{"id":"https://openalex.org/W1554366315","doi":"https://doi.org/10.1023/a:1022145020786","title":"Approximate Gradient Methods in Policy-Space Optimization of Markov Reward Processes","display_name":"Approximate Gradient Methods in Policy-Space Optimization of Markov Reward Processes","publication_year":2003,"publication_date":"2003-01-01","ids":{"openalex":"https://openalex.org/W1554366315","doi":"https://doi.org/10.1023/a:1022145020786","mag":"1554366315"},"language":"en","primary_location":{"id":"doi:10.1023/a:1022145020786","is_oa":false,"landing_page_url":"https://doi.org/10.1023/a:1022145020786","pdf_url":null,"source":{"id":"https://openalex.org/S134484881","display_name":"Discrete Event Dynamic Systems","issn_l":"0924-6703","issn":["0924-6703","1573-7594"],"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":"Discrete Event Dynamic Systems","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/A5012311701","display_name":"Peter Marbach","orcid":"https://orcid.org/0009-0005-4781-6845"},"institutions":[{"id":"https://openalex.org/I185261750","display_name":"University of Toronto","ror":"https://ror.org/03dbr7087","country_code":"CA","type":"education","lineage":["https://openalex.org/I185261750"]}],"countries":["CA"],"is_corresponding":true,"raw_author_name":"Peter Marbach","raw_affiliation_strings":["Department of Computer Science, University of Toronto, Toronto, ON, M5S 3H4, Canada","Department of Computer Science, University of Toronto, Toronto, ON, M5S 3H4 marbach@cs.toronto.edu#TAB#"],"affiliations":[{"raw_affiliation_string":"Department of Computer Science, University of Toronto, Toronto, ON, M5S 3H4, Canada","institution_ids":["https://openalex.org/I185261750"]},{"raw_affiliation_string":"Department of Computer Science, University of Toronto, Toronto, ON, M5S 3H4 marbach@cs.toronto.edu#TAB#","institution_ids":["https://openalex.org/I185261750"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5108523422","display_name":"John N. Tsitsiklis","orcid":null},"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"]},{"id":"https://openalex.org/I63966007","display_name":"Massachusetts Institute of Technology","ror":"https://ror.org/042nb2s44","country_code":"US","type":"education","lineage":["https://openalex.org/I63966007"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"John N. Tsitsiklis","raw_affiliation_strings":["Laboratory for Information and Decision Systems, Massachusetts Institute of Technology, Cambridge, MA, 02139, USA","Laboratory for Information and Decision Systems, Massachusetts Institute of Technology, Cambridge, MA 02139 [email\u00a0protected] #TAB#"],"affiliations":[{"raw_affiliation_string":"Laboratory for Information and Decision Systems, Massachusetts Institute of Technology, Cambridge, MA, 02139, USA","institution_ids":["https://openalex.org/I4210143601","https://openalex.org/I63966007"]},{"raw_affiliation_string":"Laboratory for Information and Decision Systems, Massachusetts Institute of Technology, Cambridge, MA 02139 [email\u00a0protected] #TAB#","institution_ids":["https://openalex.org/I63966007"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5012311701"],"corresponding_institution_ids":["https://openalex.org/I185261750"],"apc_list":{"value":2390,"currency":"EUR","value_usd":2990},"apc_paid":null,"fwci":5.1894,"has_fulltext":false,"cited_by_count":52,"citation_normalized_percentile":{"value":0.95250332,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":89,"max":97},"biblio":{"volume":"13","issue":"1-2","first_page":"111","last_page":"148"},"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/T12056","display_name":"Markov Chains and Monte Carlo Methods","score":0.9991999864578247,"subfield":{"id":"https://openalex.org/subfields/2613","display_name":"Statistics and Probability"},"field":{"id":"https://openalex.org/fields/26","display_name":"Mathematics"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T12288","display_name":"Optimization and Search Problems","score":0.9991000294685364,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/convergence","display_name":"Convergence (economics)","score":0.6157026886940002},{"id":"https://openalex.org/keywords/variance","display_name":"Variance (accounting)","score":0.5957688689231873},{"id":"https://openalex.org/keywords/markov-chain","display_name":"Markov chain","score":0.5393881797790527},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.49941277503967285},{"id":"https://openalex.org/keywords/markov-process","display_name":"Markov process","score":0.481145977973938},{"id":"https://openalex.org/keywords/gradient-descent","display_name":"Gradient descent","score":0.4807048439979553},{"id":"https://openalex.org/keywords/path","display_name":"Path (computing)","score":0.46748846769332886},{"id":"https://openalex.org/keywords/set","display_name":"Set (abstract data type)","score":0.4603009819984436},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.4510481059551239},{"id":"https://openalex.org/keywords/process","display_name":"Process (computing)","score":0.445298433303833},{"id":"https://openalex.org/keywords/mathematical-optimization","display_name":"Mathematical optimization","score":0.44028806686401367},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.3488398790359497},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.12758147716522217},{"id":"https://openalex.org/keywords/statistics","display_name":"Statistics","score":0.12308856844902039},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.0879158079624176}],"concepts":[{"id":"https://openalex.org/C2777303404","wikidata":"https://www.wikidata.org/wiki/Q759757","display_name":"Convergence (economics)","level":2,"score":0.6157026886940002},{"id":"https://openalex.org/C196083921","wikidata":"https://www.wikidata.org/wiki/Q7915758","display_name":"Variance (accounting)","level":2,"score":0.5957688689231873},{"id":"https://openalex.org/C98763669","wikidata":"https://www.wikidata.org/wiki/Q176645","display_name":"Markov chain","level":2,"score":0.5393881797790527},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.49941277503967285},{"id":"https://openalex.org/C159886148","wikidata":"https://www.wikidata.org/wiki/Q176645","display_name":"Markov process","level":2,"score":0.481145977973938},{"id":"https://openalex.org/C153258448","wikidata":"https://www.wikidata.org/wiki/Q1199743","display_name":"Gradient descent","level":3,"score":0.4807048439979553},{"id":"https://openalex.org/C2777735758","wikidata":"https://www.wikidata.org/wiki/Q817765","display_name":"Path (computing)","level":2,"score":0.46748846769332886},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.4603009819984436},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.4510481059551239},{"id":"https://openalex.org/C98045186","wikidata":"https://www.wikidata.org/wiki/Q205663","display_name":"Process (computing)","level":2,"score":0.445298433303833},{"id":"https://openalex.org/C126255220","wikidata":"https://www.wikidata.org/wiki/Q141495","display_name":"Mathematical optimization","level":1,"score":0.44028806686401367},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.3488398790359497},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.12758147716522217},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.12308856844902039},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.0879158079624176},{"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/C144133560","wikidata":"https://www.wikidata.org/wiki/Q4830453","display_name":"Business","level":0,"score":0.0},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.0},{"id":"https://openalex.org/C121955636","wikidata":"https://www.wikidata.org/wiki/Q4116214","display_name":"Accounting","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/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1023/a:1022145020786","is_oa":false,"landing_page_url":"https://doi.org/10.1023/a:1022145020786","pdf_url":null,"source":{"id":"https://openalex.org/S134484881","display_name":"Discrete Event Dynamic Systems","issn_l":"0924-6703","issn":["0924-6703","1573-7594"],"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":"Discrete Event Dynamic Systems","raw_type":"journal-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":23,"referenced_works":["https://openalex.org/W1516403053","https://openalex.org/W1523765121","https://openalex.org/W1544193923","https://openalex.org/W1602007439","https://openalex.org/W1970602736","https://openalex.org/W2006036383","https://openalex.org/W2021231433","https://openalex.org/W2047154179","https://openalex.org/W2050882265","https://openalex.org/W2091694970","https://openalex.org/W2098432798","https://openalex.org/W2119717200","https://openalex.org/W2120465407","https://openalex.org/W2159871982","https://openalex.org/W2160067530","https://openalex.org/W2170009401","https://openalex.org/W2171033527","https://openalex.org/W2503725246","https://openalex.org/W2539369127","https://openalex.org/W2798766386","https://openalex.org/W4241811150","https://openalex.org/W6663113359","https://openalex.org/W6750230808"],"related_works":["https://openalex.org/W1660242800","https://openalex.org/W2077211377","https://openalex.org/W3152686072","https://openalex.org/W1006270037","https://openalex.org/W3129238073","https://openalex.org/W2379651310","https://openalex.org/W2113019827","https://openalex.org/W1541249122","https://openalex.org/W2413828414","https://openalex.org/W2367222340"],"abstract_inverted_index":null,"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2022,"cited_by_count":1},{"year":2021,"cited_by_count":2},{"year":2020,"cited_by_count":4},{"year":2019,"cited_by_count":2},{"year":2018,"cited_by_count":1},{"year":2017,"cited_by_count":1},{"year":2016,"cited_by_count":2},{"year":2015,"cited_by_count":2},{"year":2014,"cited_by_count":1},{"year":2013,"cited_by_count":3},{"year":2012,"cited_by_count":2}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2016-06-24T00:00:00"}