{"id":"https://openalex.org/W3187974874","doi":"https://doi.org/10.3233/faia361","title":"Exploiting Environment Configurability in Reinforcement Learning","display_name":"Exploiting Environment Configurability in Reinforcement Learning","publication_year":2022,"publication_date":"2022-11-23","ids":{"openalex":"https://openalex.org/W3187974874","doi":"https://doi.org/10.3233/faia361","mag":"3187974874"},"language":"en","primary_location":{"id":"doi:10.3233/faia361","is_oa":false,"landing_page_url":"https://doi.org/10.3233/faia361","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":"monograph"},"type":"book","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/A5037963323","display_name":"Alberto Maria Metelli","orcid":"https://orcid.org/0000-0002-3424-5212"},"institutions":[{"id":"https://openalex.org/I93860229","display_name":"Politecnico di Milano","ror":"https://ror.org/01nffqt88","country_code":"IT","type":"education","lineage":["https://openalex.org/I93860229"]}],"countries":["IT"],"is_corresponding":true,"raw_author_name":"Alberto Maria Metelli","raw_affiliation_strings":["Dipartimento di Elettronica, Informazione e Bioingegneria, Politecnico di Milano, Milano, Italy"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Dipartimento di Elettronica, Informazione e Bioingegneria, Politecnico di Milano, Milano, Italy","institution_ids":["https://openalex.org/I93860229"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":["https://openalex.org/A5037963323"],"corresponding_institution_ids":["https://openalex.org/I93860229"],"apc_list":null,"apc_paid":null,"fwci":0.7395,"has_fulltext":false,"cited_by_count":3,"citation_normalized_percentile":{"value":0.75665025,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":96},"biblio":{"volume":null,"issue":null,"first_page":null,"last_page":null},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10462","display_name":"Reinforcement Learning in Robotics","score":0.7512000203132629,"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":0.7512000203132629,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/reinforcement-learning","display_name":"Reinforcement learning","score":0.6735876798629761},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.5430002808570862},{"id":"https://openalex.org/keywords/reinforcement","display_name":"Reinforcement","score":0.5204815864562988},{"id":"https://openalex.org/keywords/human\u2013computer-interaction","display_name":"Human\u2013computer interaction","score":0.37205770611763},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.25722628831863403},{"id":"https://openalex.org/keywords/psychology","display_name":"Psychology","score":0.23227953910827637},{"id":"https://openalex.org/keywords/social-psychology","display_name":"Social psychology","score":0.058236896991729736}],"concepts":[{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.6735876798629761},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5430002808570862},{"id":"https://openalex.org/C67203356","wikidata":"https://www.wikidata.org/wiki/Q1321905","display_name":"Reinforcement","level":2,"score":0.5204815864562988},{"id":"https://openalex.org/C107457646","wikidata":"https://www.wikidata.org/wiki/Q207434","display_name":"Human\u2013computer interaction","level":1,"score":0.37205770611763},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.25722628831863403},{"id":"https://openalex.org/C15744967","wikidata":"https://www.wikidata.org/wiki/Q9418","display_name":"Psychology","level":0,"score":0.23227953910827637},{"id":"https://openalex.org/C77805123","wikidata":"https://www.wikidata.org/wiki/Q161272","display_name":"Social psychology","level":1,"score":0.058236896991729736}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.3233/faia361","is_oa":false,"landing_page_url":"https://doi.org/10.3233/faia361","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":"monograph"},{"id":"pmh:oai:re.public.polimi.it:11311/1236404","is_oa":false,"landing_page_url":"https://hdl.handle.net/11311/1236404","pdf_url":null,"source":{"id":"https://openalex.org/S4306400312","display_name":"Virtual