{"id":"https://openalex.org/W2971672682","doi":"https://doi.org/10.1007/s10994-021-06033-3","title":"Policy space identification in configurable environments","display_name":"Policy space identification in configurable environments","publication_year":2021,"publication_date":"2021-09-05","ids":{"openalex":"https://openalex.org/W2971672682","doi":"https://doi.org/10.1007/s10994-021-06033-3","mag":"2971672682"},"language":"en","primary_location":{"id":"doi:10.1007/s10994-021-06033-3","is_oa":true,"landing_page_url":"https://doi.org/10.1007/s10994-021-06033-3","pdf_url":"https://link.springer.com/content/pdf/10.1007/s10994-021-06033-3.pdf","source":{"id":"https://openalex.org/S62148650","display_name":"Machine Learning","issn_l":"0885-6125","issn":["0885-6125","1573-0565"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319900","host_organization_name":"Springer Science+Business Media","host_organization_lineage":["https://openalex.org/P4310319900","https://openalex.org/P4310319965"],"host_organization_lineage_names":["Springer Science+Business Media","Springer Nature"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Machine Learning","raw_type":"journal-article"},"type":"article","indexed_in":["arxiv","crossref","datacite"],"open_access":{"is_oa":true,"oa_status":"hybrid","oa_url":"https://link.springer.com/content/pdf/10.1007/s10994-021-06033-3.pdf","any_repository_has_fulltext":true},"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":["DEIB, Politecnico di Milano, Piazza Leonardo Da Vinci, 32, 20133, Milan, Italy","Polytechnic University of Milan"],"raw_orcid":"https://orcid.org/0000-0002-3424-5212","affiliations":[{"raw_affiliation_string":"DEIB, Politecnico di Milano, Piazza Leonardo Da Vinci, 32, 20133, Milan, Italy","institution_ids":["https://openalex.org/I93860229"]},{"raw_affiliation_string":"Polytechnic University of Milan","institution_ids":["https://openalex.org/I93860229"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5026492591","display_name":"Guglielmo Manneschi","orcid":null},"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":false,"raw_author_name":"Guglielmo Manneschi","raw_affiliation_strings":["DEIB, Politecnico di Milano, Piazza Leonardo Da Vinci, 32, 20133, Milan, Italy","Polytechnic University of Milan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"DEIB, Politecnico di Milano, Piazza Leonardo Da Vinci, 32, 20133, Milan, Italy","institution_ids":["https://openalex.org/I93860229"]},{"raw_affiliation_string":"Polytechnic University of Milan","institution_ids":["https://openalex.org/I93860229"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5017130830","display_name":"Marcello Restelli","orcid":"https://orcid.org/0000-0002-6322-1076"},"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":false,"raw_author_name":"Marcello Restelli","raw_affiliation_strings":["DEIB, Politecnico di Milano, Piazza Leonardo Da Vinci, 32, 20133, Milan, Italy","Polytechnic University of Milan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"DEIB, Politecnico di Milano, Piazza Leonardo Da Vinci, 32, 20133, Milan, Italy","institution_ids":["https://openalex.org/I93860229"]},{"raw_affiliation_string":"Polytechnic University of Milan","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":{"value":2780,"currency":"USD","value_usd":2780},"apc_paid":{"value":2780,"currency":"USD","value_usd":2780},"fwci":0.1401,"has_fulltext":true,"cited_by_count":1,"citation_normalized_percentile":{"value":0.55602545,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":94},"biblio":{"volume":"111","issue":"6","first_page":"2093","last_page":"2145"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10462","display_name":"Reinforcement Learning in Robotics","score":0.9988999962806702,"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":0.9988999962806702,"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/T12072","display_name":"Machine Learning and Algorithms","score":0.9937999844551086,"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/T12761","display_name":"Data Stream Mining Techniques","score":0.980400025844574,"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/identification","display_name":"Identification (biology)","score":0.7373201847076416},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7106186747550964},{"id":"https://openalex.org/keywords/probabilistic-logic","display_name":"Probabilistic logic","score":0.6580860614776611},{"id":"https://openalex.org/keywords/set","display_name":"Set (abstract data type)","score":0.6461468935012817},{"id":"https://openalex.org/keywords/markov-decision-process","display_name":"Markov decision process","score":0.6165965795516968},{"id":"https://openalex.org/keywords/space","display_name":"Space (punctuation)","score":0.5909143090248108},{"id":"https://openalex.org/keywords/frame","display_name":"Frame (networking)","score":0.5634284019470215},{"id":"https://openalex.org/keywords/parametric-statistics","display_name":"Parametric statistics","score":0.5324040055274963},{"id":"https://openalex.org/keywords/control","display_name":"Control (management)","score":0.46336930990219116},{"id":"https://openalex.org/keywords/markov-chain","display_name":"Markov chain","score":0.4406241774559021},{"id":"https://openalex.org/keywords/mathematical-optimization","display_name":"Mathematical