{"id":"https://openalex.org/W2395090196","doi":"https://doi.org/10.3233/978-1-61499-452-7-3","title":"Approximate Policy Iteration with Bellman Residuals Minimization","display_name":"Approximate Policy Iteration with Bellman Residuals Minimization","publication_year":2014,"publication_date":"2014-01-01","ids":{"openalex":"https://openalex.org/W2395090196","doi":"https://doi.org/10.3233/978-1-61499-452-7-3","mag":"2395090196"},"language":"en","primary_location":{"id":"doi:10.3233/978-1-61499-452-7-3","is_oa":false,"landing_page_url":"https://doi.org/10.3233/978-1-61499-452-7-3","pdf_url":null,"source":{"id":"https://openalex.org/S4210201731","display_name":"Frontiers in artificial intelligence and applications","issn_l":"0922-6389","issn":["0922-6389","1879-8314"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Frontiers in Artificial Intelligence and Applications","raw_type":"book-chapter"},"type":"book-chapter","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/A5085532591","display_name":"G. Esposito","orcid":"https://orcid.org/0000-0002-9700-2971"},"institutions":[],"countries":[],"is_corresponding":true,"raw_author_name":"Esposito Gennaro","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5026842131","display_name":"Mario Mart\u00edn","orcid":"https://orcid.org/0000-0002-4125-6630"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Martin Mario","raw_affiliation_strings":[],"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5085532591"],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.17793828,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"3","last_page":"12"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10462","display_name":"Reinforcement Learning in Robotics","score":0.9682999849319458,"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":0.9682999849319458,"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/T12288","display_name":"Optimization and Search Problems","score":0.9681000113487244,"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/T12101","display_name":"Advanced Bandit Algorithms Research","score":0.9610999822616577,"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/minification","display_name":"Minification","score":0.7003214359283447},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.44171980023384094},{"id":"https://openalex.org/keywords/mathematical-optimization","display_name":"Mathematical optimization","score":0.43221527338027954},{"id":"https://openalex.org/keywords/economics","display_name":"Economics","score":0.4247598648071289},{"id":"https://openalex.org/keywords/applied-mathematics","display_name":"Applied mathematics","score":0.32057905197143555}],"concepts":[{"id":"https://openalex.org/C147764199","wikidata":"https://www.wikidata.org/wiki/Q6865248","display_name":"Minification","level":2,"score":0.7003214359283447},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.44171980023384094},{"id":"https://openalex.org/C126255220","wikidata":"https://www.wikidata.org/wiki/Q141495","display_name":"Mathematical optimization","level":1,"score":0.43221527338027954},{"id":"https://openalex.org/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","level":0,"score":0.4247598648071289},{"id":"https://openalex.org/C28826006","wikidata":"https://www.wikidata.org/wiki/Q33521","display_name":"Applied mathematics","level":1,"score":0.32057905197143555}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.3233/978-1-61499-452-7-3","is_oa":false,"landing_page_url":"https://doi.org/10.3233/978-1-61499-452-7-3","pdf_url":null,"source":{"id":"https://openalex.org/S4210201731","display_name":"Frontiers in artificial intelligence and applications","issn_l":"0922-6389","issn":["0922-6389","1879-8314"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Frontiers in Artificial Intelligence and Applications","raw_type":"book-chapter"},{"id":"mag:2395090196","is_oa":false,"landing_page_url":"https://dblp.uni-trier.de/db/conf/ccia/ccia2014.html#EspositoM14","pdf_url":null,"source":{"id":"https://openalex.org/S4306505786","display_name":"CCIA","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"journal"},"license":null,"license_id":null,"version":null,"is_accepted":false,"is_published":null,"raw_source_name":"CCIA","raw_type":null}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/13","display_name":"Climate action","score":0.5899999737739563}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":["https://openalex.org/W4391375266","https://openalex.org/W1979597421","https://openalex.org/W2007980826","https://openalex.org/W2061531152","https://openalex.org/W3002753104","https://openalex.org/W2077600819","https://openalex.org/W2142036596","https://openalex.org/W2072657027","https://openalex.org/W2962838298","https://openalex.org/W2600246793"],"abstract_inverted_index":{"Reinforcement":[0],"Learning":[1],"(RL)":[2],"provides":[3],"a":[4,26,139],"general":[5],"methodology":[6],"to":[7,75,92,121],"solve":[8],"complex":[9],"uncertain":[10],"decision":[11],"problems,":[12],"which":[13,44,142],"are":[14,86],"very":[15,59,154],"challenging":[16],"in":[17,33,58,104,107],"many":[18],"real-world":[19],"applications.":[20],"RL":[21,43,69,108,123,152],"problem":[22],"is":[23,64,71,138,167],"modeled":[24],"as":[25],"Markov":[27],"Decision":[28],"Process":[29],"(MDP)":[30],"deeply":[31],"studied":[32],"the":[34,97,125,159,164],"literature.":[35],"We":[36],"consider":[37],"Policy":[38],"Iteration":[39],"(PI)":[40],"algorithms":[41,70],"for":[42,78,82],"iteratively":[45],"evaluate":[46],"and":[47,145,161],"improve":[48],"control":[49],"policies.":[50],"In":[51],"handling":[52],"problems":[53],"with":[54,132],"continuous":[55],"states":[56,129],"or":[57],"large":[60],"state":[61],"spaces,":[62],"generalization":[63,98,119],"mandatory.":[65],"Generalization":[66],"property":[67],"of":[68,112,148,163],"an":[72],"important":[73],"factor":[74],"predict":[76],"values":[77],"unexplored":[79],"states.":[80],"Candidates":[81],"value":[83,149],"function":[84,150],"approximation":[85],"Support":[87],"Vector":[88],"Regression":[89],"(SVR)":[90],"known":[91],"have":[93],"good":[94,146],"properties":[95],"over":[96],"ability.":[99],"SVR":[100,115,118,137],"has":[101],"been":[102],"used":[103],"batch":[105],"frameworks":[106],"but,":[109],"smart":[110],"implementations":[111],"incremental":[113],"exact":[114],"can":[116],"extend":[117],"ability":[120],"online":[122,136],"where":[124],"expected":[126],"reward":[127],"from":[128],"change":[130],"constantly":[131],"experience.":[133],"Hence":[134],"our":[135],"novelty":[140],"method":[141],"allows":[143],"fast":[144],"estimation":[147],"achieving":[151],"objective":[153],"efficiently.":[155],"Throughout":[156],"simulation":[157],"tests,":[158],"feasibility":[160],"usefulness":[162],"proposed":[165],"approach":[166],"demonstrated.":[168]},"counts_by_year":[],"updated_date":"2025-12-28T23:10:05.387466","created_date":"2025-10-10T00:00:00"}