{"id":"https://openalex.org/W75129147","doi":"https://doi.org/10.1007/978-3-540-87536-9_38","title":"Self-organized\u00a0Reinforcement\u00a0Learning Based\u00a0on\u00a0Policy\u00a0Gradient in\u00a0Nonstationary\u00a0Environments","display_name":"Self-organized\u00a0Reinforcement\u00a0Learning Based\u00a0on\u00a0Policy\u00a0Gradient in\u00a0Nonstationary\u00a0Environments","publication_year":2008,"publication_date":"2008-09-05","ids":{"openalex":"https://openalex.org/W75129147","doi":"https://doi.org/10.1007/978-3-540-87536-9_38","mag":"75129147"},"language":"en","primary_location":{"id":"doi:10.1007/978-3-540-87536-9_38","is_oa":false,"landing_page_url":"https://doi.org/10.1007/978-3-540-87536-9_38","pdf_url":null,"source":{"id":"https://openalex.org/S106296714","display_name":"Lecture notes in computer science","issn_l":"0302-9743","issn":["0302-9743","1611-3349"],"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":"book series"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Lecture Notes in Computer Science","raw_type":"book-chapter"},"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/A5100546550","display_name":"Yu Hiei","orcid":null},"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":"Yu Hiei","raw_affiliation_strings":["Graduate School of Information Science, Nara Institute of Science and Technology (NAIST), \u00a0, Takayama 8916-5, Ikoma, Nara, 630-0192, Japan","Graduate School of Information Science, Nara Institute of Science and Technology (NAIST), , Ikoma, Japan 630-0192#TAB#"],"affiliations":[{"raw_affiliation_string":"Graduate School of Information Science, Nara Institute of Science and Technology (NAIST), \u00a0, Takayama 8916-5, Ikoma, Nara, 630-0192, Japan","institution_ids":["https://openalex.org/I75917431"]},{"raw_affiliation_string":"Graduate School of Information Science, Nara Institute of Science and Technology (NAIST), , Ikoma, Japan 630-0192#TAB#","institution_ids":["https://openalex.org/I75917431"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5103376816","display_name":"Takeshi Mori","orcid":null},"institutions":[{"id":"https://openalex.org/I22299242","display_name":"Kyoto University","ror":"https://ror.org/02kpeqv85","country_code":"JP","type":"education","lineage":["https://openalex.org/I22299242"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Takeshi Mori","raw_affiliation_strings":["Graduate School of Informatics, Kyoto University, Gokasho, Uji, Kyoto, 611-0011, Japan","Graduate School of Informatics, Kyoto University, Gokasho, Uji, Japan 611-0011"],"affiliations":[{"raw_affiliation_string":"Graduate School of Informatics, Kyoto University, Gokasho, Uji, Kyoto, 611-0011, Japan","institution_ids":["https://openalex.org/I22299242"]},{"raw_affiliation_string":"Graduate School of Informatics, Kyoto University, Gokasho, Uji, Japan 611-0011","institution_ids":["https://openalex.org/I22299242"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5072540019","display_name":"Shin Ishii","orcid":"https://orcid.org/0000-0001-9385-8230"},"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"]},{"id":"https://openalex.org/I22299242","display_name":"Kyoto University","ror":"https://ror.org/02kpeqv85","country_code":"JP","type":"education","lineage":["https://openalex.org/I22299242"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Shin Ishii","raw_affiliation_strings":["Graduate School of Informatics, Kyoto University, Gokasho, Uji, Kyoto, 611-0011, Japan","Graduate School of Information Science, Nara Institute of Science and Technology (NAIST), \u00a0, Takayama 8916-5, Ikoma, Nara, 630-0192, Japan","Graduate School of Information Science, Nara Institute of Science and Technology (NAIST), , Ikoma, Japan 630-0192 and Graduate School of Informatics, Kyoto University, Gokasho, Uji, Japan 611-0011"],"affiliations":[{"raw_affiliation_string":"Graduate School of Informatics, Kyoto University, Gokasho, Uji, Kyoto, 611-0011, Japan","institution_ids":["https://openalex.org/I22299242"]},{"raw_affiliation_string":"Graduate School of Information Science, Nara Institute of Science and Technology (NAIST), \u00a0, Takayama 8916-5, Ikoma, Nara, 630-0192, Japan","institution_ids":["https://openalex.org/I75917431"]},{"raw_affiliation_string":"Graduate School of Information Science, Nara Institute of Science and Technology (NAIST), , Ikoma, Japan 630-0192 and Graduate School of Informatics, Kyoto University, Gokasho, Uji, Japan 611-0011","institution_ids":["https://openalex.org/I75917431"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5100546550"],"corresponding_institution_ids":["https://openalex.org/I75917431"],"apc_list":{"value":5000,"currency":"EUR","value_usd":5392},"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.01176955,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":"108","issue":"101","first_page":"367","last_page":"376"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10462","display_name":"Reinforcement Learning in Robotics","score":0.7366999983787537,"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":0.7366999983787537,"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":0.9239242076873779},{"id":"https://openalex.org/keywords/theory-of-computation","display_name":"Theory