{"id":"https://openalex.org/W4312206822","doi":"https://doi.org/10.3233/ia-220140","title":"A unified view of configurable Markov Decision Processes: Solution concepts, value functions, and operators","display_name":"A unified view of configurable Markov Decision Processes: Solution concepts, value functions, and operators","publication_year":2022,"publication_date":"2022-12-27","ids":{"openalex":"https://openalex.org/W4312206822","doi":"https://doi.org/10.3233/ia-220140"},"language":"en","primary_location":{"id":"doi:10.3233/ia-220140","is_oa":false,"landing_page_url":"https://doi.org/10.3233/ia-220140","pdf_url":null,"source":{"id":"https://openalex.org/S207922018","display_name":"Intelligenza Artificiale","issn_l":"1724-8035","issn":["1724-8035","2211-0097"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310318577","host_organization_name":"IOS Press","host_organization_lineage":["https://openalex.org/P4310318577"],"host_organization_lineage_names":["IOS Press"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Intelligenza Artificiale: The international journal of the AIxIA","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/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, Piazza Leonardo da Vinci, 32, Milan, Italy"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Dipartimento di Elettronica, Informazione e Bioingegneria, Politecnico di Milano, Piazza Leonardo da Vinci, 32, Milan, 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":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.14264276,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":"16","issue":"2","first_page":"165","last_page":"184"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10462","display_name":"Reinforcement Learning in Robotics","score":0.9962999820709229,"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":0.9962999820709229,"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/T10639","display_name":"Advanced Software Engineering Methodologies","score":0.9815999865531921,"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/T11195","display_name":"Simulation Techniques and Applications","score":0.9722999930381775,"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/markov-decision-process","display_name":"Markov decision process","score":0.8950885534286499},{"id":"https://openalex.org/keywords/configurator","display_name":"Configurator","score":0.8400157690048218},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7214433550834656},{"id":"https://openalex.org/keywords/process","display_name":"Process (computing)","score":0.5510256886482239},{"id":"https://openalex.org/keywords/partially-observable-markov-decision-process","display_name":"Partially observable Markov decision process","score":0.5252432823181152},{"id":"https://openalex.org/keywords/value","display_name":"Value (mathematics)","score":0.5160786509513855},{"id":"https://openalex.org/keywords/markov-process","display_name":"Markov process","score":0.4763615131378174},{"id":"https://openalex.org/keywords/markov-chain","display_name":"Markov chain","score":0.46584710478782654},{"id":"https://openalex.org/keywords/mathematical-optimization","display_name":"Mathematical optimization","score":0.4340742230415344},{"id":"https://openalex.org/keywords/extension","display_name":"Extension (predicate logic)","score":0.41591233015060425},{"id":"https://openalex.org/keywords/markov-model","display_name":"Markov model","score":0.3268893361091614},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.16716167330741882},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.1478303074836731},{"id":"https://openalex.org/keywords/programming-language","display_name":"Programming language","score":0.10553237795829773}],"concepts":[{"id":"https://openalex.org/C106189395","wikidata":"https://www.wikidata.org/wiki/Q176789","display_name":"Markov decision process","level":3,"score":0.8950885534286499},{"id":"https://openalex.org/C2777210712","wikidata":"https://www.wikidata.org/wiki/Q15221050","display_name":"Configurator","level":2,"score":0.8400157690048218},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7214433550834656},{"id":"https://openalex.org/C98045186","wikidata":"https://www.wikidata.org/wiki/Q205663","display_name":"Process (computing)","level":2,"score":0.5510256886482239},{"id":"https://openalex.org/C17098449","wikidata":"https://www.wikidata.org/wiki/Q176814","display_name":"Partially observable Markov decision process","level":4,"score":0.5252432823181152},{"id":"https://openalex.org/C2776291640","wikidata":"https://www.wikidata.org/wiki/Q2912517","display_name":"Value (mathematics)","level":2,"score":0.5160786509513855},{"id":"https://openalex.org/C159886148","wikidata":"https://www.wikidata.org/wiki/Q176645","display_name":"Markov process","level":2,"score":0.4763615131378174},{"id":"https://openalex.org/C98763669","wikidata":"https://www.wikidata.org/wiki/Q176645","display_name":"Markov