{"id":"https://openalex.org/W1485905671","doi":"https://doi.org/10.1016/b978-1-55860-377-6.50044-x","title":"Reinforcement Learning by Stochastic Hill Climbing on Discounted Reward","display_name":"Reinforcement Learning by Stochastic Hill Climbing on Discounted Reward","publication_year":1995,"publication_date":"1995-01-01","ids":{"openalex":"https://openalex.org/W1485905671","doi":"https://doi.org/10.1016/b978-1-55860-377-6.50044-x","mag":"1485905671"},"language":"en","primary_location":{"id":"doi:10.1016/b978-1-55860-377-6.50044-x","is_oa":false,"landing_page_url":"https://doi.org/10.1016/b978-1-55860-377-6.50044-x","pdf_url":null,"source":{"id":"https://openalex.org/S4306463230","display_name":"Elsevier eBooks","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/P4310320990","host_organization_name":"Elsevier BV","host_organization_lineage":["https://openalex.org/P4310320990"],"host_organization_lineage_names":["Elsevier BV"],"type":"ebook platform"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Machine Learning Proceedings 1995","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/A5100764613","display_name":"Hajime Kimura","orcid":"https://orcid.org/0000-0002-4442-0758"},"institutions":[{"id":"https://openalex.org/I114531698","display_name":"Tokyo Institute of Technology","ror":"https://ror.org/0112mx960","country_code":"JP","type":"education","lineage":["https://openalex.org/I114531698"]}],"countries":["JP"],"is_corresponding":true,"raw_author_name":"Hajime Kimura","raw_affiliation_strings":["Department of Intelligence Science, Interdisciplinary Graduate School of Science and Engineering, Tokyo Institute of Technology, 4259, Nagatsuda, Midori-ku, Yokohama, 226 JAPAN"],"affiliations":[{"raw_affiliation_string":"Department of Intelligence Science, Interdisciplinary Graduate School of Science and Engineering, Tokyo Institute of Technology, 4259, Nagatsuda, Midori-ku, Yokohama, 226 JAPAN","institution_ids":["https://openalex.org/I114531698"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5069532250","display_name":"M. Yamamura","orcid":"https://orcid.org/0000-0001-9053-8653"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Masayuki Yamamura","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5100877933","display_name":"Shigenobu Kobayashi","orcid":null},"institutions":[{"id":"https://openalex.org/I114531698","display_name":"Tokyo Institute of Technology","ror":"https://ror.org/0112mx960","country_code":"JP","type":"education","lineage":["https://openalex.org/I114531698"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Shigenobu Kobayashi","raw_affiliation_strings":["Department of Intelligence Science, Interdisciplinary Graduate School of Science and Engineering, Tokyo Institute of Technology, 4259, Nagatsuda, Midori-ku, Yokohama, 226 JAPAN"],"affiliations":[{"raw_affiliation_string":"Department of Intelligence Science, Interdisciplinary Graduate School of Science and Engineering, Tokyo Institute of Technology, 4259, Nagatsuda, Midori-ku, Yokohama, 226 JAPAN","institution_ids":["https://openalex.org/I114531698"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5100764613"],"corresponding_institution_ids":["https://openalex.org/I114531698"],"apc_list":null,"apc_paid":null,"fwci":0.9301,"has_fulltext":false,"cited_by_count":59,"citation_normalized_percentile":{"value":0.70780142,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":98},"biblio":{"volume":null,"issue":null,"first_page":"295","last_page":"303"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10462","display_name":"Reinforcement Learning in Robotics","score":0.9998999834060669,"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":0.9998999834060669,"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/T11975","display_name":"Evolutionary Algorithms and Applications","score":0.9912999868392944,"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/T10848","display_name":"Advanced Multi-Objective Optimization Algorithms","score":0.9833999872207642,"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":0.848953127861023},{"id":"https://openalex.org/keywords/markov-decision-process","display_name":"Markov decision process","score":0.7060457468032837},{"id":"https://openalex.org/keywords/q-learning","display_name":"Q-learning","score":0.6747404932975769},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6003432869911194},{"id":"https://openalex.org/keywords/climbing","display_name":"Climbing","score":0.5582872629165649},{"id":"https://openalex.org/keywords/reinforcement","display_name":"Reinforcement","score":0.5078304409980774},{"id":"https://openalex.org/keywords/mathematical-optimization","display_name":"Mathematical optimization","score":0.4322819709777832},{"id":"https://openalex.org/keywords/markov-process","display_name":"Markov process","score":0.4301433861255646},{"id":"https://openalex.org/keywords/markov-chain","display_name":"Markov chain","score":0.4249486029148102},{"id":"https://openalex.org/keywords/independent-and-identically-distributed-random-variables","display_name":"Independent and identically distributed random