{"id":"https://openalex.org/W2027855416","doi":"https://doi.org/10.1007/s10479-012-1128-z","title":"Q-learning and policy iteration algorithms for stochastic shortest path problems","display_name":"Q-learning and policy iteration algorithms for stochastic shortest path problems","publication_year":2012,"publication_date":"2012-04-17","ids":{"openalex":"https://openalex.org/W2027855416","doi":"https://doi.org/10.1007/s10479-012-1128-z","mag":"2027855416"},"language":"en","primary_location":{"id":"doi:10.1007/s10479-012-1128-z","is_oa":false,"landing_page_url":"https://doi.org/10.1007/s10479-012-1128-z","pdf_url":null,"source":{"id":"https://openalex.org/S57667410","display_name":"Annals of Operations Research","issn_l":"0254-5330","issn":["0254-5330","1572-9338"],"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":"Annals of Operations Research","raw_type":"journal-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"http://hdl.handle.net/1721.1/93745","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5014937312","display_name":"Huizhen Yu","orcid":"https://orcid.org/0000-0002-3673-0094"},"institutions":[{"id":"https://openalex.org/I4210143601","display_name":"Decision Systems (United States)","ror":"https://ror.org/0434dpa13","country_code":"US","type":"company","lineage":["https://openalex.org/I4210143601"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Huizhen Yu","raw_affiliation_strings":["Lab. for Information and Decision Systems, MIT, Cambridge, MA, 02139, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Lab. for Information and Decision Systems, MIT, Cambridge, MA, 02139, USA","institution_ids":["https://openalex.org/I4210143601"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5039911471","display_name":"Dimitri P. Bertsekas","orcid":"https://orcid.org/0000-0001-6909-7208"},"institutions":[{"id":"https://openalex.org/I4210143601","display_name":"Decision Systems (United States)","ror":"https://ror.org/0434dpa13","country_code":"US","type":"company","lineage":["https://openalex.org/I4210143601"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Dimitri P. Bertsekas","raw_affiliation_strings":["Lab. for Information and Decision Systems, MIT, Cambridge, MA, 02139, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Lab. for Information and Decision Systems, MIT, Cambridge, MA, 02139, USA","institution_ids":["https://openalex.org/I4210143601"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I4210143601"],"apc_list":{"value":2390,"currency":"EUR","value_usd":2990},"apc_paid":null,"fwci":3.3546,"has_fulltext":false,"cited_by_count":41,"citation_normalized_percentile":{"value":0.92525697,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":90,"max":98},"biblio":{"volume":"208","issue":"1","first_page":"95","last_page":"132"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T12288","display_name":"Optimization and Search Problems","score":0.9740999937057495,"subfield":{"id":"https://openalex.org/subfields/1705","display_name":"Computer Networks and Communications"},"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/T12288","display_name":"Optimization and Search Problems","score":0.9740999937057495,"subfield":{"id":"https://openalex.org/subfields/1705","display_name":"Computer Networks and Communications"},"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/T13553","display_name":"Age of Information Optimization","score":0.9721999764442444,"subfield":{"id":"https://openalex.org/subfields/1705","display_name":"Computer Networks and Communications"},"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/T10974","display_name":"Advanced Queuing Theory Analysis","score":0.9718000292778015,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/markov-decision-process","display_name":"Markov decision process","score":0.7283231616020203},{"id":"https://openalex.org/keywords/shortest-path-problem","display_name":"Shortest path problem","score":0.6087042093276978},{"id":"https://openalex.org/keywords/q-learning","display_name":"Q-learning","score":0.5698886513710022},{"id":"https://openalex.org/keywords/theory-of-computation","display_name":"Theory of computation","score":0.5061883330345154},{"id":"https://openalex.org/keywords/asynchronous-communication","display_name":"Asynchronous communication","score":0.5004944801330566},{"id":"https://openalex.org/keywords/mathematical-optimization","display_name":"Mathematical optimization","score":0.4934810400009155},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.48793575167655945},{"id":"https://openalex.org/keywords/convergence","display_name":"Convergence (economics)","score":0.4598032534122467},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.4540402293205261},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.449001669883728},{"id":"https://openalex.org/keywords/stochastic-approximation","display_name":"Stochastic