{"id":"https://openalex.org/W2573105523","doi":"https://doi.org/10.3233/978-1-61499-682-8-15","title":"Solving MDPs with Unknown Rewards Using Nondominated Vector-Valued Functions","display_name":"Solving MDPs with Unknown Rewards Using Nondominated Vector-Valued Functions","publication_year":2016,"publication_date":"2016-01-01","ids":{"openalex":"https://openalex.org/W2573105523","doi":"https://doi.org/10.3233/978-1-61499-682-8-15","mag":"2573105523"},"language":"en","primary_location":{"id":"doi:10.3233/978-1-61499-682-8-15","is_oa":true,"landing_page_url":"https://doi.org/10.3233/978-1-61499-682-8-15","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":"cc-by-nc","license_id":"https://openalex.org/licenses/cc-by-nc","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":true,"oa_status":"hybrid","oa_url":"https://doi.org/10.3233/978-1-61499-682-8-15","any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5027553821","display_name":"Pegah Alizadeh","orcid":"https://orcid.org/0000-0002-7231-5840"},"institutions":[{"id":"https://openalex.org/I204730241","display_name":"Universit\u00e9 Paris Cit\u00e9","ror":"https://ror.org/05f82e368","country_code":"FR","type":"education","lineage":["https://openalex.org/I204730241"]}],"countries":["FR"],"is_corresponding":false,"raw_author_name":"Alizadeh Pegah","raw_affiliation_strings":["Universit\u00e9 Paris Cit\u00e9, Paris, France"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Universit\u00e9 Paris Cit\u00e9, Paris, France","institution_ids":["https://openalex.org/I204730241"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5081034810","display_name":"Yann Chevaleyre","orcid":"https://orcid.org/0000-0002-6609-5562"},"institutions":[{"id":"https://openalex.org/I204730241","display_name":"Universit\u00e9 Paris Cit\u00e9","ror":"https://ror.org/05f82e368","country_code":"FR","type":"education","lineage":["https://openalex.org/I204730241"]}],"countries":["FR"],"is_corresponding":false,"raw_author_name":"Chevaleyre Yann","raw_affiliation_strings":["Universit\u00e9 Paris Cit\u00e9, Paris, France"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Universit\u00e9 Paris Cit\u00e9, Paris, France","institution_ids":["https://openalex.org/I204730241"]}]},{"author_position":"last","author":{"id":null,"display_name":"Lévy François","orcid":null},"institutions":[{"id":"https://openalex.org/I204730241","display_name":"Universit\u00e9 Paris Cit\u00e9","ror":"https://ror.org/05f82e368","country_code":"FR","type":"education","lineage":["https://openalex.org/I204730241"]}],"countries":["FR"],"is_corresponding":false,"raw_author_name":"Lévy François","raw_affiliation_strings":["Universit\u00e9 Paris Cit\u00e9, Paris, France"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Universit\u00e9 Paris Cit\u00e9, Paris, France","institution_ids":["https://openalex.org/I204730241"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.3389,"has_fulltext":false,"cited_by_count":1,"citation_normalized_percentile":{"value":0.62330285,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":94},"biblio":{"volume":null,"issue":null,"first_page":"15","last_page":"26"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10462","display_name":"Reinforcement Learning in Robotics","score":0.9980000257492065,"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":0.9980000257492065,"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/T10603","display_name":"Smart Grid Energy Management","score":0.9961000084877014,"subfield":{"id":"https://openalex.org/subfields/2208","display_name":"Electrical and Electronic Engineering"},"field":{"id":"https://openalex.org/fields/22","display_name":"Engineering"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T10791","display_name":"Advanced Control Systems Optimization","score":0.9919999837875366,"subfield":{"id":"https://openalex.org/subfields/2207","display_name":"Control and Systems Engineering"},"field":{"id":"https://openalex.org/fields/22","display_name":"Engineering"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/mathematical-optimization","display_name":"Mathematical optimization","score":0.5308467149734497},{"id":"https://openalex.org/keywords/vector","display_name":"Vector (molecular biology)","score":0.4748975336551666},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.465107262134552},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.3842449486255646},{"id":"https://openalex.org/keywords/biology","display_name":"Biology","score":0.23863494396209717},{"id":"https://openalex.org/keywords/biochemistry","display_name":"Biochemistry","score":0.0415097177028656},{"id":"https://openalex.org/keywords/recombinant-dna","display_name":"Recombinant