of computation","score":0.7694035768508911},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7519888877868652},{"id":"https://openalex.org/keywords/markov-decision-process","display_name":"Markov decision process","score":0.7080397009849548},{"id":"https://openalex.org/keywords/decomposition","display_name":"Decomposition","score":0.6672173142433167},{"id":"https://openalex.org/keywords/modular-design","display_name":"Modular design","score":0.6671165227890015},{"id":"https://openalex.org/keywords/control","display_name":"Control (management)","score":0.5504938364028931},{"id":"https://openalex.org/keywords/stability","display_name":"Stability (learning theory)","score":0.49831676483154297},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4799352288246155},{"id":"https://openalex.org/keywords/markov-process","display_name":"Markov process","score":0.3910382390022278},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.3067415952682495},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.19701653718948364},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.16985481977462769}],"concepts":[{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.9239242076873779},{"id":"https://openalex.org/C24858836","wikidata":"https://www.wikidata.org/wiki/Q844718","display_name":"Theory of computation","level":2,"score":0.7694035768508911},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7519888877868652},{"id":"https://openalex.org/C106189395","wikidata":"https://www.wikidata.org/wiki/Q176789","display_name":"Markov decision process","level":3,"score":0.7080397009849548},{"id":"https://openalex.org/C124681953","wikidata":"https://www.wikidata.org/wiki/Q339062","display_name":"Decomposition","level":2,"score":0.6672173142433167},{"id":"https://openalex.org/C101468663","wikidata":"https://www.wikidata.org/wiki/Q1620158","display_name":"Modular design","level":2,"score":0.6671165227890015},{"id":"https://openalex.org/C2775924081","wikidata":"https://www.wikidata.org/wiki/Q55608371","display_name":"Control (management)","level":2,"score":0.5504938364028931},{"id":"https://openalex.org/C112972136","wikidata":"https://www.wikidata.org/wiki/Q7595718","display_name":"Stability (learning theory)","level":2,"score":0.49831676483154297},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4799352288246155},{"id":"https://openalex.org/C159886148","wikidata":"https://www.wikidata.org/wiki/Q176645","display_name":"Markov process","level":2,"score":0.3910382390022278},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.3067415952682495},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.19701653718948364},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.16985481977462769},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"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/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.0},{"id":"https://openalex.org/C18903297","wikidata":"https://www.wikidata.org/wiki/Q7150","display_name":"Ecology","level":1,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1007/978-3-540-87536-9_38","is_oa":false,"landing_page_url":"https://doi.org/10.1007/978-3-540-87536-9_38","pdf_url":null,"source":{"id":"https://openalex.org/S106296714","display_name":"Lecture notes in computer science","issn_l":"0302-9743","issn":["0302-9743","1611-3349"],"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":"book series"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Lecture Notes in Computer Science","raw_type":"book-chapter"},{"id":"mag:75129147","is_oa":false,"landing_page_url":"https://ci.nii.ac.jp/naid/110006951369","pdf_url":null,"source":{"id":"https://openalex.org/S149828480","display_name":"Natural Computing","issn_l":"1567-7818","issn":["1567-7818","1572-9796"],"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":null,"is_accepted":false,"is_published":null,"raw_source_name":"Natural Computing","raw_type":null}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.6000000238418579,"id":"https://metadata.un.org/sdg/10","display_name":"Reduced inequalities"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":6,"referenced_works":["https://openalex.org/W1990517717","https://openalex.org/W2097815751","https://openalex.org/W2097861969","https://openalex.org/W2109910161","https://openalex.org/W2116064496","https://openalex.org/W2168342951"],"related_works":["https://openalex.org/W1486519009","https://openalex.org/W1506296237","https://openalex.org/W42929088","https://openalex.org/W2131627605","https://openalex.org/W1997816436","https://openalex.org/W3154189348","https://openalex.org/W3196528513","https://openalex.org/W2466611570","https://openalex.org/W2513578279","https://openalex.org/W2397557326","https://openalex.org/W1990961668","https://openalex.org/W2919701918","https://openalex.org/W2965963242","https://openalex.org/W2800391888","https://openalex.org/W2965407115","https://openalex.org/W3103145727","https://openalex.org/W2972525556","https://openalex.org/W2139394304","https://openalex.org/W2295413729","https://openalex.org/W2995773109"],"abstract_inverted_index":null,"counts_by_year":[],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}