optimization","score":0.3611176311969757},{"id":"https://openalex.org/keywords/theoretical-computer-science","display_name":"Theoretical computer science","score":0.3307698369026184},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.3190525770187378},{"id":"https://openalex.org/keywords/markov-process","display_name":"Markov process","score":0.3147352933883667},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.28572237491607666},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.19198721647262573}],"concepts":[{"id":"https://openalex.org/C116834253","wikidata":"https://www.wikidata.org/wiki/Q2039217","display_name":"Identification (biology)","level":2,"score":0.7373201847076416},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7106186747550964},{"id":"https://openalex.org/C49937458","wikidata":"https://www.wikidata.org/wiki/Q2599292","display_name":"Probabilistic logic","level":2,"score":0.6580860614776611},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.6461468935012817},{"id":"https://openalex.org/C106189395","wikidata":"https://www.wikidata.org/wiki/Q176789","display_name":"Markov decision process","level":3,"score":0.6165965795516968},{"id":"https://openalex.org/C2778572836","wikidata":"https://www.wikidata.org/wiki/Q380933","display_name":"Space (punctuation)","level":2,"score":0.5909143090248108},{"id":"https://openalex.org/C126042441","wikidata":"https://www.wikidata.org/wiki/Q1324888","display_name":"Frame (networking)","level":2,"score":0.5634284019470215},{"id":"https://openalex.org/C117251300","wikidata":"https://www.wikidata.org/wiki/Q1849855","display_name":"Parametric statistics","level":2,"score":0.5324040055274963},{"id":"https://openalex.org/C2775924081","wikidata":"https://www.wikidata.org/wiki/Q55608371","display_name":"Control (management)","level":2,"score":0.46336930990219116},{"id":"https://openalex.org/C98763669","wikidata":"https://www.wikidata.org/wiki/Q176645","display_name":"Markov chain","level":2,"score":0.4406241774559021},{"id":"https://openalex.org/C126255220","wikidata":"https://www.wikidata.org/wiki/Q141495","display_name":"Mathematical optimization","level":1,"score":0.3611176311969757},{"id":"https://openalex.org/C80444323","wikidata":"https://www.wikidata.org/wiki/Q2878974","display_name":"Theoretical computer science","level":1,"score":0.3307698369026184},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.3190525770187378},{"id":"https://openalex.org/C159886148","wikidata":"https://www.wikidata.org/wiki/Q176645","display_name":"Markov process","level":2,"score":0.3147352933883667},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.28572237491607666},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.19198721647262573},{"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/C59822182","wikidata":"https://www.wikidata.org/wiki/Q441","display_name":"Botany","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},{"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/C76155785","wikidata":"https://www.wikidata.org/wiki/Q418","display_name":"Telecommunications","level":1,"score":0.0}],"mesh":[],"locations_count":4,"locations":[{"id":"doi:10.1007/s10994-021-06033-3","is_oa":true,"landing_page_url":"https://doi.org/10.1007/s10994-021-06033-3","pdf_url":"https://link.springer.com/content/pdf/10.1007/s10994-021-06033-3.pdf","source":{"id":"https://openalex.org/S62148650","display_name":"Machine Learning","issn_l":"0885-6125","issn":["0885-6125","1573-0565"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319900","host_organization_name":"Springer Science+Business Media","host_organization_lineage":["https://openalex.org/P4310319900","https://openalex.org/P4310319965"],"host_organization_lineage_names":["Springer Science+Business Media","Springer Nature"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Machine Learning","raw_type":"journal-article"},{"id":"pmh:oai:arXiv.org:1909.03984","is_oa":true,"landing_page_url":"http://arxiv.org/abs/1909.03984","pdf_url":"https://arxiv.org/pdf/1909.03984","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"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":"text"},{"id":"doi:10.48550/arxiv.1909.03984","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.1909.03984","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":null,"is_accepted":false,"is_published":null,"raw_source_name":null,"raw_type":"Preprint"},{"id":"mag:2971672682","is_oa":false,"landing_page_url":null,"pdf_url":null,"source":null,"license":null,"license_id":null,"version":null,"is_accepted":false,"is_published":null,"raw_source_name":null,"raw_type":null}],"best_oa_location":{"id":"doi:10.1007/s10994-021-06033-3","is_oa":true,"landing_page_url":"https://doi.org/10.1007/s10994-021-06033-3","pdf_url":"https://link.springer.com/content/pdf/10.1007/s10994-021-06033-3.pdf","source":{"id":"https://openalex.org/S62148650","display_name":"Machine Learning","issn_l":"0885-6125","issn":["0885-6125","1573-0565"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319900","host_organization_name":"Springer Science+Business Media","host_organization_lineage":["https://openalex.org/P4310319900","https://openalex.org/P4310319965"],"host_organization_lineage_names":["Springer Science+Business