{"id":"https://openalex.org/W2766806202","doi":"https://doi.org/10.1007/978-3-319-70087-8_79","title":"Average Reward Reinforcement Learning for Semi-Markov Decision Processes","display_name":"Average Reward Reinforcement Learning for Semi-Markov Decision Processes","publication_year":2017,"publication_date":"2017-01-01","ids":{"openalex":"https://openalex.org/W2766806202","doi":"https://doi.org/10.1007/978-3-319-70087-8_79","mag":"2766806202"},"language":"en","primary_location":{"id":"doi:10.1007/978-3-319-70087-8_79","is_oa":false,"landing_page_url":"https://doi.org/10.1007/978-3-319-70087-8_79","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/A5100726978","display_name":"Jiaxuan Yang","orcid":"https://orcid.org/0000-0002-0672-1330"},"institutions":[{"id":"https://openalex.org/I204983213","display_name":"Harbin Institute of Technology","ror":"https://ror.org/01yqg2h08","country_code":"CN","type":"education","lineage":["https://openalex.org/I204983213"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Jiayuan Yang","raw_affiliation_strings":["Harbin Institute of Technology Shenzhen Graduate School, Shenzhen, China"],"affiliations":[{"raw_affiliation_string":"Harbin Institute of Technology Shenzhen Graduate School, Shenzhen, China","institution_ids":["https://openalex.org/I204983213"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100677178","display_name":"Yanjie Li","orcid":"https://orcid.org/0000-0001-7890-9677"},"institutions":[{"id":"https://openalex.org/I90610280","display_name":"South China University of Technology","ror":"https://ror.org/0530pts50","country_code":"CN","type":"education","lineage":["https://openalex.org/I90610280"]},{"id":"https://openalex.org/I204983213","display_name":"Harbin Institute of Technology","ror":"https://ror.org/01yqg2h08","country_code":"CN","type":"education","lineage":["https://openalex.org/I204983213"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yanjie Li","raw_affiliation_strings":["Harbin Institute of Technology Shenzhen Graduate School, Shenzhen, China","South China University of Technology, Guangzhou, China"],"affiliations":[{"raw_affiliation_string":"Harbin Institute of Technology Shenzhen Graduate School, Shenzhen, China","institution_ids":["https://openalex.org/I204983213"]},{"raw_affiliation_string":"South China University of Technology, Guangzhou, China","institution_ids":["https://openalex.org/I90610280"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5072197068","display_name":"Haoyao Chen","orcid":"https://orcid.org/0000-0003-1652-9681"},"institutions":[{"id":"https://openalex.org/I204983213","display_name":"Harbin Institute of Technology","ror":"https://ror.org/01yqg2h08","country_code":"CN","type":"education","lineage":["https://openalex.org/I204983213"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Haoyao Chen","raw_affiliation_strings":["Harbin Institute of Technology Shenzhen Graduate School, Shenzhen, China"],"affiliations":[{"raw_affiliation_string":"Harbin Institute of Technology Shenzhen Graduate School, Shenzhen, China","institution_ids":["https://openalex.org/I204983213"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5102010512","display_name":"Jiangang Li","orcid":"https://orcid.org/0000-0002-6064-3361"},"institutions":[{"id":"https://openalex.org/I204983213","display_name":"Harbin Institute of Technology","ror":"https://ror.org/01yqg2h08","country_code":"CN","type":"education","lineage":["https://openalex.org/I204983213"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jiangang Li","raw_affiliation_strings":["Harbin Institute of Technology Shenzhen Graduate School, Shenzhen, China"],"affiliations":[{"raw_affiliation_string":"Harbin Institute of Technology Shenzhen Graduate School, Shenzhen, China","institution_ids":["https://openalex.org/I204983213"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5100726978"],"corresponding_institution_ids":["https://openalex.org/I204983213"],"apc_list":{"value":5000,"currency":"EUR","value_usd":5392},"apc_paid":null,"fwci":0.8477,"has_fulltext":false,"cited_by_count":8,"citation_normalized_percentile":{"value":0.7785369,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":98},"biblio":{"volume":null,"issue":null,"first_page":"768","last_page":"777"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10462","display_name":"Reinforcement Learning in Robotics","score":0.9995999932289124,"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":0.9995999932289124,"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/T10328","display_name":"Supply Chain and Inventory Management","score":0.9926000237464905,"subfield":{"id":"https://openalex.org/subfields/1404","display_name":"Management Information Systems"},"field":{"id":"https://openalex.org/fields/14","display_name":"Business, Management and Accounting"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}},{"id":"https://openalex.org/T10791","display_name":"Advanced Control Systems Optimization","score":0.970300018787384,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/markov-decision-process","display_name":"Markov decision process","score":0.9018509387969971},{"id":"https://openalex.org/keywords/reinforcement-learning","display_name":"Reinforcement learning","score":0.8232008814811707},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7096587419509888},{"id":"https://openalex.org/keywords/convergence","display_name":"Convergence (economics)","score":0.5831945538520813},{"id":"https://openalex.org/keywords/mathematical-optimization","display_name":"Mathematical optimization","score":0.5505880117416382},{"id":"https://openalex.org/keywords/bellman-equation","display_name":"Bellman equation","score":0.5412582159042358},{"id":"https://openalex.org/keywords/markov-chain","display_name":"Markov