{"id":"https://openalex.org/W2103451687","doi":"https://doi.org/10.1109/cdc.2009.5400592","title":"An actor-critic method using Least Squares Temporal Difference learning","display_name":"An actor-critic method using Least Squares Temporal Difference learning","publication_year":2009,"publication_date":"2009-12-01","ids":{"openalex":"https://openalex.org/W2103451687","doi":"https://doi.org/10.1109/cdc.2009.5400592","mag":"2103451687"},"language":"en","primary_location":{"id":"doi:10.1109/cdc.2009.5400592","doi":"https://doi.org/10.1109/cdc.2009.5400592","is_oa":false,"landing_page_url":"https://doi.org/10.1109/cdc.2009.5400592","pdf_url":null,"source":{"id":"https://openalex.org/S4210221977","display_name":"IEEE Conference on Decision and Control (CDC)","issn_l":"0191-2216","issn":["0191-2216"],"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 48h IEEE Conference on Decision and Control (CDC) held jointly with 2009 28th Chinese Control Conference","raw_type":"proceedings-article"},"volume":null,"type":"conference-paper","is_traditional":true,"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/A5075696701","display_name":"Ioannis Ch. Paschalidis","orcid":"https://orcid.org/0000-0002-3343-2913","observed_orcids":["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":["Center for Information & Systems Engineering, Department of Electrical and Computer Engineering and Division of Systems Engineering, Boston University, Brookline, MA, USA","Center for Information & Systems Eng., Dept. of Electrical & Computer Eng., and Division of Systems Eng., Boston University, 15 St. Mary's St., Brookline, MA 02446, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Center for Information & Systems Engineering, Department of Electrical and Computer Engineering and Division of Systems Engineering, Boston University, Brookline, MA, USA","institution_ids":["https://openalex.org/I111088046"]},{"raw_affiliation_string":"Center for Information & Systems Eng., Dept. of Electrical & Computer Eng., and Division of Systems Eng., Boston University, 15 St. Mary's St., Brookline, MA 02446, USA","institution_ids":["https://openalex.org/I111088046"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5082728073","display_name":"K. Li","orcid":null,"observed_orcids":[]},"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":"Keyong Li","raw_affiliation_strings":["Center for Information & Systems Engineering, Boston University, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Center for Information & Systems Engineering, Boston University, USA","institution_ids":["https://openalex.org/I111088046"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5041751346","display_name":"Reza Moazzez Estanjini","orcid":null,"observed_orcids":[]},"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":"Reza Moazzez Estanjini","raw_affiliation_strings":["Center for Information & Systems Engineering, Boston University, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Center for Information & Systems Engineering, Boston University, USA","institution_ids":["https://openalex.org/I111088046"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I111088046"],"apc_list":null,"apc_paid":null,"fwci":1.2471,"has_fulltext":false,"cited_by_count":12,"citation_normalized_percentile":{"value":0.77051072,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":87,"max":95},"biblio":{"volume":null,"issue":null,"first_page":"2564","last_page":"2569"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10462","display_name":"Reinforcement Learning in Robotics","score":0.9365000128746033,"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":0.9365000128746033,"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/T12794","display_name":"Adaptive Dynamic Programming Control","score":0.0625,"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"}},{"id":"https://openalex.org/T11195","display_name":"Simulation Techniques and Applications","score":0.00019999999494757503,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/actor-critic","display_name":"actor-critic","score":0.722000002861023},{"id":"https://openalex.org/keywords/convergence-analysis","display_name":"convergence analysis","score":0.7289999723434448},{"id":"https://openalex.org/keywords/policy-gradient","display_name":"policy gradient","score":0.43700000643730164},{"id":"https://openalex.org/keywords/td-lambda","display_name":"TD(lambda)","score":0.5600000023841858},{"id":"https://openalex.org/keywords/warehouse-automation","display_name":"warehouse automation","score":0.6579999923706055},{"id":"https://openalex.org/keywords/reinforcement-learning","display_name":"reinforcement learning","score":0.7459999918937683}],"concepts":[{"id":"https://openalex.org/C196340769","wikidata":"https://www.wikidata.org/wiki/Q7698910","display_name":"Temporal difference learning","level":3,"score":0.8795239925384521},{"id":"https://openalex.org/C2777303404","wikidata":"https://www.wikidata.org/wiki/Q759757","display_name":"Convergence (economics)","level":2,"score":0.6903974413871765},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6621155738830566},{"id":"https://openalex.org/C14646407","wikidata":"https://www.wikidata.org/wiki/Q1430750","display_name":"Bellman equation","level":2,"score":0.579942524433136},{"id":"https://openalex.org/C98045186","wikidata":"https://www.wikidata.org/wiki/Q205663","display_name":"Process (computing)","level":2,"score":0.5670415163040161},{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.5438199639320374},{"id":"https://openalex.org/C126255220","wikidata":"https://www.wikidata.org/wiki/Q141495","display_name":"Mathematical optimization","level":1,"score":0.5392154455184937},{"id":"https://openalex.org/C198531522","wikidata":"https://www.wikidata.org/wiki/Q485146","display_name":"Sample (material)","level":2,"score":0.5091585516929626},{"id":"https://openalex.org/C2777735758","wikidata":"https://www.wikidata.org/wiki/Q817765","display_name":"Path (computing)","level":2,"score":0.48884767293930054},{"id":"https://openalex.org/C14036430","wikidata":"https://www.wikidata.org/wiki/Q3736076","display_name":"Function (biology)","level":2,"score":0.47627514600753784},{"id":"https://openalex.org/C182306322","wikidata":"https://www.wikidata.org/wiki/Q1779371","display_name":"Order (exchange)","level":2,"score":0.4101085066795349},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.40763136744499207},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.24505853652954102},{"id":"https://openalex.org/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","level":0,"score":0.0859815776348114},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.0},{"id":"https://openalex.org/C43617362","wikidata":"https://www.wikidata.org/wiki/Q170050","display_name":"Chromatography","level":1,"score":0.0},{"id":"https://openalex.org/C78458016","wikidata":"https://www.wikidata.org/wiki/Q840400","display_name":"Evolutionary biology","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/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","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},{"id":"https://openalex.org/C10138342","wikidata":"https://www.wikidata.org/wiki/Q43015","display_name":"Finance","level":1,"score":0.0},{"id":"https://openalex.org/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/cdc.2009.5400592","doi":"https://doi.org/10.1109/cdc.2009.5400592","is_oa":false,"landing_page_url":"https://doi.org/10.1109/cdc.2009.5400592","pdf_url":null,"source":{"id":"https://openalex.org/S4210221977","display_name":"IEEE Conference on Decision and Control (CDC)","issn_l":"0191-2216","issn":["0191-2216"],"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 48h IEEE Conference on Decision and Control (CDC) held jointly with 2009 28th Chinese Control Conference","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"study_designs":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":24,"referenced_works":["https://openalex.org/W1507222174","https://openalex.org/W1518539242","https://openalex.org/W1576452626","https://openalex.org/W1583833196","https://openalex.org/W1597303641","https://openalex.org/W1622701847","https://openalex.org/W1854776945","https://openalex.org/W2009303086","https://openalex.org/W2070570138","https://openalex.org/W2072931156","https://openalex.org/W2100857832","https://openalex.org/W2108772579","https://openalex.org/W2121863487","https://openalex.org/W2136602922","https://openalex.org/W2148888643","https://openalex.org/W2156737235","https://openalex.org/W2164569010","https://openalex.org/W2165418472","https://openalex.org/W2172968643","https://openalex.org/W2415292238","https://openalex.org/W4214717370","https://openalex.org/W4307347247","https://openalex.org/W6604969303","https://openalex.org/W6634528131"],"related_works":["https://openalex.org/W2772929266","https://openalex.org/W1964782533","https://openalex.org/W1420406291","https://openalex.org/W1597303641","https://openalex.org/W7098517347","https://openalex.org/W4327544661","https://openalex.org/W86816279","https://openalex.org/W1759430956","https://openalex.org/W7098025415","https://openalex.org/W4221162264"],"abstract_inverted_index":{"In":[0],"this":[1],"paper,":[2],"we":[3,111],"use":[4],"a":[5,36,58,101,124],"Least":[6],"Squares":[7],"Temporal":[8],"Difference":[9],"(LSTD)":[10],"algorithm":[11],"in":[12,123],"an":[13,117],"actor-critic":[14,115],"framework":[15],"where":[16],"the":[17,20,29,39,50,65,74,77,89,96,105,108,113],"actor":[18],"and":[19,71,103],"critic":[21,40],"operate":[22],"concurrently.":[23],"That":[24],"is,":[25],"instead":[26],"of":[27,35,56,107,119],"learning":[28,44],"value":[30],"function":[31],"or":[32],"policy":[33,51],"gradient":[34],"fixed":[37],"policy,":[38],"carries":[41],"out":[42,82],"its":[43],"on":[45,88],"one":[46],"sample":[47],"path":[48],"while":[49],"is":[52],"slowly":[53],"varying.":[54],"Convergence":[55],"such":[57],"process":[59],"has":[60],"previously":[61],"been":[62],"proven":[63],"for":[64,95],"first":[66],"order":[67],"TD":[68],"algorithms,":[69],"TD(\u03bb)":[70],"TD(1).":[72],"However,":[73],"conversion":[75],"to":[76,116],"more":[78],"powerful":[79],"LSTD":[80,97,114],"turns":[81],"not":[83],"straightforward,":[84],"because":[85],"some":[86],"conditions":[87],"stepsize":[90],"sequences":[91],"must":[92],"be":[93],"modified":[94],"case.":[98],"We":[99],"propose":[100],"solution":[102],"prove":[104],"convergence":[106],"process.":[109],"Furthermore,":[110],"apply":[112],"application":[118],"intelligently":[120],"dispatching":[121],"forklifts":[122],"warehouse.":[125]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2024,"cited_by_count":1},{"year":2021,"cited_by_count":1},{"year":2020,"cited_by_count":1},{"year":2016,"cited_by_count":1},{"year":2015,"cited_by_count":1},{"year":2014,"cited_by_count":1},{"year":2012,"cited_by_count":2}],"updated_date":"2026-11-07T11:25:07.637180","created_date":"2016-06-24T00:00:00"}