{"id":"https://openalex.org/W2063190773","doi":"https://doi.org/10.1007/s10015-012-0058-9","title":"Reinforcement learning approach to multi-stage decision making problems with changes in action sets","display_name":"Reinforcement learning approach to multi-stage decision making problems with changes in action sets","publication_year":2012,"publication_date":"2012-11-05","ids":{"openalex":"https://openalex.org/W2063190773","doi":"https://doi.org/10.1007/s10015-012-0058-9","mag":"2063190773"},"language":"en","primary_location":{"id":"doi:10.1007/s10015-012-0058-9","is_oa":false,"landing_page_url":"https://doi.org/10.1007/s10015-012-0058-9","pdf_url":null,"source":{"id":"https://openalex.org/S104439334","display_name":"Artificial Life and Robotics","issn_l":"1433-5298","issn":["1433-5298","1614-7456"],"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":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Artificial Life and Robotics","raw_type":"journal-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/A5043096200","display_name":"Takuya Etoh","orcid":null},"institutions":[{"id":"https://openalex.org/I135598925","display_name":"Kyushu University","ror":"https://ror.org/00p4k0j84","country_code":"JP","type":"education","lineage":["https://openalex.org/I135598925"]}],"countries":["JP"],"is_corresponding":true,"raw_author_name":"Takuya Etoh","raw_affiliation_strings":["Kyushu University, 744 Motooka, Nishi-ku, Fukuoka, Japan","Kyushu University, Nishi-ku, Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Kyushu University, 744 Motooka, Nishi-ku, Fukuoka, Japan","institution_ids":["https://openalex.org/I135598925"]},{"raw_affiliation_string":"Kyushu University, Nishi-ku, Japan","institution_ids":["https://openalex.org/I135598925"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5112212112","display_name":"Hirotaka Takano","orcid":null},"institutions":[{"id":"https://openalex.org/I135598925","display_name":"Kyushu University","ror":"https://ror.org/00p4k0j84","country_code":"JP","type":"education","lineage":["https://openalex.org/I135598925"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Hirotaka Takano","raw_affiliation_strings":["Kyushu University, 744 Motooka, Nishi-ku, Fukuoka, Japan","Kyushu University, Nishi-ku, Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Kyushu University, 744 Motooka, Nishi-ku, Fukuoka, Japan","institution_ids":["https://openalex.org/I135598925"]},{"raw_affiliation_string":"Kyushu University, Nishi-ku, Japan","institution_ids":["https://openalex.org/I135598925"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5085520273","display_name":"Junichi Murata","orcid":null},"institutions":[{"id":"https://openalex.org/I135598925","display_name":"Kyushu University","ror":"https://ror.org/00p4k0j84","country_code":"JP","type":"education","lineage":["https://openalex.org/I135598925"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Junichi Murata","raw_affiliation_strings":["Kyushu University, 744 Motooka, Nishi-ku, Fukuoka, Japan","Kyushu University, Nishi-ku, Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Kyushu University, 744 Motooka, Nishi-ku, Fukuoka, Japan","institution_ids":["https://openalex.org/I135598925"]},{"raw_affiliation_string":"Kyushu University, Nishi-ku, Japan","institution_ids":["https://openalex.org/I135598925"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":["https://openalex.org/A5043096200"],"corresponding_institution_ids":["https://openalex.org/I135598925"],"apc_list":{"value":2990,"currency":"USD","value_usd":2990},"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.11853817,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":"17","issue":"2","first_page":"293","last_page":"299"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T12794","display_name":"Adaptive Dynamic Programming Control","score":0.9979000091552734,"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"}},"topics":[{"id":"https://openalex.org/T12794","display_name":"Adaptive Dynamic Programming Control","score":0.9979000091552734,"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/T10462","display_name":"Reinforcement Learning in Robotics","score":0.9733999967575073,"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/T14083","display_name":"Extremum Seeking Control Systems","score":0.9575999975204468,"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":0.8383603096008301},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7668718099594116},{"id":"https://openalex.org/keywords/action","display_name":"Action (physics)","score":0.6567068696022034},{"id":"https://openalex.org/keywords/action-selection","display_name":"Action selection","score":0.6379233598709106},{"id":"https://openalex.org/keywords/selection","display_name":"Selection (genetic algorithm)","score":0.5977213978767395},{"id":"https://openalex.org/keywords/shortest-path-problem","display_name":"Shortest path problem","score":0.561516523361206},{"id":"https://openalex.org/keywords/reinforcement","display_name":"Reinforcement","score":0.546369194984436},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.48542889952659607},{"id":"https://openalex.org/keywords/decision-problem","display_name":"Decision problem","score":0.46038225293159485},{"id":"https://openalex.org/keywords/mathematical-optimization","display_name":"Mathematical