{"id":"https://openalex.org/W2041277185","doi":"https://doi.org/10.1109/tac.2015.2418411","title":"Classification-Based Approximate Policy Iteration","display_name":"Classification-Based Approximate Policy Iteration","publication_year":2015,"publication_date":"2015-04-01","ids":{"openalex":"https://openalex.org/W2041277185","doi":"https://doi.org/10.1109/tac.2015.2418411","mag":"2041277185"},"language":"en","primary_location":{"id":"doi:10.1109/tac.2015.2418411","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tac.2015.2418411","pdf_url":null,"source":{"id":"https://openalex.org/S184954342","display_name":"IEEE Transactions on Automatic Control","issn_l":"0018-9286","issn":["0018-9286","1558-2523","2334-3303"],"is_oa":false,"is_in_doaj":false,"is_core":true,"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":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Transactions on Automatic Control","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/A5109495187","display_name":"Amir\u2010massoud Farahmand","orcid":null},"institutions":[{"id":"https://openalex.org/I4210159266","display_name":"Mitsubishi Electric (United States)","ror":"https://ror.org/053jnhe44","country_code":"US","type":"company","lineage":["https://openalex.org/I1306287861","https://openalex.org/I4210133125","https://openalex.org/I4210159266"]},{"id":"https://openalex.org/I5023651","display_name":"McGill University","ror":"https://ror.org/01pxwe438","country_code":"CA","type":"education","lineage":["https://openalex.org/I5023651"]}],"countries":["CA","US"],"is_corresponding":false,"raw_author_name":"Amir-massoud Farahmand","raw_affiliation_strings":["School of Computer Science, Mitsubishi Electric Research Laboratories, Cambridge, MA, USA","[Sch. of Comput. Sci., McGill Univ., Montreal, QC, Canada]"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Computer Science, Mitsubishi Electric Research Laboratories, Cambridge, MA, USA","institution_ids":["https://openalex.org/I4210159266"]},{"raw_affiliation_string":"[Sch. of Comput. Sci., McGill Univ., Montreal, QC, Canada]","institution_ids":["https://openalex.org/I5023651"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5065836447","display_name":"Doina Precup","orcid":null},"institutions":[{"id":"https://openalex.org/I5023651","display_name":"McGill University","ror":"https://ror.org/01pxwe438","country_code":"CA","type":"education","lineage":["https://openalex.org/I5023651"]}],"countries":["CA"],"is_corresponding":false,"raw_author_name":"Doina Precup","raw_affiliation_strings":["School of Computer Science, McGill University, Montreal, Canada","[Sch. of Comput. Sci., McGill Univ., Montreal, QC, Canada]"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Computer Science, McGill University, Montreal, Canada","institution_ids":["https://openalex.org/I5023651"]},{"raw_affiliation_string":"[Sch. of Comput. Sci., McGill Univ., Montreal, QC, Canada]","institution_ids":["https://openalex.org/I5023651"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5110617622","display_name":"Andr\u00e9 M. S. Barreto","orcid":null},"institutions":[{"id":"https://openalex.org/I46090414","display_name":"Universidade Cat\u00f3lica de Petr\u00f3polis","ror":"https://ror.org/01j56e062","country_code":"BR","type":"education","lineage":["https://openalex.org/I46090414"]},{"id":"https://openalex.org/I5023651","display_name":"McGill University","ror":"https://ror.org/01pxwe438","country_code":"CA","type":"education","lineage":["https://openalex.org/I5023651"]}],"countries":["BR","CA"],"is_corresponding":false,"raw_author_name":"Andre M. S. Barreto","raw_affiliation_strings":["School of Computer Science, McGill University, Petr\u00f3polis, Brazil","[Sch. of Comput. Sci., McGill Univ., Montreal, QC, Canada]"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Computer Science, McGill University, Petr\u00f3polis, Brazil","institution_ids":["https://openalex.org/I46090414"]},{"raw_affiliation_string":"[Sch. of Comput. Sci., McGill Univ., Montreal, QC, Canada]","institution_ids":["https://openalex.org/I5023651"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5013843778","display_name":"Mohammad Ghavamzadeh","orcid":"https://orcid.org/0000-0003-0930-8688"},"institutions":[{"id":"https://openalex.org/I1306409833","display_name":"Adobe Systems (United States)","ror":"https://ror.org/059tvcg64","country_code":"US","type":"company","lineage":["https://openalex.org/I1306409833"]},{"id":"https://openalex.org/I1326498283","display_name":"Institut national de recherche en sciences et technologies du num\u00e9rique","ror":"https://ror.org/02kvxyf05","country_code":"FR","type":"government","lineage":["https://openalex.org/I1326498283"]}],"countries":["FR","US"],"is_corresponding":false,"raw_author_name":"Mohammad