{"id":"https://openalex.org/W2116903157","doi":"https://doi.org/10.1109/roman.2009.5326234","title":"Constructing continuous action space from basis functions for fast and stable reinforcement learning","display_name":"Constructing continuous action space from basis functions for fast and stable reinforcement learning","publication_year":2009,"publication_date":"2009-09-01","ids":{"openalex":"https://openalex.org/W2116903157","doi":"https://doi.org/10.1109/roman.2009.5326234","mag":"2116903157"},"language":"en","primary_location":{"id":"doi:10.1109/roman.2009.5326234","is_oa":false,"landing_page_url":"https://doi.org/10.1109/roman.2009.5326234","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"RO-MAN 2009 - The 18th IEEE International Symposium on Robot and Human Interactive Communication","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/A5020600038","display_name":"Akihiko Yamaguchi","orcid":"https://orcid.org/0000-0001-9060-3478"},"institutions":[{"id":"https://openalex.org/I75917431","display_name":"Nara Institute of Science and Technology","ror":"https://ror.org/05bhada84","country_code":"JP","type":"education","lineage":["https://openalex.org/I75917431"]}],"countries":["JP"],"is_corresponding":true,"raw_author_name":"Akihiko Yamaguchi","raw_affiliation_strings":["Graduate School of Information Science, Nara Institute of Science and Technology, Ikoma, Nara, Japan","Graduate School of Information Science, Nara Institute of Science and Technology, 8916-5 Takayama, Ikoma, 630-0192 Japan"],"affiliations":[{"raw_affiliation_string":"Graduate School of Information Science, Nara Institute of Science and Technology, Ikoma, Nara, Japan","institution_ids":["https://openalex.org/I75917431"]},{"raw_affiliation_string":"Graduate School of Information Science, Nara Institute of Science and Technology, 8916-5 Takayama, Ikoma, 630-0192 Japan","institution_ids":["https://openalex.org/I75917431"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5047085140","display_name":"Jun Takamatsu","orcid":"https://orcid.org/0000-0001-7457-2878"},"institutions":[{"id":"https://openalex.org/I75917431","display_name":"Nara Institute of Science and Technology","ror":"https://ror.org/05bhada84","country_code":"JP","type":"education","lineage":["https://openalex.org/I75917431"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Jun Takamatsu","raw_affiliation_strings":["Graduate School of Information Science, Nara Institute of Science and Technology, Ikoma, Nara, Japan","Graduate School of Information Science, Nara Institute of Science and Technology, 8916-5 Takayama, Ikoma, 630-0192 Japan"],"affiliations":[{"raw_affiliation_string":"Graduate School of Information Science, Nara Institute of Science and Technology, Ikoma, Nara, Japan","institution_ids":["https://openalex.org/I75917431"]},{"raw_affiliation_string":"Graduate School of Information Science, Nara Institute of Science and Technology, 8916-5 Takayama, Ikoma, 630-0192 Japan","institution_ids":["https://openalex.org/I75917431"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5044340470","display_name":"Tsukasa Ogasawara","orcid":"https://orcid.org/0000-0001-9767-6039"},"institutions":[{"id":"https://openalex.org/I75917431","display_name":"Nara Institute of Science and Technology","ror":"https://ror.org/05bhada84","country_code":"JP","type":"education","lineage":["https://openalex.org/I75917431"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Tsukasa Ogasawara","raw_affiliation_strings":["Graduate School of Information Science, Nara Institute of Science and Technology, Ikoma, Nara, Japan","Graduate School of Information Science, Nara Institute of Science and Technology, 8916-5 Takayama, Ikoma, 630-0192 Japan"],"affiliations":[{"raw_affiliation_string":"Graduate School of Information Science, Nara Institute of Science and Technology, Ikoma, Nara, Japan","institution_ids":["https://openalex.org/I75917431"]},{"raw_affiliation_string":"Graduate School of Information Science, Nara Institute of Science and Technology, 8916-5 Takayama, Ikoma, 630-0192 Japan","institution_ids":["https://openalex.org/I75917431"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5020600038"],"corresponding_institution_ids":["https://openalex.org/I75917431"],"apc_list":null,"apc_paid":null,"fwci":0.9033,"has_fulltext":false,"cited_by_count":2,"citation_normalized_percentile":{"value":0.81284439,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":"25","issue":null,"first_page":"401","last_page":"407"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11975","display_name":"Evolutionary Algorithms and