approximation","score":0.41862428188323975},{"id":"https://openalex.org/keywords/bellman-equation","display_name":"Bellman equation","score":0.4181933104991913},{"id":"https://openalex.org/keywords/reinforcement-learning","display_name":"Reinforcement learning","score":0.3275933265686035},{"id":"https://openalex.org/keywords/markov-process","display_name":"Markov process","score":0.21638032793998718},{"id":"https://openalex.org/keywords/discrete-mathematics","display_name":"Discrete mathematics","score":0.13511443138122559},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.08578947186470032},{"id":"https://openalex.org/keywords/graph","display_name":"Graph","score":0.08110833168029785}],"concepts":[{"id":"https://openalex.org/C106189395","wikidata":"https://www.wikidata.org/wiki/Q176789","display_name":"Markov decision process","level":3,"score":0.7283231616020203},{"id":"https://openalex.org/C22590252","wikidata":"https://www.wikidata.org/wiki/Q1058754","display_name":"Shortest path problem","level":3,"score":0.6087042093276978},{"id":"https://openalex.org/C188116033","wikidata":"https://www.wikidata.org/wiki/Q2664563","display_name":"Q-learning","level":3,"score":0.5698886513710022},{"id":"https://openalex.org/C24858836","wikidata":"https://www.wikidata.org/wiki/Q844718","display_name":"Theory of computation","level":2,"score":0.5061883330345154},{"id":"https://openalex.org/C151319957","wikidata":"https://www.wikidata.org/wiki/Q752739","display_name":"Asynchronous communication","level":2,"score":0.5004944801330566},{"id":"https://openalex.org/C126255220","wikidata":"https://www.wikidata.org/wiki/Q141495","display_name":"Mathematical optimization","level":1,"score":0.4934810400009155},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.48793575167655945},{"id":"https://openalex.org/C2777303404","wikidata":"https://www.wikidata.org/wiki/Q759757","display_name":"Convergence (economics)","level":2,"score":0.4598032534122467},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.4540402293205261},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.449001669883728},{"id":"https://openalex.org/C55479107","wikidata":"https://www.wikidata.org/wiki/Q97663916","display_name":"Stochastic approximation","level":3,"score":0.41862428188323975},{"id":"https://openalex.org/C14646407","wikidata":"https://www.wikidata.org/wiki/Q1430750","display_name":"Bellman equation","level":2,"score":0.4181933104991913},{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.3275933265686035},{"id":"https://openalex.org/C159886148","wikidata":"https://www.wikidata.org/wiki/Q176645","display_name":"Markov process","level":2,"score":0.21638032793998718},{"id":"https://openalex.org/C118615104","wikidata":"https://www.wikidata.org/wiki/Q121416","display_name":"Discrete mathematics","level":1,"score":0.13511443138122559},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.08578947186470032},{"id":"https://openalex.org/C132525143","wikidata":"https://www.wikidata.org/wiki/Q141488","display_name":"Graph","level":2,"score":0.08110833168029785},{"id":"https://openalex.org/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","level":0,"score":0.0},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.0},{"id":"https://openalex.org/C31258907","wikidata":"https://www.wikidata.org/wiki/Q1301371","display_name":"Computer network","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}],"mesh":[],"locations_count":6,"locations":[{"id":"doi:10.1007/s10479-012-1128-z","is_oa":false,"landing_page_url":"https://doi.org/10.1007/s10479-012-1128-z","pdf_url":null,"source":{"id":"https://openalex.org/S57667410","display_name":"Annals of Operations Research","issn_l":"0254-5330","issn":["0254-5330","1572-9338"],"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":"Annals of Operations Research","raw_type":"journal-article"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.228.8129","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.228.8129","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://www.mit.edu/people/dimitrib/qlearning_ssp_YB.pdf","raw_type":"text"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.294.8442","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.294.8442","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://web.mit.edu/dimitrib/www/qlearning_ssp_YB.pdf","raw_type":"text"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.690.1518","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.690.1518","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://dspace.mit.edu/bitstream/handle/1721.1/93745/YU+qlearning_ssp_YB+%282%29.pdf?sequence%3D1","raw_type":"text"},{"id":"pmh:oai:RePEc:spr:annopr:v:208:y:2013:i:1:p:95-132:10.1007/s10479-012-1128-z","is_oa":false,"landing_page_url":"http://hdl.handle.net/10.1007/s10479-012-1128-z","pdf_url":null,"source":{"id":"https://openalex.org/S4306401271","display_name":"RePEc: