,"cited_by_count":6},{"year":2014,"cited_by_count":5},{"year":2013,"cited_by_count":10},{"year":2012,"cited_by_count":3}],"updated_date":"2026-04-28T14:05:53.105641","created_date":"2025-10-10T00:00:00"}