Applications","score":0.9876999855041504,"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/T11975","display_name":"Evolutionary Algorithms and Applications","score":0.9876999855041504,"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/T10462","display_name":"Reinforcement Learning in Robotics","score":0.9745000004768372,"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/T11663","display_name":"Viral Infectious Diseases and Gene Expression in Insects","score":0.9713000059127808,"subfield":{"id":"https://openalex.org/subfields/1312","display_name":"Molecular Biology"},"field":{"id":"https://openalex.org/fields/13","display_name":"Biochemistry, Genetics and Molecular Biology"},"domain":{"id":"https://openalex.org/domains/1","display_name":"Life Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/reinforcement-learning","display_name":"Reinforcement learning","score":0.7655283212661743},{"id":"https://openalex.org/keywords/action","display_name":"Action (physics)","score":0.717327356338501},{"id":"https://openalex.org/keywords/stability","display_name":"Stability (learning theory)","score":0.6972164511680603},{"id":"https://openalex.org/keywords/basis","display_name":"Basis (linear algebra)","score":0.6740089654922485},{"id":"https://openalex.org/keywords/basis-function","display_name":"Basis function","score":0.6105659008026123},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.610549807548523},{"id":"https://openalex.org/keywords/set","display_name":"Set (abstract data type)","score":0.5794464349746704},{"id":"https://openalex.org/keywords/space","display_name":"Space (punctuation)","score":0.5715895891189575},{"id":"https://openalex.org/keywords/function","display_name":"Function (biology)","score":0.5548007488250732},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.4941454231739044},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4443841576576233},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.3342772126197815},{"id":"https://openalex.org/keywords/mathematical-optimization","display_name":"Mathematical optimization","score":0.3311765789985657},{"id":"https://openalex.org/keywords/control-theory","display_name":"Control theory (sociology)","score":0.3284072279930115},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.14771154522895813},{"id":"https://openalex.org/keywords/mathematical-analysis","display_name":"Mathematical analysis","score":0.14609092473983765},{"id":"https://openalex.org/keywords/geometry","display_name":"Geometry","score":0.10780352354049683},{"id":"https://openalex.org/keywords/control","display_name":"Control (management)","score":0.10733446478843689}],"concepts":[{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.7655283212661743},{"id":"https://openalex.org/C2780791683","wikidata":"https://www.wikidata.org/wiki/Q846785","display_name":"Action (physics)","level":2,"score":0.717327356338501},{"id":"https://openalex.org/C112972136","wikidata":"https://www.wikidata.org/wiki/Q7595718","display_name":"Stability (learning theory)","level":2,"score":0.6972164511680603},{"id":"https://openalex.org/C12426560","wikidata":"https://www.wikidata.org/wiki/Q189569","display_name":"Basis (linear algebra)","level":2,"score":0.6740089654922485},{"id":"https://openalex.org/C5917680","wikidata":"https://www.wikidata.org/wiki/Q2621825","display_name":"Basis function","level":2,"score":0.6105659008026123},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.610549807548523},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.5794464349746704},{"id":"https://openalex.org/C2778572836","wikidata":"https://www.wikidata.org/wiki/Q380933","display_name":"Space (punctuation)","level":2,"score":0.5715895891189575},{"id":"https://openalex.org/C14036430","wikidata":"https://www.wikidata.org/wiki/Q3736076","display_name":"Function (biology)","level":2,"score":0.5548007488250732},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.4941454231739044},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4443841576576233},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.3342772126197815},{"id":"https://openalex.org/C126255220","wikidata":"https://www.wikidata.org/wiki/Q141495","display_name":"Mathematical optimization","level":1,"score":0.3311765789985657},{"id":"https://openalex.org/C47446073","wikidata":"https://www.wikidata.org/wiki/Q5165890","display_name":"Control theory (sociology)","level":3,"score":0.3284072279930115},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.14771154522895813},{"id":"https://openalex.org/C134306372","wikidata":"https://www.wikidata.org/wiki/Q7754","display_name":"Mathematical