Media","Springer Nature"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Machine Learning","raw_type":"journal-article"},"sustainable_development_goals":[{"display_name":"Peace, Justice and strong institutions","id":"https://metadata.un.org/sdg/16","score":0.7900000214576721}],"awards":[],"funders":[{"id":"https://openalex.org/F4320324039","display_name":"Politecnico di Milano","ror":"https://ror.org/01nffqt88"}],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W2971672682.pdf","grobid_xml":"https://content.openalex.org/works/W2971672682.grobid-xml"},"referenced_works_count":59,"referenced_works":["https://openalex.org/W568673721","https://openalex.org/W1501567504","https://openalex.org/W1758031947","https://openalex.org/W1969074599","https://openalex.org/W1986014385","https://openalex.org/W1996356638","https://openalex.org/W2012587148","https://openalex.org/W2019841176","https://openalex.org/W2026653933","https://openalex.org/W2036794509","https://openalex.org/W2044394043","https://openalex.org/W2052044664","https://openalex.org/W2061562262","https://openalex.org/W2075672181","https://openalex.org/W2098774185","https://openalex.org/W2099618002","https://openalex.org/W2104733512","https://openalex.org/W2104753538","https://openalex.org/W2109102709","https://openalex.org/W2119567691","https://openalex.org/W2121863487","https://openalex.org/W2125612430","https://openalex.org/W2130599357","https://openalex.org/W2140135625","https://openalex.org/W2147544021","https://openalex.org/W2152938409","https://openalex.org/W2155027007","https://openalex.org/W2187180375","https://openalex.org/W2562989799","https://openalex.org/W2592998600","https://openalex.org/W2595142274","https://openalex.org/W2604763608","https://openalex.org/W2753088790","https://openalex.org/W2786878425","https://openalex.org/W2794908222","https://openalex.org/W2806985155","https://openalex.org/W2890597452","https://openalex.org/W2903013229","https://openalex.org/W2904372083","https://openalex.org/W2944465737","https://openalex.org/W2946467679","https://openalex.org/W2953214153","https://openalex.org/W2963035419","https://openalex.org/W2965394911","https://openalex.org/W2965497096","https://openalex.org/W2995411906","https://openalex.org/W3037828308","https://openalex.org/W3082245592","https://openalex.org/W4245577611","https://openalex.org/W4298082496","https://openalex.org/W6605167227","https://openalex.org/W6675999342","https://openalex.org/W6677916085","https://openalex.org/W6718092244","https://openalex.org/W6734797129","https://openalex.org/W6751495484","https://openalex.org/W6751908871","https://openalex.org/W6754610480","https://openalex.org/W7001894244"],"related_works":["https://openalex.org/W3196519516","https://openalex.org/W2965394911","https://openalex.org/W1530446548","https://openalex.org/W31377030","https://openalex.org/W2810606128","https://openalex.org/W2127288102","https://openalex.org/W2896989282","https://openalex.org/W2097828232","https://openalex.org/W835621606","https://openalex.org/W1594183216","https://openalex.org/W3168806575","https://openalex.org/W2785535773","https://openalex.org/W2185750233","https://openalex.org/W1536817645","https://openalex.org/W1554605283","https://openalex.org/W2524405402","https://openalex.org/W2064567069","https://openalex.org/W2947430226","https://openalex.org/W3041813209","https://openalex.org/W2077448915"],"abstract_inverted_index":{"Abstract":[0],"We":[1,37],"study":[2],"the":[3,7,27,30,34,48,54,77,86,90,97,102,112,117,123,127,131,154],"problem":[4],"of":[5,23,50,85,92,104,111,116,125,156],"identifying":[6],"policy":[8,32,51,62,78],"space":[9],"available":[10],"to":[11,20,46,96,129,133,152],"an":[12,39,143],"agent":[13,28,55,132],"in":[14,33,89],"a":[15,21,59,82],"learning":[16],"process,":[17],"having":[18],"access":[19],"set":[22,49],"demonstrations":[24],"generated":[25],"by":[26],"playing":[29],"optimal":[31],"considered":[35],"space.":[36,63],"introduce":[38],"approach":[40],"based":[41],"on":[42,76,146],"frequentist":[43],"statistical":[44],"testing":[45],"identify":[47],"parameters":[52,136],"that":[53],"can":[56,138],"control,":[57],"within":[58],"larger":[60],"parametric":[61],"After":[64],"presenting":[65],"two":[66],"identification":[67,106,158],"rules":[68],"(combinatorial":[69],"and":[70,149],"simplified),":[71],"applicable":[72],"under":[73],"different":[74],"assumptions":[75],"space,":[79],"we":[80,108,141],"provide":[81,142],"probabilistic":[83],"analysis":[84],"simplified":[87],"one":[88],"case":[91],"linear":[93],"policies":[94],"belonging":[95],"exponential":[98],"family.":[99],"To":[100],"improve":[101],"performance":[103],"our":[105,157],"rules,":[107],"make":[109],"use":[110],"recently":[113],"introduced":[114],"framework":[115],"Configurable":[118],"Markov":[119],"Decision":[120],"Processes,":[121],"exploiting":[122],"opportunity":[124],"configuring":[126],"environment":[128],"induce":[130],"reveal":[134],"which":[135],"it":[137],"control.":[139],"Finally,":[140],"empirical":[144],"evaluation,":[145],"both":[147],"discrete":[148],"continuous":[150],"domains,":[151],"prove":[153],"effectiveness":[155],"rules.":[159]},"counts_by_year":[{"year":2024,"cited_by_count":1}],"updated_date":"2026-08-28T12:50:07.497085","created_date":"2025-10-10T00:00:00"}