variables","score":0.41740691661834717},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4044732451438904},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.2883068323135376},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.19950714707374573},{"id":"https://openalex.org/keywords/random-variable","display_name":"Random variable","score":0.1327173411846161},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.10973373055458069},{"id":"https://openalex.org/keywords/statistics","display_name":"Statistics","score":0.09554746747016907}],"concepts":[{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.848953127861023},{"id":"https://openalex.org/C106189395","wikidata":"https://www.wikidata.org/wiki/Q176789","display_name":"Markov decision process","level":3,"score":0.7060457468032837},{"id":"https://openalex.org/C188116033","wikidata":"https://www.wikidata.org/wiki/Q2664563","display_name":"Q-learning","level":3,"score":0.6747404932975769},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6003432869911194},{"id":"https://openalex.org/C95038775","wikidata":"https://www.wikidata.org/wiki/Q22857","display_name":"Climbing","level":2,"score":0.5582872629165649},{"id":"https://openalex.org/C67203356","wikidata":"https://www.wikidata.org/wiki/Q1321905","display_name":"Reinforcement","level":2,"score":0.5078304409980774},{"id":"https://openalex.org/C126255220","wikidata":"https://www.wikidata.org/wiki/Q141495","display_name":"Mathematical optimization","level":1,"score":0.4322819709777832},{"id":"https://openalex.org/C159886148","wikidata":"https://www.wikidata.org/wiki/Q176645","display_name":"Markov process","level":2,"score":0.4301433861255646},{"id":"https://openalex.org/C98763669","wikidata":"https://www.wikidata.org/wiki/Q176645","display_name":"Markov chain","level":2,"score":0.4249486029148102},{"id":"https://openalex.org/C141513077","wikidata":"https://www.wikidata.org/wiki/Q378542","display_name":"Independent and identically distributed random variables","level":3,"score":0.41740691661834717},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4044732451438904},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.2883068323135376},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.19950714707374573},{"id":"https://openalex.org/C122123141","wikidata":"https://www.wikidata.org/wiki/Q176623","display_name":"Random variable","level":2,"score":0.1327173411846161},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.10973373055458069},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.09554746747016907},{"id":"https://openalex.org/C66938386","wikidata":"https://www.wikidata.org/wiki/Q633538","display_name":"Structural engineering","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1016/b978-1-55860-377-6.50044-x","is_oa":false,"landing_page_url":"https://doi.org/10.1016/b978-1-55860-377-6.50044-x","pdf_url":null,"source":{"id":"https://openalex.org/S4306463230","display_name":"Elsevier eBooks","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/P4310320990","host_organization_name":"Elsevier BV","host_organization_lineage":["https://openalex.org/P4310320990"],"host_organization_lineage_names":["Elsevier BV"],"type":"ebook platform"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Machine Learning Proceedings 1995","raw_type":"book-chapter"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/16","display_name":"Peace, Justice and strong institutions","score":0.75}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":21,"referenced_works":["https://openalex.org/W32403112","https://openalex.org/W1520048352","https://openalex.org/W1522632257","https://openalex.org/W1541084404","https://openalex.org/W1542941925","https://openalex.org/W1549353711","https://openalex.org/W1555801537","https://openalex.org/W1557517019","https://openalex.org/W1657674574","https://openalex.org/W1995663008","https://openalex.org/W2064018461","https://openalex.org/W2099873296","https://openalex.org/W2100677568","https://openalex.org/W2101130101","https://openalex.org/W2109090232","https://openalex.org/W2119717200","https://openalex.org/W2160067530","https://openalex.org/W3041202696","https://openalex.org/W6600402959","https://openalex.org/W6604176764","https://openalex.org/W6633302335"],"related_works":["https://openalex.org/W2808418668","https://openalex.org/W2357975469","https://openalex.org/W2101748387","https://openalex.org/W3096874164","https://openalex.org/W4281812492","https://openalex.org/W2315999538","https://openalex.org/W3105579180","https://openalex.org/W2970347269","https://openalex.org/W3167472281","https://openalex.org/W4400868993"],"abstract_inverted_index":null,"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2024,"cited_by_count":1},{"year":2022,"cited_by_count":3},{"year":2021,"cited_by_count":4},{"year":2020,"cited_by_count":2},{"year":2019,"cited_by_count":1},{"year":2018,"cited_by_count":3},{"year":2017,"cited_by_count":1},{"year":2016,"cited_by_count":2},{"year":2014,"cited_by_count":2},{"year":2013,"cited_by_count":4}],"updated_date":"2026-04-04T16:13:02.066488","created_date":"2025-10-10T00:00:00"}