analysis","level":1,"score":0.14609092473983765},{"id":"https://openalex.org/C2524010","wikidata":"https://www.wikidata.org/wiki/Q8087","display_name":"Geometry","level":1,"score":0.10780352354049683},{"id":"https://openalex.org/C2775924081","wikidata":"https://www.wikidata.org/wiki/Q55608371","display_name":"Control (management)","level":2,"score":0.10733446478843689},{"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/C78458016","wikidata":"https://www.wikidata.org/wiki/Q840400","display_name":"Evolutionary biology","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/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","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}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/roman.2009.5326234","is_oa":false,"landing_page_url":"https://doi.org/10.1109/roman.2009.5326234","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"RO-MAN 2009 - The 18th IEEE International Symposium on Robot and Human Interactive Communication","raw_type":"proceedings-article"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.663.7062","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.663.7062","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://robotics.aist-nara.ac.jp/%7Eakihiko-y/wdocs/YamaguchiOgasawara2009roman-Constructing_Continuous_Action_Space_from_Basis_Functions_for_Fast_and_Stable_Reinforcement_Learning-roman09-draft.pdf","raw_type":"text"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Peace, Justice and strong institutions","score":0.41999998688697815,"id":"https://metadata.un.org/sdg/16"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":29,"referenced_works":["https://openalex.org/W1531886263","https://openalex.org/W1543217731","https://openalex.org/W1594783240","https://openalex.org/W1751034982","https://openalex.org/W1966268398","https://openalex.org/W1984986877","https://openalex.org/W2045463255","https://openalex.org/W2090139585","https://openalex.org/W2110771465","https://openalex.org/W2113913482","https://openalex.org/W2115558966","https://openalex.org/W2119072456","https://openalex.org/W2121863487","https://openalex.org/W2123967136","https://openalex.org/W2139418546","https://openalex.org/W2162617871","https://openalex.org/W2181031009","https://openalex.org/W2518102996","https://openalex.org/W2535652371","https://openalex.org/W2545768840","https://openalex.org/W2610686804","https://openalex.org/W3011120880","https://openalex.org/W3139377883","https://openalex.org/W4214717370","https://openalex.org/W6635508374","https://openalex.org/W6676684363","https://openalex.org/W6678157427","https://openalex.org/W6729212690","https://openalex.org/W6775686901"],"related_works":["https://openalex.org/W2006953814","https://openalex.org/W2542637001","https://openalex.org/W1972782945","https://openalex.org/W3212981098","https://openalex.org/W4221090543","https://openalex.org/W2136751449","https://openalex.org/W2130622405","https://openalex.org/W2109887391","https://openalex.org/W1819996744","https://openalex.org/W2154858558"],"abstract_inverted_index":{"This":[0,139],"paper":[1,140],"presents":[2],"a":[3,18,101],"new":[4],"continuous":[5],"action":[6,25,58,73],"space":[7,59],"for":[8],"reinforcement":[9],"learning":[10],"(RL)":[11],"with":[12,24],"the":[13,32,39,44,50,54,63,71,83,90,106,113,117,120,123,127,131,137],"wire-fitting.":[14,118],"The":[15,56,108],"wire-fitting":[16,33],"has":[17],"desirable":[19],"feature":[20],"to":[21,89,94,104,136],"be":[22],"used":[23],"value":[26],"function":[27],"based":[28],"RL":[29],"algorithms.":[30],"However,":[31],"becomes":[34],"unstable":[35],"caused":[36],"by":[37,66],"changing":[38],"parameters":[40,91],"of":[41,53,126],"actions.":[42],"Furthermore,":[43,97],"acquired":[45],"behavior":[46],"highly":[47],"depend":[48],"on":[49,82],"initial":[51],"values":[52],"parameters.":[55,107],"proposed":[57,65,114,128],"is":[60,75,130],"expanded":[61],"from":[62,77],"DCOB,":[64,84],"Yamaguchi":[67],"et":[68],"al.,":[69],"where":[70],"discrete":[72],"set":[74],"generated":[76],"given":[78],"basis":[79],"functions.":[80],"Based":[81],"we":[85,98],"apply":[86],"some":[87],"constraints":[88],"in":[92],"order":[93],"obtain":[95],"stability.":[96],"also":[99,141],"describe":[100],"proper":[102],"way":[103],"initialize":[105],"simulation":[109],"results":[110],"demonstrate":[111],"that":[112],"method":[115,129],"outperforms":[116],"On":[119],"other":[121],"hand,":[122],"resulting":[124],"performance":[125],"same":[132],"as,":[133],"or":[134],"inferior":[135],"DCOB.":[138],"discuss":[142],"about":[143],"this":[144],"result.":[145]},"counts_by_year":[],"updated_date":"2026-04-05T17:49:38.594831","created_date":"2025-10-10T00:00:00"}