{"id":"https://openalex.org/W1968823695","doi":"https://doi.org/10.1109/cdc.2014.7039533","title":"A Hessian actor-critic algorithm","display_name":"A Hessian actor-critic algorithm","publication_year":2014,"publication_date":"2014-12-01","ids":{"openalex":"https://openalex.org/W1968823695","doi":"https://doi.org/10.1109/cdc.2014.7039533","mag":"1968823695"},"language":"en","primary_location":{"id":"doi:10.1109/cdc.2014.7039533","is_oa":false,"landing_page_url":"https://doi.org/10.1109/cdc.2014.7039533","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"53rd IEEE Conference on Decision and Control","raw_type":"proceedings-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/A5100378632","display_name":"Jing Wang","orcid":"https://orcid.org/0000-0003-0182-0353"},"institutions":[{"id":"https://openalex.org/I111088046","display_name":"Boston University","ror":"https://ror.org/05qwgg493","country_code":"US","type":"education","lineage":["https://openalex.org/I111088046"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Jing Wang","raw_affiliation_strings":["t Division of Systems Engineering, Boston University","Division of Systems Eng., Boston University, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"t Division of Systems Engineering, Boston University","institution_ids":["https://openalex.org/I111088046"]},{"raw_affiliation_string":"Division of Systems Eng., Boston University, USA","institution_ids":["https://openalex.org/I111088046"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5075696701","display_name":"Ioannis Ch. Paschalidis","orcid":"https://orcid.org/0000-0002-3343-2913"},"institutions":[{"id":"https://openalex.org/I111088046","display_name":"Boston University","ror":"https://ror.org/05qwgg493","country_code":"US","type":"education","lineage":["https://openalex.org/I111088046"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Ioannis Ch. Paschalidis","raw_affiliation_strings":["Department of Electrical and Computer Engineering and Division of Systems Engineering, Boston University, 8 St. Mary's St., MA, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Electrical and Computer Engineering and Division of Systems Engineering, Boston University, 8 St. Mary's St., MA, USA","institution_ids":["https://openalex.org/I111088046"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.4229,"has_fulltext":false,"cited_by_count":1,"citation_normalized_percentile":{"value":0.73248734,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":94},"biblio":{"volume":"13","issue":null,"first_page":"1131","last_page":"1136"},"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/T12101","display_name":"Advanced Bandit Algorithms Research","score":0.9970999956130981,"subfield":{"id":"https://openalex.org/subfields/1803","display_name":"Management Science and Operations Research"},"field":{"id":"https://openalex.org/fields/18","display_name":"Decision Sciences"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}},{"id":"https://openalex.org/T12288","display_name":"Optimization and Search Problems","score":0.9894000291824341,"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/parameterized-complexity","display_name":"Parameterized complexity","score":0.8263112306594849},{"id":"https://openalex.org/keywords/hessian-matrix","display_name":"Hessian matrix","score":0.8259426355361938},{"id":"https://openalex.org/keywords/convergence","display_name":"Convergence (economics)","score":0.73143470287323},{"id":"https://openalex.org/keywords/markov-decision-process","display_name":"Markov decision process","score":0.7043057680130005},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.674020528793335},{"id":"https://openalex.org/keywords/set","display_name":"Set (abstract data type)","score":0.604597270488739},{"id":"https://openalex.org/keywords/mathematical-optimization","display_name":"Mathematical optimization","score":0.5851590037345886},{"id":"https://openalex.org/keywords/gradient-descent","display_name":"Gradient descent","score":0.571496844291687},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.5051811337471008},{"id":"https://openalex.org/keywords/robotics","display_name":"Robotics","score":0.4921247363090515},{"id":"https://openalex.org/keywords/decision-maker","display_name":"Decision maker","score":0.48976755142211914},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.42555510997772217},{"id":"https://openalex.org/keywords/robot","display_name":"Robot","score":0.32066839933395386},{"id":"https://openalex.org/keywords/markov-process","display_name":"Markov process","score":0.316877543926239},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.2593523859977722},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.17639264464378357},{"id":"https://openalex.org/keywords/applied-mathematics","display_name":"Applied mathematics","score":0.09998342394828796},{"id":"https://openalex.org/keywords/operations-research","display_name":"Operations research","score":0.09411531686782837}],"concepts":[{"id":"https://openalex.org/C165464430","wikidata":"https://www.wikidata.org/wiki/Q1570441","display_name":"Parameterized complexity","level":2,"score":0.8263112306594849},{"id":"https://openalex.org/C203616005","wikidata":"https://www.wikidata.org/wiki/Q620495","display_name":"Hessian matrix","level":2,"score":0.8259426355361938},{"id":"https://openalex.org/C2777303404","wikidata":"https://www.wikidata.org/wiki/Q759757","display_name":"Convergence (economics)","level":2,"score":0.73143470287323},{"id":"https://openalex.org/C106189395","wikidata":"https://www.wikidata.org/wiki/Q176789","display_name":"Markov decision