Ghavamzadeh","raw_affiliation_strings":["Adobe Research, INRIA Lille, France","[Adobe Research San Francisco, CA, USA]"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Adobe Research, INRIA Lille, France","institution_ids":["https://openalex.org/I1326498283"]},{"raw_affiliation_string":"[Adobe Research San Francisco, CA, USA]","institution_ids":["https://openalex.org/I1306409833"]}]}],"institutions":[],"countries_distinct_count":4,"institutions_distinct_count":5,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.8731,"has_fulltext":false,"cited_by_count":7,"citation_normalized_percentile":{"value":0.82476901,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":93,"max":97},"biblio":{"volume":"60","issue":"11","first_page":"2989","last_page":"2993"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10462","display_name":"Reinforcement Learning in Robotics","score":0.9991000294685364,"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":0.9991000294685364,"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/T10142","display_name":"Formal Methods in Verification","score":0.9641000032424927,"subfield":{"id":"https://openalex.org/subfields/1703","display_name":"Computational Theory and Mathematics"},"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":0.9606000185012817,"subfield":{"id":"https://openalex.org/subfields/1703","display_name":"Computational Theory and Mathematics"},"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/exploit","display_name":"Exploit","score":0.8574700355529785},{"id":"https://openalex.org/keywords/reinforcement-learning","display_name":"Reinforcement learning","score":0.7239322066307068},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7150510549545288},{"id":"https://openalex.org/keywords/mathematical-optimization","display_name":"Mathematical optimization","score":0.56395423412323},{"id":"https://openalex.org/keywords/nonparametric-statistics","display_name":"Nonparametric statistics","score":0.5500744581222534},{"id":"https://openalex.org/keywords/dynamic-programming","display_name":"Dynamic programming","score":0.53022700548172},{"id":"https://openalex.org/keywords/variety","display_name":"Variety (cybernetics)","score":0.5114785432815552},{"id":"https://openalex.org/keywords/function","display_name":"Function (biology)","score":0.4841945469379425},{"id":"https://openalex.org/keywords/bellman-equation","display_name":"Bellman equation","score":0.47513654828071594},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.40021196007728577},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.2964358329772949},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.2726648449897766},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.2393021583557129},{"id":"https://openalex.org/keywords/statistics","display_name":"Statistics","score":0.07158768177032471}],"concepts":[{"id":"https://openalex.org/C165696696","wikidata":"https://www.wikidata.org/wiki/Q11287","display_name":"Exploit","level":2,"score":0.8574700355529785},{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.7239322066307068},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7150510549545288},{"id":"https://openalex.org/C126255220","wikidata":"https://www.wikidata.org/wiki/Q141495","display_name":"Mathematical optimization","level":1,"score":0.56395423412323},{"id":"https://openalex.org/C102366305","wikidata":"https://www.wikidata.org/wiki/Q1097688","display_name":"Nonparametric statistics","level":2,"score":0.5500744581222534},{"id":"https://openalex.org/C37404715","wikidata":"https://www.wikidata.org/wiki/Q380679","display_name":"Dynamic programming","level":2,"score":0.53022700548172},{"id":"https://openalex.org/C136197465","wikidata":"https://www.wikidata.org/wiki/Q1729295","display_name":"Variety (cybernetics)","level":2,"score":0.5114785432815552},{"id":"https://openalex.org/C14036430","wikidata":"https://www.wikidata.org/wiki/Q3736076","display_name":"Function (biology)","level":2,"score":0.4841945469379425},{"id":"https://openalex.org/C14646407","wikidata":"https://www.wikidata.org/wiki/Q1430750","display_name":"Bellman equation","level":2,"score":0.47513654828071594},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.40021196007728577},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.2964358329772949},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.2726648449897766},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.2393021583557129},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.07158768177032471},{"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/C38652104","wikidata":"https://www.wikidata.org/wiki/Q3510521","display_name":"Computer