Community of Pathological Anatomy (University of Castilla La Mancha)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I79189158","host_organization_name":"University of Castilla-La Mancha","host_organization_lineage":["https://openalex.org/I79189158"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"info:eu-repo/semantics/book"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/13","score":0.5299999713897705,"display_name":"Climate action"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":["https://openalex.org/W2899084033","https://openalex.org/W2748952813","https://openalex.org/W2920061524","https://openalex.org/W4310083477","https://openalex.org/W1977959518","https://openalex.org/W2107890255","https://openalex.org/W2089013912","https://openalex.org/W2106552856","https://openalex.org/W2076061571","https://openalex.org/W2038908348"],"abstract_inverted_index":{"In":[0,17,76],"recent":[1],"decades,":[2],"Reinforcement":[3,64],"Learning":[4],"(RL)":[5],"has":[6],"emerged":[7],"as":[8,244],"an":[9,202,206],"effective":[10],"approach":[11],"to":[12,31,54,67,97,175,239],"address":[13],"complex":[14],"control":[15,230],"tasks.":[16],"a":[18,33,55,77,92,98,103,114,117],"Markov":[19,171],"Decision":[20,172],"Process":[21],"(MDP),":[22],"the":[23,27,49,80,83,86,94,109,123,135,142,147,166,177,182,188,192,198,212,223],"framework":[24],"typically":[25],"used,":[26],"environment":[28,50,74,87,95,127,207],"is":[29,137],"assumed":[30],"be":[32,38,52,156,236],"fixed":[34],"entity":[35],"that":[36,121,209],"cannot":[37],"altered":[39],"externally.":[40],"There":[41],"are,":[42],"however,":[43],"several":[44],"real-world":[45],"scenarios":[46],"in":[47,63,132,141,146],"which":[48],"can":[51,155],"modified":[53],"limited":[56],"extent.":[57],"This":[58],"book,":[59],"Exploiting":[60],"Environment":[61],"Configurability":[62],"Learning,":[65],"aims":[66],"formalize":[68],"and":[69,88,101,152,154,196,205,229],"study":[70],"diverse":[71],"aspects":[72],"of":[73,85,108,112,119,169,187,200,222,237,246],"configuration.":[75],"traditional":[78],"MDP,":[79],"agent":[81,110,203],"perceives":[82],"state":[84,100],"performs":[89],"actions.":[90],"As":[91],"consequence,":[93],"transitions":[96],"new":[99],"generates":[102],"reward":[104],"signal.":[105],"The":[106,144,162,184,215,233],"goal":[107],"consists":[111],"learning":[113],"policy,":[115],"i.e.,":[116],"prescription":[118],"actions":[120],"maximize":[122],"long-term":[124,213],"reward.":[125,214],"Although":[126],"configuration":[128,178,208],"arises":[129],"quite":[130],"often":[131],"real":[133],"applications,":[134],"topic":[136],"very":[138],"little":[139],"explored":[140],"literature.":[143],"contributions":[145],"book":[148,189,234],"are":[149],"theoretical,":[150],"algorithmic,":[151],"experimental":[153],"broadly":[157],"subdivided":[158],"into":[159],"three":[160],"parts.":[161],"first":[163],"part":[164,186,217,245],"introduces":[165],"novel":[167],"formalism":[168],"Configurable":[170],"Processes":[173],"(Conf-MDPs)":[174],"model":[176],"opportunities":[179],"offered":[180],"by":[181],"environment.":[183],"second":[185],"focuses":[190],"on":[191],"cooperative":[193],"Conf-MDP":[194,224],"setting":[195],"investigates":[197],"problem":[199],"finding":[201],"policy":[204,226],"jointly":[210],"optimize":[211],"third":[216],"addresses":[218],"two":[219],"specific":[220],"applications":[221],"framework:":[225],"space":[227],"identification":[228],"frequency":[231],"adaptation.":[232],"will":[235],"interest":[238],"all":[240],"those":[241],"using":[242],"RL":[243],"their":[247],"work.":[248]},"counts_by_year":[{"year":2024,"cited_by_count":1},{"year":2022,"cited_by_count":2}],"updated_date":"2026-08-08T01:25:22.217667","created_date":"2025-10-10T00:00:00"}
