{"id":"https://openalex.org/W2152446322","doi":"https://doi.org/10.1007/s10015-014-0146-0","title":"A reward allocation method for reinforcement learning in stabilizing control tasks","display_name":"A reward allocation method for reinforcement learning in stabilizing control tasks","publication_year":2014,"publication_date":"2014-07-28","ids":{"openalex":"https://openalex.org/W2152446322","doi":"https://doi.org/10.1007/s10015-014-0146-0","mag":"2152446322"},"language":"en","primary_location":{"id":"doi:10.1007/s10015-014-0146-0","is_oa":false,"landing_page_url":"https://doi.org/10.1007/s10015-014-0146-0","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/A5049676683","display_name":"Shu Hosokawa","orcid":null},"institutions":[{"id":"https://openalex.org/I20529979","display_name":"University of Electro-Communications","ror":"https://ror.org/02x73b849","country_code":"JP","type":"education","lineage":["https://openalex.org/I20529979"]}],"countries":["JP"],"is_corresponding":true,"raw_author_name":"Shu Hosokawa","raw_affiliation_strings":["Department of Electronic Engineering, The University of Electro-Communications, 1-5-1 Chofu-ga-oka, Tokyo, Chofu, 182-8585, Japan"],"affiliations":[{"raw_affiliation_string":"Department of Electronic Engineering, The University of Electro-Communications, 1-5-1 Chofu-ga-oka, Tokyo, Chofu, 182-8585, Japan","institution_ids":["https://openalex.org/I20529979"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101112200","display_name":"Joji Kato","orcid":null},"institutions":[{"id":"https://openalex.org/I20529979","display_name":"University of Electro-Communications","ror":"https://ror.org/02x73b849","country_code":"JP","type":"education","lineage":["https://openalex.org/I20529979"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Joji Kato","raw_affiliation_strings":["Department of Electronic Engineering, The University of Electro-Communications, 1-5-1 Chofu-ga-oka, Tokyo, Chofu, 182-8585, Japan"],"affiliations":[{"raw_affiliation_string":"Department of Electronic Engineering, The University of Electro-Communications, 1-5-1 Chofu-ga-oka, Tokyo, Chofu, 182-8585, Japan","institution_ids":["https://openalex.org/I20529979"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5103711128","display_name":"Kazushi Nakano","orcid":null},"institutions":[{"id":"https://openalex.org/I20529979","display_name":"University of Electro-Communications","ror":"https://ror.org/02x73b849","country_code":"JP","type":"education","lineage":["https://openalex.org/I20529979"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Kazushi Nakano","raw_affiliation_strings":["Department of Electronic Engineering, The University of Electro-Communications, 1-5-1 Chofu-ga-oka, Tokyo, Chofu, 182-8585, Japan"],"affiliations":[{"raw_affiliation_string":"Department of Electronic Engineering, The University of Electro-Communications, 1-5-1 Chofu-ga-oka, Tokyo, Chofu, 182-8585, Japan","institution_ids":["https://openalex.org/I20529979"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5049676683"],"corresponding_institution_ids":["https://openalex.org/I20529979"],"apc_list":{"value":2390,"currency":"EUR","value_usd":2990},"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":6,"citation_normalized_percentile":{"value":0.12073904,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":96},"biblio":{"volume":"19","issue":"2","first_page":"109","last_page":"114"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10462","display_name":"Reinforcement Learning in Robotics","score":0.9998000264167786,"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":0.9998000264167786,"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/T10791","display_name":"Advanced Control Systems Optimization","score":0.9835000038146973,"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"}},{"id":"https://openalex.org/T12794","display_name":"Adaptive Dynamic Programming Control","score":0.9787999987602234,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/reinforcement-learning","display_name":"Reinforcement learning","score":0.8527010679244995},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7896578907966614},{"id":"https://openalex.org/keywords/markov-decision-process","display_name":"Markov decision process","score":0.6758381128311157},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.6512900590896606},{"id":"https://openalex.org/keywords/robot","display_name":"Robot","score":0.5678738951683044},{"id":"https://openalex.org/keywords/q-learning","display_name":"Q-learning","score":0.5545152425765991},{"id":"https://openalex.org/keywords/inverted-pendulum","display_name":"Inverted pendulum","score":0.5393713712692261},{"id":"https://openalex.org/keywords/process","display_name":"Process (computing)","score":0.5375293493270874},{"id":"https://openalex.org/keywords/control","display_name":"Control (management)","score":0.520973265171051},{"id":"https://openalex.org/keywords/convergence","display_name":"Convergence (economics)","score":0.5125434398651123},{"id":"https://openalex.org/keywords/learning-classifier-system","display_name":"Learning classifier