security","level":1,"score":0.0},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/tac.2015.2418411","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tac.2015.2418411","pdf_url":null,"source":{"id":"https://openalex.org/S184954342","display_name":"IEEE Transactions on Automatic Control","issn_l":"0018-9286","issn":["0018-9286","1558-2523","2334-3303"],"is_oa":false,"is_in_doaj":false,"is_core":true,"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":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Transactions on Automatic Control","raw_type":"journal-article"},{"id":"pmh:oai:publications.polymtl.ca:63136","is_oa":false,"landing_page_url":"https://publications.polymtl.ca/63136/","pdf_url":null,"source":{"id":"https://openalex.org/S4306401013","display_name":"PolyPublie (\u00c9cole Polytechnique de Montr\u00e9al)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I45683168","host_organization_name":"Polytechnique Montr\u00e9al","host_organization_lineage":["https://openalex.org/I45683168"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"acceptedVersion","is_accepted":true,"is_published":false,"raw_source_name":null,"raw_type":"Article de revue"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.6299999952316284,"id":"https://metadata.un.org/sdg/16","display_name":"Peace, Justice and strong institutions"}],"awards":[],"funders":[{"id":"https://openalex.org/F4320334593","display_name":"Natural Sciences and Engineering Research Council of Canada","ror":"https://ror.org/01h531d29"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":45,"referenced_works":["https://openalex.org/W1484867920","https://openalex.org/W1511421254","https://openalex.org/W1571975558","https://openalex.org/W1698155719","https://openalex.org/W1931877416","https://openalex.org/W2006330826","https://openalex.org/W2012547817","https://openalex.org/W2046513829","https://openalex.org/W2063368770","https://openalex.org/W2073384958","https://openalex.org/W2096899507","https://openalex.org/W2100785108","https://openalex.org/W2103568863","https://openalex.org/W2111625536","https://openalex.org/W2120346334","https://openalex.org/W2120465407","https://openalex.org/W2128812357","https://openalex.org/W2134289401","https://openalex.org/W2138663952","https://openalex.org/W2150821861","https://openalex.org/W2157864803","https://openalex.org/W2158738729","https://openalex.org/W2160284799","https://openalex.org/W2165060096","https://openalex.org/W2181692883","https://openalex.org/W2586680856","https://openalex.org/W2962957031","https://openalex.org/W3100743579","https://openalex.org/W3141455185","https://openalex.org/W4285719527","https://openalex.org/W4299401133","https://openalex.org/W4300173024","https://openalex.org/W6630532500","https://openalex.org/W6640174482","https://openalex.org/W6675278435","https://openalex.org/W6675682287","https://openalex.org/W6676872911","https://openalex.org/W6677737365","https://openalex.org/W6679100793","https://openalex.org/W6679703492","https://openalex.org/W6680477579","https://openalex.org/W6683356630","https://openalex.org/W6683554789","https://openalex.org/W6684022048","https://openalex.org/W6980386631"],"related_works":["https://openalex.org/W4239477580","https://openalex.org/W4385342861","https://openalex.org/W4323339366","https://openalex.org/W4240668504","https://openalex.org/W2373808749","https://openalex.org/W2263747200","https://openalex.org/W1519972694","https://openalex.org/W2149418961","https://openalex.org/W2156992384","https://openalex.org/W2342906992"],"abstract_inverted_index":{"Tackling":[0],"large":[1],"approximate":[2,42],"dynamic":[3],"programming":[4],"or":[5,34],"reinforcement":[6],"learning":[7],"problems":[8],"requires":[9],"methods":[10,22],"that":[11,47],"can":[12,48,80],"exploit":[13,49],"regularities":[14,28,50],"of":[15,29,51,61,77,84,92],"the":[16,27,31,35,58,66,89,93],"problem":[17],"in":[18],"hand.":[19],"Most":[20],"current":[21],"are":[23,96],"geared":[24],"towards":[25],"exploiting":[26],"either":[30],"value":[32],"function":[33],"policy.":[36],"We":[37,53],"introduce":[38],"a":[39,74],"general":[40],"classification-based":[41],"policy":[43,67],"iteration":[44],"(CAPI)":[45],"framework":[46],"both.":[52],"establish":[54],"theoretical":[55],"guarantees":[56],"for":[57],"sample":[59],"complexity":[60],"CAPI-style":[62],"algorithms,":[63,78],"which":[64],"allow":[65],"evaluation":[68],"step":[69],"to":[70],"be":[71],"performed":[72],"by":[73],"wide":[75],"variety":[76],"and":[79],"handle":[81],"nonparametric":[82],"representations":[83],"policies.":[85],"Our":[86],"bounds":[87],"on":[88],"estimation":[90],"error":[91],"performance":[94],"loss":[95],"tighter":[97],"than":[98],"existing":[99],"results.":[100]},"counts_by_year":[{"year":2021,"cited_by_count":2},{"year":2020,"cited_by_count":3},{"year":2016,"cited_by_count":2}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}