DNA","score":0.03156888484954834}],"concepts":[{"id":"https://openalex.org/C126255220","wikidata":"https://www.wikidata.org/wiki/Q141495","display_name":"Mathematical optimization","level":1,"score":0.5308467149734497},{"id":"https://openalex.org/C92087593","wikidata":"https://www.wikidata.org/wiki/Q427389","display_name":"Vector (molecular biology)","level":4,"score":0.4748975336551666},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.465107262134552},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.3842449486255646},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.23863494396209717},{"id":"https://openalex.org/C55493867","wikidata":"https://www.wikidata.org/wiki/Q7094","display_name":"Biochemistry","level":1,"score":0.0415097177028656},{"id":"https://openalex.org/C40767141","wikidata":"https://www.wikidata.org/wiki/Q285697","display_name":"Recombinant DNA","level":3,"score":0.03156888484954834},{"id":"https://openalex.org/C104317684","wikidata":"https://www.wikidata.org/wiki/Q7187","display_name":"Gene","level":2,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.3233/978-1-61499-682-8-15","is_oa":true,"landing_page_url":"https://doi.org/10.3233/978-1-61499-682-8-15","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":"cc-by-nc","license_id":"https://openalex.org/licenses/cc-by-nc","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Frontiers in Artificial Intelligence and Applications","raw_type":"book-chapter"},{"id":"mag:2573105523","is_oa":false,"landing_page_url":"https://dblp.uni-trier.de/db/conf/stairs/stairs2016.html#AlizadehCL16","pdf_url":null,"source":{"id":"https://openalex.org/S4306420941","display_name":"Starting AI Researchers' Symposium","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":"conference"},"license":null,"license_id":null,"version":null,"is_accepted":false,"is_published":null,"raw_source_name":"Starting AI Researchers' Symposium","raw_type":null}],"best_oa_location":{"id":"doi:10.3233/978-1-61499-682-8-15","is_oa":true,"landing_page_url":"https://doi.org/10.3233/978-1-61499-682-8-15","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":"cc-by-nc","license_id":"https://openalex.org/licenses/cc-by-nc","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Frontiers in Artificial Intelligence and Applications","raw_type":"book-chapter"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":8,"referenced_works":["https://openalex.org/W9932698","https://openalex.org/W115994101","https://openalex.org/W1541317966","https://openalex.org/W2119567691","https://openalex.org/W2120518702","https://openalex.org/W2155817812","https://openalex.org/W2405100124","https://openalex.org/W2556090351"],"related_works":["https://openalex.org/W2899084033","https://openalex.org/W2748952813","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"],"abstract_inverted_index":{"This":[0],"paper":[1],"addresses":[2],"vectorial":[3,99],"form":[4],"of":[5,31,41,51,67,94,113,117],"Markov":[6],"Decision":[7],"Processes":[8],"(MDPs)":[9],"to":[10,18,28,61,70,109,143],"solve":[11],"MDPs":[12,101],"with":[13,64,83],"unknown":[14],"rewards.":[15],"Our":[16],"method":[17],"find":[19],"optimal":[20,86,123,140],"strategies":[21],"is":[22,38,48],"based":[23,102],"on":[24,98,103],"reducing":[25],"the":[26,29,39,46,49,111,149],"computation":[27],"determination":[30],"two":[32],"separate":[33],"polytopes.":[34],"The":[35],"first":[36],"one":[37],"set":[40,50,66,112,137],"admissible":[42,52],"vector-valued":[43],"functions":[44],"and":[45],"second":[47],"weight":[53,56,150],"vectors.":[54],"Unknown":[55],"vectors":[57],"are":[58],"discovered":[59],"according":[60,142],"an":[62,131,138],"agent":[63],"a":[65,92],"preferences.":[68,119],"Contrary":[69],"most":[71],"existing":[72],"algorithms":[73],"for":[74,133],"reward-uncertain":[75],"MDPs,":[76],"our":[77],"approach":[78],"does":[79],"not":[80],"require":[81],"interactions":[82],"user":[84,118,144],"during":[85],"policies":[87,115],"generation.":[88],"Instead,":[89],"we":[90,129],"use":[91],"variant":[93],"approximate":[95,110],"value":[96,100],"iteration":[97],"classifying":[104],"advantages,":[105],"that":[106],"allows":[107],"us":[108],"non-dominated":[114],"regardless":[116],"Since":[120],"any":[121],"agent's":[122],"policy":[124,141],"comes":[125],"from":[126],"this":[127,136],"set,":[128],"propose":[130],"algorithm":[132],"discovering":[134],"in":[135],"approximated":[139],"priorities":[145],"while":[146],"narrowing":[147],"interactively":[148],"polytope.":[151]},"counts_by_year":[{"year":2018,"cited_by_count":1}],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2017-01-26T00:00:00"}