{"id":"https://openalex.org/W1506993216","doi":"https://doi.org/10.1007/978-3-642-17298-4_29","title":"Swarm Reinforcement Learning Method Based on an Actor-Critic Method","display_name":"Swarm Reinforcement Learning Method Based on an Actor-Critic Method","publication_year":2010,"publication_date":"2010-01-01","ids":{"openalex":"https://openalex.org/W1506993216","doi":"https://doi.org/10.1007/978-3-642-17298-4_29","mag":"1506993216"},"language":"en","primary_location":{"id":"doi:10.1007/978-3-642-17298-4_29","is_oa":false,"landing_page_url":"https://doi.org/10.1007/978-3-642-17298-4_29","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/A5081026637","display_name":"Hitoshi Iima","orcid":"https://orcid.org/0000-0001-9596-8679"},"institutions":[{"id":"https://openalex.org/I27429435","display_name":"Kyoto Institute of Technology","ror":"https://ror.org/00965ax52","country_code":"JP","type":"education","lineage":["https://openalex.org/I27429435"]}],"countries":["JP"],"is_corresponding":true,"raw_author_name":"Hitoshi Iima","raw_affiliation_strings":["Kyoto Institute of Technology, Matsugasaki, Sakyo-ku, Kyoto, Japan","Kyoto Institute of Technology, Sakyo-ku, Kyoto, Japan#TAB#"],"affiliations":[{"raw_affiliation_string":"Kyoto Institute of Technology, Matsugasaki, Sakyo-ku, Kyoto, Japan","institution_ids":["https://openalex.org/I27429435"]},{"raw_affiliation_string":"Kyoto Institute of Technology, Sakyo-ku, Kyoto, Japan#TAB#","institution_ids":["https://openalex.org/I27429435"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5001161243","display_name":"Yasuaki Kuroe","orcid":"https://orcid.org/0000-0001-5126-0660"},"institutions":[{"id":"https://openalex.org/I27429435","display_name":"Kyoto Institute of Technology","ror":"https://ror.org/00965ax52","country_code":"JP","type":"education","lineage":["https://openalex.org/I27429435"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Yasuaki Kuroe","raw_affiliation_strings":["Kyoto Institute of Technology, Matsugasaki, Sakyo-ku, Kyoto, Japan","Kyoto Institute of Technology, Sakyo-ku, Kyoto, Japan#TAB#"],"affiliations":[{"raw_affiliation_string":"Kyoto Institute of Technology, Matsugasaki, Sakyo-ku, Kyoto, Japan","institution_ids":["https://openalex.org/I27429435"]},{"raw_affiliation_string":"Kyoto Institute of Technology, Sakyo-ku, Kyoto, Japan#TAB#","institution_ids":["https://openalex.org/I27429435"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5081026637"],"corresponding_institution_ids":["https://openalex.org/I27429435"],"apc_list":{"value":5000,"currency":"EUR","value_usd":5392},"apc_paid":null,"fwci":0.5664,"has_fulltext":false,"cited_by_count":5,"citation_normalized_percentile":{"value":0.65014935,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":96},"biblio":{"volume":null,"issue":null,"first_page":"279","last_page":"288"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10462","display_name":"Reinforcement Learning in Robotics","score":0.9976999759674072,"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":0.9976999759674072,"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/T12794","display_name":"Adaptive Dynamic Programming Control","score":0.9491999745368958,"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/T12611","display_name":"Neural Networks and Reservoir Computing","score":0.9054999947547913,"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":0.8772573471069336},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7643305063247681},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5862494707107544},{"id":"https://openalex.org/keywords/state-space","display_name":"State space","score":0.5663368701934814},{"id":"https://openalex.org/keywords/swarm-behaviour","display_name":"Swarm behaviour","score":0.5589879751205444},{"id":"https://openalex.org/keywords/learning-classifier-system","display_name":"Learning classifier system","score":0.5449482798576355},{"id":"https://openalex.org/keywords/inverted-pendulum","display_name":"Inverted pendulum","score":0.531258761882782},{"id":"https://openalex.org/keywords/action","display_name":"Action (physics)","score":0.4907720983028412},{"id":"https://openalex.org/keywords/temporal-difference-learning","display_name":"Temporal difference learning","score":0.41473427414894104},{"id":"https://openalex.org/keywords/error-driven-learning","display_name":"Error-driven learning","score":0.412563681602478},{"id":"https://openalex.org/keywords/q-learning","display_name":"Q-learning","score":0.4124917984008789},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.38565772771835327},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.12880375981330872}],"concepts":[{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.8772573471069336},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7643305063247681},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5862494707107544},{"id":"https://openalex.org/C72434380","wikidata":"https://www.wikidata.org/wiki/Q230930","display_name":"State space","level":2,"score":0.5663368701934814},{"id":"https://openalex.org/C181335050","wikidata":"https://www.wikidata.org/wiki/Q14915018","display_name":"Swarm behaviour","level":2,"score":0.5589879751205444},{"id":"https://openalex.org/C199190896","wikidata":"https://www.wikidata.org/wiki/Q3509276","display_name":"Learning classifier system","level":3,"score":0.5449482798576355},{"id":"https://openalex.org/C192921069","wikidata":"https://www.wikidata.org/wiki/Q550134","display_name":"Inverted pendulum","level":3,"score":0.531258761882782},{"id":"https://openalex.org/C2780791683","wikidata":"https://www.wikidata.org/wiki/Q846785","display_name":"Action (physics)","level":2,"score":0.4907720983028412},{"id":"https://openalex.org/C196340769","wikidata":"https://www.wikidata.org/wiki/Q7698910","display_name":"Temporal difference learning","level":3,"score":0.41473427414894104},{"id":"https://openalex.org/C47932503","wikidata":"https://www.wikidata.org/wiki/Q5395689","display_name":"Error-driven learning","level":3,"score":0.412563681602478},{"id":"https://openalex.org/C188116033","wikidata":"https://www.wikidata.org/wiki/Q2664563","display_name":"Q-learning","level":3,"score":0.4124917984008789},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.38565772771835327},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.12880375981330872},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","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/C62520636","wikidata":"https://www.wikidata.org/wiki/Q944","display_name":"Quantum mechanics","level":1,"score":0.0},{"id":"https://openalex.org/C158622935","wikidata":"https://www.wikidata.org/wiki/Q660848","display_name":"Nonlinear system","level":2,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1007/978-3-642-17298-4_29","is_oa":false,"landing_page_url":"https://doi.org/10.1007/978-3-642-17298-4_29","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":[{"display_name":"Peace, Justice and strong institutions","score":0.4399999976158142,"id":"https://metadata.un.org/sdg/16"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":11,"referenced_works":["https://openalex.org/W32403112","https://openalex.org/W1515851193","https://openalex.org/W1521427077","https://openalex.org/W1557517019","https://openalex.org/W2099618002","https://openalex.org/W2113501460","https://openalex.org/W2114317160","https://openalex.org/W2397962349","https://openalex.org/W2911283634","https://openalex.org/W2914656440","https://openalex.org/W4301630257"],"related_works":["https://openalex.org/W3140225428","https://openalex.org/W2610686804","https://openalex.org/W3148138296","https://openalex.org/W4213341750","https://openalex.org/W2313756439","https://openalex.org/W2171128163","https://openalex.org/W4253074907","https://openalex.org/W2152445738","https://openalex.org/W2130711276","https://openalex.org/W4206305295"],"abstract_inverted_index":null,"counts_by_year":[{"year":2018,"cited_by_count":2},{"year":2014,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}