process","level":3,"score":0.7043057680130005},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.674020528793335},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.604597270488739},{"id":"https://openalex.org/C126255220","wikidata":"https://www.wikidata.org/wiki/Q141495","display_name":"Mathematical optimization","level":1,"score":0.5851590037345886},{"id":"https://openalex.org/C153258448","wikidata":"https://www.wikidata.org/wiki/Q1199743","display_name":"Gradient descent","level":3,"score":0.571496844291687},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.5051811337471008},{"id":"https://openalex.org/C34413123","wikidata":"https://www.wikidata.org/wiki/Q170978","display_name":"Robotics","level":3,"score":0.4921247363090515},{"id":"https://openalex.org/C2986080485","wikidata":"https://www.wikidata.org/wiki/Q1331926","display_name":"Decision maker","level":2,"score":0.48976755142211914},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.42555510997772217},{"id":"https://openalex.org/C90509273","wikidata":"https://www.wikidata.org/wiki/Q11012","display_name":"Robot","level":2,"score":0.32066839933395386},{"id":"https://openalex.org/C159886148","wikidata":"https://www.wikidata.org/wiki/Q176645","display_name":"Markov process","level":2,"score":0.316877543926239},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.2593523859977722},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.17639264464378357},{"id":"https://openalex.org/C28826006","wikidata":"https://www.wikidata.org/wiki/Q33521","display_name":"Applied mathematics","level":1,"score":0.09998342394828796},{"id":"https://openalex.org/C42475967","wikidata":"https://www.wikidata.org/wiki/Q194292","display_name":"Operations research","level":1,"score":0.09411531686782837},{"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/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","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":1,"locations":[{"id":"doi:10.1109/cdc.2014.7039533","is_oa":false,"landing_page_url":"https://doi.org/10.1109/cdc.2014.7039533","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"53rd IEEE Conference on Decision and Control","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.7699999809265137,"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":43,"referenced_works":["https://openalex.org/W1507222174","https://openalex.org/W1518539242","https://openalex.org/W1576452626","https://openalex.org/W1597303641","https://openalex.org/W1606011487","https://openalex.org/W1964782533","https://openalex.org/W1970789124","https://openalex.org/W1979464096","https://openalex.org/W1995713768","https://openalex.org/W2009303086","https://openalex.org/W2016990484","https://openalex.org/W2049553644","https://openalex.org/W2070619758","https://openalex.org/W2072931156","https://openalex.org/W2098432798","https://openalex.org/W2101950184","https://openalex.org/W2102988084","https://openalex.org/W2103451687","https://openalex.org/W2120465407","https://openalex.org/W2121863487","https://openalex.org/W2125176858","https://openalex.org/W2127107099","https://openalex.org/W2130801532","https://openalex.org/W2136602922","https://openalex.org/W2143490508","https://openalex.org/W2144446635","https://openalex.org/W2155938881","https://openalex.org/W2159871982","https://openalex.org/W2165418472","https://openalex.org/W2171033527","https://openalex.org/W2172968643","https://openalex.org/W2182995676","https://openalex.org/W2236623899","https://openalex.org/W2797925981","https://openalex.org/W3103182070","https://openalex.org/W4205326910","https://openalex.org/W4214717370","https://openalex.org/W4242209908","https://openalex.org/W4302617909","https://openalex.org/W6635767209","https://openalex.org/W6675256285","https://openalex.org/W6679257226","https://openalex.org/W6680194329"],"related_works":["https://openalex.org/W2051058708","https://openalex.org/W154868527","https://openalex.org/W4283017538","https://openalex.org/W1494268238","https://openalex.org/W1545275724","https://openalex.org/W2049472152","https://openalex.org/W2355987247","https://openalex.org/W1974307281","https://openalex.org/W4297883503","https://openalex.org/W1989888202"],"abstract_inverted_index":{"We":[0,102],"consider":[1],"Markov":[2],"Decision":[3],"Processes":[4],"(MDPs)":[5],"following":[6],"a":[7,11,33,64,94,112],"policy":[8,21,42],"parametrized":[9],"by":[10],"parsimonious":[12],"set":[13],"of":[14,79,98],"parameters":[15],"and":[16,115],"seek":[17],"to":[18],"optimize":[19],"the":[20,40,46,60,77,80,83,99,104],"over":[22],"these":[23],"parameters.":[24],"In":[25,68],"this":[26,69,89],"setting,":[27],"optimization":[28],"can":[29,43],"be":[30],"done":[31],"using":[32],"gradient":[34,61],"ascent":[35,66],"method.":[36],"If":[37],"designed":[38],"well,":[39],"parameterized":[41],"significantly":[44],"reduce":[45],"problem":[47],"complexity.":[48],"Existing":[49],"algorithms":[50,110],"usually":[51],"suffer":[52],"from":[53],"slow":[54],"convergence":[55],"because":[56],"they":[57],"search":[58],"along":[59],"direction":[62],"in":[63,111],"steepest":[65],"way.":[67],"paper,":[70],"we":[71,91],"first":[72],"propose":[73],"an":[74],"estimate":[75],"for":[76],"Hessian":[78],"overall":[81],"reward":[82],"decision":[84],"maker":[85],"receives.":[86],"Based":[87],"on":[88],"estimate,":[90],"then":[92],"introduce":[93],"new":[95,105],"Newton-like":[96],"method":[97,119],"actor-critic":[100],"type.":[101],"compare":[103],"algorithm":[106],"with":[107],"several":[108],"existing":[109],"robotics":[113],"application":[114],"demonstrate":[116],"that":[117],"our":[118],"exhibits":[120],"faster":[121],"convergence.":[122]},"counts_by_year":[{"year":2016,"cited_by_count":1}],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2025-10-10T00:00:00"}