chain","level":2,"score":0.46584710478782654},{"id":"https://openalex.org/C126255220","wikidata":"https://www.wikidata.org/wiki/Q141495","display_name":"Mathematical optimization","level":1,"score":0.4340742230415344},{"id":"https://openalex.org/C2778029271","wikidata":"https://www.wikidata.org/wiki/Q5421931","display_name":"Extension (predicate logic)","level":2,"score":0.41591233015060425},{"id":"https://openalex.org/C163836022","wikidata":"https://www.wikidata.org/wiki/Q6771326","display_name":"Markov model","level":3,"score":0.3268893361091614},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.16716167330741882},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.1478303074836731},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.10553237795829773},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.0},{"id":"https://openalex.org/C144133560","wikidata":"https://www.wikidata.org/wiki/Q4830453","display_name":"Business","level":0,"score":0.0},{"id":"https://openalex.org/C162853370","wikidata":"https://www.wikidata.org/wiki/Q39809","display_name":"Marketing","level":1,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.3233/ia-220140","is_oa":false,"landing_page_url":"https://doi.org/10.3233/ia-220140","pdf_url":null,"source":{"id":"https://openalex.org/S207922018","display_name":"Intelligenza Artificiale","issn_l":"1724-8035","issn":["1724-8035","2211-0097"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310318577","host_organization_name":"IOS Press","host_organization_lineage":["https://openalex.org/P4310318577"],"host_organization_lineage_names":["IOS Press"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Intelligenza Artificiale: The international journal of the AIxIA","raw_type":"journal-article"},{"id":"pmh:oai:re.public.polimi.it:11311/1230383","is_oa":false,"landing_page_url":"https://hdl.handle.net/11311/1230383","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/article"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Peace, Justice and strong institutions","score":0.44999998807907104,"id":"https://metadata.un.org/sdg/16"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":23,"referenced_works":["https://openalex.org/W76132677","https://openalex.org/W1496672808","https://openalex.org/W1971309210","https://openalex.org/W1980516134","https://openalex.org/W2012547817","https://openalex.org/W2030659867","https://openalex.org/W2103104707","https://openalex.org/W2145339207","https://openalex.org/W2168405694","https://openalex.org/W2344786740","https://openalex.org/W2575731723","https://openalex.org/W2739535217","https://openalex.org/W2903013229","https://openalex.org/W2907537824","https://openalex.org/W2965394911","https://openalex.org/W2972448932","https://openalex.org/W2998066995","https://openalex.org/W3037429136","https://openalex.org/W3111509061","https://openalex.org/W3187974874","https://openalex.org/W3196519516","https://openalex.org/W4206638449","https://openalex.org/W4234761190"],"related_works":["https://openalex.org/W2096013579","https://openalex.org/W52153049","https://openalex.org/W1760611253","https://openalex.org/W1515117609","https://openalex.org/W1589140671","https://openalex.org/W4323315247","https://openalex.org/W2294884454","https://openalex.org/W3169161914","https://openalex.org/W4321379664","https://openalex.org/W2211790881"],"abstract_inverted_index":{"In":[0],"this":[1,115],"paper,":[2],"we":[3,62,94,100],"provide":[4],"a":[5,56],"unified":[6],"presentation":[7],"of":[8,21,59],"the":[9,22,30,45,66,70,76,105],"Configurable":[10],"Markov":[11,24],"Decision":[12,25],"Process":[13,26],"(Conf-MDP)":[14],"framework.":[15,117],"A":[16],"Conf-MDP":[17],"is":[18,72],"an":[19,51],"extension":[20],"traditional":[23,106],"(MDP)":[27],"that":[28],"models":[29],"possibility":[31],"to":[32,75,103,114],"configure":[33],"some":[34],"environmental":[35],"parameters.":[36],"This":[37],"configuration":[38,71],"activity":[39],"can":[40],"be":[41],"carried":[42],"out":[43],"by":[44,50],"learning":[46],"agent":[47,84],"itself":[48],"or":[49],"external":[52],"configurator.":[53],"We":[54],"introduce":[55],"general":[57],"definition":[58],"Conf-MDP,":[60],"then":[61],"particularize":[63],"it":[64],"for":[65,109],"cooperative":[67],"setting,":[68,81],"where":[69],"fully":[73],"functional":[74],"agent\u2019s":[77],"goals,":[78],"and":[79,85,111],"non-cooperative":[80],"in":[82],"which":[83],"configurator":[86],"might":[87],"have":[88],"different":[89],"interests.":[90],"For":[91],"both":[92],"settings,":[93],"propose":[95],"suitable":[96],"solution":[97],"concepts.":[98],"Furthermore,":[99],"illustrate":[101],"how":[102],"extend":[104],"value":[107],"functions":[108],"MDPs":[110],"Bellman":[112],"operators":[113],"new":[116]},"counts_by_year":[],"updated_date":"2026-05-03T06:03:33.228499","created_date":"2023-01-04T00:00:00"}