chain","score":0.5344632863998413},{"id":"https://openalex.org/keywords/bisection","display_name":"Bisection","score":0.4823126792907715},{"id":"https://openalex.org/keywords/shortest-path-problem","display_name":"Shortest path problem","score":0.4731800854206085},{"id":"https://openalex.org/keywords/bisection-method","display_name":"Bisection method","score":0.4616073668003082},{"id":"https://openalex.org/keywords/markov-process","display_name":"Markov process","score":0.4573823809623718},{"id":"https://openalex.org/keywords/stochastic-approximation","display_name":"Stochastic approximation","score":0.4202166497707367},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.335762083530426},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.3080158233642578},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.2709529995918274},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.2183951437473297},{"id":"https://openalex.org/keywords/theoretical-computer-science","display_name":"Theoretical computer science","score":0.1340823769569397},{"id":"https://openalex.org/keywords/graph","display_name":"Graph","score":0.09632164239883423},{"id":"https://openalex.org/keywords/statistics","display_name":"Statistics","score":0.08897808194160461}],"concepts":[{"id":"https://openalex.org/C106189395","wikidata":"https://www.wikidata.org/wiki/Q176789","display_name":"Markov decision process","level":3,"score":0.9018509387969971},{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.8232008814811707},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7096587419509888},{"id":"https://openalex.org/C2777303404","wikidata":"https://www.wikidata.org/wiki/Q759757","display_name":"Convergence (economics)","level":2,"score":0.5831945538520813},{"id":"https://openalex.org/C126255220","wikidata":"https://www.wikidata.org/wiki/Q141495","display_name":"Mathematical optimization","level":1,"score":0.5505880117416382},{"id":"https://openalex.org/C14646407","wikidata":"https://www.wikidata.org/wiki/Q1430750","display_name":"Bellman equation","level":2,"score":0.5412582159042358},{"id":"https://openalex.org/C98763669","wikidata":"https://www.wikidata.org/wiki/Q176645","display_name":"Markov chain","level":2,"score":0.5344632863998413},{"id":"https://openalex.org/C31599958","wikidata":"https://www.wikidata.org/wiki/Q3128632","display_name":"Bisection","level":2,"score":0.4823126792907715},{"id":"https://openalex.org/C22590252","wikidata":"https://www.wikidata.org/wiki/Q1058754","display_name":"Shortest path problem","level":3,"score":0.4731800854206085},{"id":"https://openalex.org/C157544257","wikidata":"https://www.wikidata.org/wiki/Q866300","display_name":"Bisection method","level":2,"score":0.4616073668003082},{"id":"https://openalex.org/C159886148","wikidata":"https://www.wikidata.org/wiki/Q176645","display_name":"Markov process","level":2,"score":0.4573823809623718},{"id":"https://openalex.org/C55479107","wikidata":"https://www.wikidata.org/wiki/Q97663916","display_name":"Stochastic approximation","level":3,"score":0.4202166497707367},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.335762083530426},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3080158233642578},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.2709529995918274},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.2183951437473297},{"id":"https://openalex.org/C80444323","wikidata":"https://www.wikidata.org/wiki/Q2878974","display_name":"Theoretical computer science","level":1,"score":0.1340823769569397},{"id":"https://openalex.org/C132525143","wikidata":"https://www.wikidata.org/wiki/Q141488","display_name":"Graph","level":2,"score":0.09632164239883423},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.08897808194160461},{"id":"https://openalex.org/C2524010","wikidata":"https://www.wikidata.org/wiki/Q8087","display_name":"Geometry","level":1,"score":0.0},{"id":"https://openalex.org/C38652104","wikidata":"https://www.wikidata.org/wiki/Q3510521","display_name":"Computer security","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/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.0},{"id":"https://openalex.org/C50522688","wikidata":"https://www.wikidata.org/wiki/Q189833","display_name":"Economic growth","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1007/978-3-319-70087-8_79","is_oa":false,"landing_page_url":"https://doi.org/10.1007/978-3-319-70087-8_79","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":[{"score":0.550000011920929,"id":"https://metadata.un.org/sdg/16","display_name":"Peace, Justice and strong institutions"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":22,"referenced_works":["https://openalex.org/W566534119","https://openalex.org/W628582992","https://openalex.org/W1549353711","https://openalex.org/W1850488217","https://openalex.org/W1979894788","https://openalex.org/W1991138660","https://openalex.org/W1998645260","https://openalex.org/W2075754841","https://openalex.org/W2097931172","https://openalex.org/W2100677568","https://openalex.org/W2101242010","https://openalex.org/W2101915445","https://openalex.org/W2103406407","https://openalex.org/W2111764152","https://openalex.org/W2119567691","https://openalex.org/W2123952007","https://openalex.org/W2154204727","https://openalex.org/W2161753411","https://openalex.org/W2293893700","https://openalex.org/W2553188523","https://openalex.org/W3139377883","https://openalex.org/W4298023569"],"related_works":["https://openalex.org/W2329494729","https://openalex.org/W3112697985","https://openalex.org/W41290553","https://openalex.org/W2585516632","https://openalex.org/W1986919722","https://openalex.org/W2093663313","https://openalex.org/W40332083","https://openalex.org/W4296983618","https://openalex.org/W2158390333","https://openalex.org/W2577097539"],"abstract_inverted_index":null,"counts_by_year":[{"year":2024,"cited_by_count":5},{"year":2020,"cited_by_count":1},{"year":2019,"cited_by_count":1},{"year":2017,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}