Research Papers in Economics","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I77793887","host_organization_name":"Federal Reserve Bank of St. Louis","host_organization_lineage":["https://openalex.org/I77793887"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"article"},{"id":"pmh:oai:dspace.mit.edu:1721.1/93745","is_oa":true,"landing_page_url":"http://hdl.handle.net/1721.1/93745","pdf_url":null,"source":{"id":"https://openalex.org/S4306400425","display_name":"DSpace@MIT (Massachusetts Institute of Technology)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I63966007","host_organization_name":"Massachusetts Institute of Technology","host_organization_lineage":["https://openalex.org/I63966007"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by-nc-sa","license_id":"https://openalex.org/licenses/cc-by-nc-sa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Prof. Bertsekas via Chris Sherratt","raw_type":"http://purl.org/eprint/type/JournalArticle"}],"best_oa_location":{"id":"pmh:oai:dspace.mit.edu:1721.1/93745","is_oa":true,"landing_page_url":"http://hdl.handle.net/1721.1/93745","pdf_url":null,"source":{"id":"https://openalex.org/S4306400425","display_name":"DSpace@MIT (Massachusetts Institute of Technology)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I63966007","host_organization_name":"Massachusetts Institute of Technology","host_organization_lineage":["https://openalex.org/I63966007"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by-nc-sa","license_id":"https://openalex.org/licenses/cc-by-nc-sa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Prof. Bertsekas via Chris Sherratt","raw_type":"http://purl.org/eprint/type/JournalArticle"},"sustainable_development_goals":[{"score":0.7799999713897705,"display_name":"Peace, Justice and strong institutions","id":"https://metadata.un.org/sdg/16"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":50,"referenced_works":["https://openalex.org/W624875331","https://openalex.org/W798021849","https://openalex.org/W1547105496","https://openalex.org/W1576452626","https://openalex.org/W1579026795","https://openalex.org/W1603765807","https://openalex.org/W1607065182","https://openalex.org/W1826343992","https://openalex.org/W1978564754","https://openalex.org/W1980994346","https://openalex.org/W2001015965","https://openalex.org/W2014981566","https://openalex.org/W2019172585","https://openalex.org/W2023782756","https://openalex.org/W2062541405","https://openalex.org/W2080631849","https://openalex.org/W2081287319","https://openalex.org/W2089933214","https://openalex.org/W2098432798","https://openalex.org/W2104335146","https://openalex.org/W2119380668","https://openalex.org/W2119567691","https://openalex.org/W2122945138","https://openalex.org/W2147750403","https://openalex.org/W2148864095","https://openalex.org/W2155143729","https://openalex.org/W2156168464","https://openalex.org/W2158278868","https://openalex.org/W2160067530","https://openalex.org/W2161950876","https://openalex.org/W2165131254","https://openalex.org/W2167509584","https://openalex.org/W2169982856","https://openalex.org/W2312609093","https://openalex.org/W2334782222","https://openalex.org/W2486403688","https://openalex.org/W2487144912","https://openalex.org/W2612868016","https://openalex.org/W2625910744","https://openalex.org/W2911283634","https://openalex.org/W2914656440","https://openalex.org/W3011120880","https://openalex.org/W4212774754","https://openalex.org/W4285719527","https://openalex.org/W4307347247","https://openalex.org/W6634483419","https://openalex.org/W6634528131","https://openalex.org/W6689723076","https://openalex.org/W6775686901","https://openalex.org/W7039022430"],"related_works":["https://openalex.org/W2152670157","https://openalex.org/W2101748387","https://openalex.org/W4308702637","https://openalex.org/W2386410636","https://openalex.org/W176737593","https://openalex.org/W2808418668","https://openalex.org/W2903299703","https://openalex.org/W2016648086","https://openalex.org/W2156021013","https://openalex.org/W1574958246"],"abstract_inverted_index":null,"counts_by_year":[{"year":2024,"cited_by_count":2},{"year":2023,"cited_by_count":1},{"year":2022,"cited_by_count":5},{"year":2021,"cited_by_count":6},{"year":2020,"cited_by_count":4},{"year":2019,"cited_by_count":3},{"year":2018,"cited_by_count":3},{"year":2017,"cited_by_count":2},{"year":2016,"cited_by_count":5},{"year":2015,"cited_by_count":2},{"year":2014,"cited_by_count":1},{"year":2013,"cited_by_count":1},{"year":2012,"cited_by_count":5}],"updated_date":"2026-06-26T08:34:08.712188","created_date":"2025-10-10T00:00:00"}