system","score":0.47006353735923767},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.46645015478134155},{"id":"https://openalex.org/keywords/state","display_name":"State (computer science)","score":0.42812225222587585},{"id":"https://openalex.org/keywords/stability","display_name":"Stability (learning theory)","score":0.4234943687915802},{"id":"https://openalex.org/keywords/markov-process","display_name":"Markov process","score":0.41550323367118835},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.3367004990577698},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.10712605714797974},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.09846940636634827},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.06753677129745483}],"concepts":[{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.8527010679244995},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7896578907966614},{"id":"https://openalex.org/C106189395","wikidata":"https://www.wikidata.org/wiki/Q176789","display_name":"Markov decision process","level":3,"score":0.6758381128311157},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.6512900590896606},{"id":"https://openalex.org/C90509273","wikidata":"https://www.wikidata.org/wiki/Q11012","display_name":"Robot","level":2,"score":0.5678738951683044},{"id":"https://openalex.org/C188116033","wikidata":"https://www.wikidata.org/wiki/Q2664563","display_name":"Q-learning","level":3,"score":0.5545152425765991},{"id":"https://openalex.org/C192921069","wikidata":"https://www.wikidata.org/wiki/Q550134","display_name":"Inverted pendulum","level":3,"score":0.5393713712692261},{"id":"https://openalex.org/C98045186","wikidata":"https://www.wikidata.org/wiki/Q205663","display_name":"Process (computing)","level":2,"score":0.5375293493270874},{"id":"https://openalex.org/C2775924081","wikidata":"https://www.wikidata.org/wiki/Q55608371","display_name":"Control (management)","level":2,"score":0.520973265171051},{"id":"https://openalex.org/C2777303404","wikidata":"https://www.wikidata.org/wiki/Q759757","display_name":"Convergence (economics)","level":2,"score":0.5125434398651123},{"id":"https://openalex.org/C199190896","wikidata":"https://www.wikidata.org/wiki/Q3509276","display_name":"Learning classifier system","level":3,"score":0.47006353735923767},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.46645015478134155},{"id":"https://openalex.org/C48103436","wikidata":"https://www.wikidata.org/wiki/Q599031","display_name":"State (computer science)","level":2,"score":0.42812225222587585},{"id":"https://openalex.org/C112972136","wikidata":"https://www.wikidata.org/wiki/Q7595718","display_name":"Stability (learning theory)","level":2,"score":0.4234943687915802},{"id":"https://openalex.org/C159886148","wikidata":"https://www.wikidata.org/wiki/Q176645","display_name":"Markov process","level":2,"score":0.41550323367118835},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.3367004990577698},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.10712605714797974},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.09846940636634827},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.06753677129745483},{"id":"https://openalex.org/C158622935","wikidata":"https://www.wikidata.org/wiki/Q660848","display_name":"Nonlinear system","level":2,"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/C201995342","wikidata":"https://www.wikidata.org/wiki/Q682496","display_name":"Systems engineering","level":1,"score":0.0},{"id":"https://openalex.org/C50522688","wikidata":"https://www.wikidata.org/wiki/Q189833","display_name":"Economic growth","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/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","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/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1007/s10015-014-0146-0","is_oa":false,"landing_page_url":"https://doi.org/10.1007/s10015-014-0146-0","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":0.46000000834465027,"id":"https://metadata.un.org/sdg/10","display_name":"Reduced inequalities"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":14,"referenced_works":["https://openalex.org/W32403112","https://openalex.org/W1514477737","https://openalex.org/W1515851193","https://openalex.org/W1557517019","https://openalex.org/W1745487673","https://openalex.org/W1995663008","https://openalex.org/W2057678859","https://openalex.org/W2066411379","https://openalex.org/W2088821982","https://openalex.org/W2109910161","https://openalex.org/W2121863487","https://openalex.org/W2124491905","https://openalex.org/W2914656440","https://openalex.org/W3139377883"],"related_works":["https://openalex.org/W2808418668","https://openalex.org/W2101748387","https://openalex.org/W2357975469","https://openalex.org/W4380550992","https://openalex.org/W4322760752","https://openalex.org/W3096874164","https://openalex.org/W2970347269","https://openalex.org/W2146763310","https://openalex.org/W3167472281","https://openalex.org/W2937181779"],"abstract_inverted_index":null,"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2023,"cited_by_count":2},{"year":2019,"cited_by_count":2},{"year":2018,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}