optimization","score":0.41308680176734924},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.38953477144241333},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.15328606963157654},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.1352214515209198},{"id":"https://openalex.org/keywords/graph","display_name":"Graph","score":0.10325035452842712}],"concepts":[{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.8383603096008301},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7668718099594116},{"id":"https://openalex.org/C2780791683","wikidata":"https://www.wikidata.org/wiki/Q846785","display_name":"Action (physics)","level":2,"score":0.6567068696022034},{"id":"https://openalex.org/C166109690","wikidata":"https://www.wikidata.org/wiki/Q4677422","display_name":"Action selection","level":3,"score":0.6379233598709106},{"id":"https://openalex.org/C81917197","wikidata":"https://www.wikidata.org/wiki/Q628760","display_name":"Selection (genetic algorithm)","level":2,"score":0.5977213978767395},{"id":"https://openalex.org/C22590252","wikidata":"https://www.wikidata.org/wiki/Q1058754","display_name":"Shortest path problem","level":3,"score":0.561516523361206},{"id":"https://openalex.org/C67203356","wikidata":"https://www.wikidata.org/wiki/Q1321905","display_name":"Reinforcement","level":2,"score":0.546369194984436},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.48542889952659607},{"id":"https://openalex.org/C115988155","wikidata":"https://www.wikidata.org/wiki/Q3262192","display_name":"Decision problem","level":2,"score":0.46038225293159485},{"id":"https://openalex.org/C126255220","wikidata":"https://www.wikidata.org/wiki/Q141495","display_name":"Mathematical optimization","level":1,"score":0.41308680176734924},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.38953477144241333},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.15328606963157654},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.1352214515209198},{"id":"https://openalex.org/C132525143","wikidata":"https://www.wikidata.org/wiki/Q141488","display_name":"Graph","level":2,"score":0.10325035452842712},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","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},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0},{"id":"https://openalex.org/C80444323","wikidata":"https://www.wikidata.org/wiki/Q2878974","display_name":"Theoretical computer science","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},{"id":"https://openalex.org/C26760741","wikidata":"https://www.wikidata.org/wiki/Q160402","display_name":"Perception","level":2,"score":0.0},{"id":"https://openalex.org/C15744967","wikidata":"https://www.wikidata.org/wiki/Q9418","display_name":"Psychology","level":0,"score":0.0},{"id":"https://openalex.org/C169760540","wikidata":"https://www.wikidata.org/wiki/Q207011","display_name":"Neuroscience","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1007/s10015-012-0058-9","is_oa":false,"landing_page_url":"https://doi.org/10.1007/s10015-012-0058-9","pdf_url":null,"source":{"id":"https://openalex.org/S104439334","display_name":"Artificial Life and Robotics","issn_l":"1433-5298","issn":["1433-5298","1614-7456"],"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":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Artificial Life and Robotics","raw_type":"journal-article"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.7699999809265137,"display_name":"Peace, Justice and strong institutions","id":"https://metadata.un.org/sdg/16"}],"awards":[{"id":"https://openalex.org/G5905595317","display_name":"Solution of multistage decision problems considering subjectively evaluated risks of changes in problems","funder_award_id":"24560499","funder_id":"https://openalex.org/F4320334764","funder_display_name":"Japan Society for the Promotion of Science"}],"funders":[{"id":"https://openalex.org/F4320334764","display_name":"Japan Society for the Promotion of Science","ror":"https://ror.org/00hhkn466"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":21,"referenced_works":["https://openalex.org/W1515851193","https://openalex.org/W1558348055","https://openalex.org/W1592847719","https://openalex.org/W1854776945","https://openalex.org/W2028145673","https://openalex.org/W2048138718","https://openalex.org/W2050838777","https://openalex.org/W2098432798","https://openalex.org/W2101075098","https://openalex.org/W2133469585","https://openalex.org/W2147704565","https://openalex.org/W2161903956","https://openalex.org/W2171715801","https://openalex.org/W2546233656","https://openalex.org/W2911633892","https://openalex.org/W3011865677","https://openalex.org/W3106238320","https://openalex.org/W3123552065","https://openalex.org/W3159971645","https://openalex.org/W4214717370","https://openalex.org/W4292158025"],"related_works":["https://openalex.org/W2920061524","https://openalex.org/W4310083477","https://openalex.org/W2015051472","https://openalex.org/W2168501056","https://openalex.org/W1965695708","https://openalex.org/W2120009678","https://openalex.org/W2912947802","https://openalex.org/W2037601570","https://openalex.org/W2123856982","https://openalex.org/W1530089576"],"abstract_inverted_index":null,"counts_by_year":[],"updated_date":"2026-07-23T08:03:31.855105","created_date":"2025-10-10T00:00:00"}