{"id":"https://openalex.org/W1556604365","doi":"https://doi.org/10.1007/978-3-540-89197-0_18","title":"Behavior Learning Based on a Policy Gradient Method: Separation of Environmental Dynamics and State Values in Policies","display_name":"Behavior Learning Based on a Policy Gradient Method: Separation of Environmental Dynamics and State Values in Policies","publication_year":2008,"publication_date":"2008-01-01","ids":{"openalex":"https://openalex.org/W1556604365","doi":"https://doi.org/10.1007/978-3-540-89197-0_18","mag":"1556604365"},"language":"en","primary_location":{"id":"doi:10.1007/978-3-540-89197-0_18","is_oa":false,"landing_page_url":"https://doi.org/10.1007/978-3-540-89197-0_18","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":"book-chapter","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/A5114007242","display_name":"Seiji Ishihara","orcid":null},"institutions":[{"id":"https://openalex.org/I916559398","display_name":"Kindai University","ror":"https://ror.org/05kt9ap64","country_code":"JP","type":"education","lineage":["https://openalex.org/I916559398"]}],"countries":["JP"],"is_corresponding":true,"raw_author_name":"Seiji Ishihara","raw_affiliation_strings":["Kinki University, 1 Takaya-umenobe, Higashi-hiroshima, Hiroshima, 739\u20132116, Japan"],"affiliations":[{"raw_affiliation_string":"Kinki University, 1 Takaya-umenobe, Higashi-hiroshima, Hiroshima, 739\u20132116, Japan","institution_ids":["https://openalex.org/I916559398"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5109452409","display_name":"Harukazu Igarashi","orcid":null},"institutions":[{"id":"https://openalex.org/I171481255","display_name":"Shibaura Institute of Technology","ror":"https://ror.org/020wjcq07","country_code":"JP","type":"education","lineage":["https://openalex.org/I171481255"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Harukazu Igarashi","raw_affiliation_strings":["Shibaura Institute of Technology, 3\u20137\u20135 Toyosu, Koto-ku, Tokyo, 135\u20138548, Japan"],"affiliations":[{"raw_affiliation_string":"Shibaura Institute of Technology, 3\u20137\u20135 Toyosu, Koto-ku, Tokyo, 135\u20138548, Japan","institution_ids":["https://openalex.org/I171481255"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5114007242"],"corresponding_institution_ids":["https://openalex.org/I916559398"],"apc_list":{"value":5000,"currency":"EUR","value_usd":5392},"apc_paid":null,"fwci":0.2788,"has_fulltext":false,"cited_by_count":1,"citation_normalized_percentile":{"value":0.54921811,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"164","last_page":"174"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10462","display_name":"Reinforcement Learning in Robotics","score":0.9779000282287598,"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":0.9779000282287598,"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/T11810","display_name":"Complex Systems and Decision Making","score":0.9574000239372253,"subfield":{"id":"https://openalex.org/subfields/1803","display_name":"Management Science and Operations Research"},"field":{"id":"https://openalex.org/fields/18","display_name":"Decision Sciences"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7531980276107788},{"id":"https://openalex.org/keywords/dynamics","display_name":"Dynamics (music)","score":0.5150525569915771},{"id":"https://openalex.org/keywords/state","display_name":"State (computer science)","score":0.5108518004417419},{"id":"https://openalex.org/keywords/separation","display_name":"Separation (statistics)","score":0.49965620040893555},{"id":"https://openalex.org/keywords/policy-learning","display_name":"Policy learning","score":0.4770464301109314},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.3804338574409485},{"id":"https://openalex.org/keywords/operations-research","display_name":"Operations research","score":0.37672656774520874},{"id":"https://openalex.org/keywords/management-science","display_name":"Management science","score":0.33816656470298767},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.2037191390991211},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.17799526453018188},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.08708056807518005},{"id":"https://openalex.org/keywords/physics","display_name":"Physics","score":0.07012298703193665},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.059060126543045044}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7531980276107788},{"id":"https://openalex.org/C145912823","wikidata":"https://www.wikidata.org/wiki/Q113558","display_name":"Dynamics (music)","level":2,"score":0.5150525569915771},{"id":"https://openalex.org/C48103436","wikidata":"https://www.wikidata.org/wiki/Q599031","display_name":"State (computer science)","level":2,"score":0.5108518004417419},{"id":"https://openalex.org/C2776061190","wikidata":"https://www.wikidata.org/wiki/Q7451805","display_name":"Separation (statistics)","level":2,"score":0.49965620040893555},{"id":"https://openalex.org/C2779436431","wikidata":"https://www.wikidata.org/wiki/Q30672407","display_name":"Policy learning","level":2,"score":0.4770464301109314},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3804338574409485},{"id":"https://openalex.org/C42475967","wikidata":"https://www.wikidata.org/wiki/Q194292","display_name":"Operations research","level":1,"score":0.37672656774520874},{"id":"https://openalex.org/C539667460","wikidata":"https://www.wikidata.org/wiki/Q2414942","display_name":"Management science","level":1,"score":0.33816656470298767},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.2037191390991211},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.17799526453018188},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.08708056807518005},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.07012298703193665},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.059060126543045044},{"id":"https://openalex.org/C24890656","wikidata":"https://www.wikidata.org/wiki/Q82811","display_name":"Acoustics","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1007/978-3-540-89197-0_18","is_oa":false,"landing_page_url":"https://doi.org/10.1007/978-3-540-89197-0_18","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"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":14,"referenced_works":["https://openalex.org/W1485905671","https://openalex.org/W1493914388","https://openalex.org/W1515851193","https://openalex.org/W1590759229","https://openalex.org/W2119717200","https://openalex.org/W2132787074","https://openalex.org/W2155027007","https://openalex.org/W2156737235","https://openalex.org/W2164056559","https://openalex.org/W2319588593","https://openalex.org/W2591255884","https://openalex.org/W2911283634","https://openalex.org/W2914656440","https://openalex.org/W4245182314"],"related_works":["https://openalex.org/W2071676784","https://openalex.org/W4292513318","https://openalex.org/W4308092240","https://openalex.org/W2287611352","https://openalex.org/W320684304","https://openalex.org/W1509352139","https://openalex.org/W4385464961","https://openalex.org/W2060903012","https://openalex.org/W2021161555","https://openalex.org/W4400836012"],"abstract_inverted_index":null,"counts_by_year":[],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}