{"id":"https://openalex.org/W2556090351","doi":"https://doi.org/10.1109/ijcnn.2016.7727695","title":"Advantage based value iteration for Markov decision processes with unknown rewards","display_name":"Advantage based value iteration for Markov decision processes with unknown rewards","publication_year":2016,"publication_date":"2016-07-01","ids":{"openalex":"https://openalex.org/W2556090351","doi":"https://doi.org/10.1109/ijcnn.2016.7727695","mag":"2556090351"},"language":"en","primary_location":{"id":"doi:10.1109/ijcnn.2016.7727695","is_oa":false,"landing_page_url":"https://doi.org/10.1109/ijcnn.2016.7727695","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2016 International Joint Conference on Neural Networks (IJCNN)","raw_type":"proceedings-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/A5027553821","display_name":"Pegah Alizadeh","orcid":"https://orcid.org/0000-0002-7231-5840"},"institutions":[{"id":"https://openalex.org/I4210091279","display_name":"Universit\u00e9 Sorbonne Paris Nord","ror":"https://ror.org/0199hds37","country_code":"FR","type":"education","lineage":["https://openalex.org/I4210091279"]}],"countries":["FR"],"is_corresponding":true,"raw_author_name":"Pegah Alizadeh","raw_affiliation_strings":["Institut Galil\u00e8e - Universit\u00e8 Paris 1399, Villetaneuse, France"],"affiliations":[{"raw_affiliation_string":"Institut Galil\u00e8e - Universit\u00e8 Paris 1399, Villetaneuse, France","institution_ids":["https://openalex.org/I4210091279"]}]},{"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/I4210091279","display_name":"Universit\u00e9 Sorbonne Paris Nord","ror":"https://ror.org/0199hds37","country_code":"FR","type":"education","lineage":["https://openalex.org/I4210091279"]}],"countries":["FR"],"is_corresponding":false,"raw_author_name":"Yann Chevaleyre","raw_affiliation_strings":["Institut Galil\u00e8e - Universit\u00e8 Paris 1399, Villetaneuse, France"],"affiliations":[{"raw_affiliation_string":"Institut Galil\u00e8e - Universit\u00e8 Paris 1399, Villetaneuse, France","institution_ids":["https://openalex.org/I4210091279"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5109365127","display_name":"Fran\u00e7ois L\u00e9vy","orcid":null},"institutions":[{"id":"https://openalex.org/I4210091279","display_name":"Universit\u00e9 Sorbonne Paris Nord","ror":"https://ror.org/0199hds37","country_code":"FR","type":"education","lineage":["https://openalex.org/I4210091279"]}],"countries":["FR"],"is_corresponding":false,"raw_author_name":"Francois Levy","raw_affiliation_strings":["Institut Galil\u00e8e - Universit\u00e8 Paris 1399, Villetaneuse, France"],"affiliations":[{"raw_affiliation_string":"Institut Galil\u00e8e - Universit\u00e8 Paris 1399, Villetaneuse, France","institution_ids":["https://openalex.org/I4210091279"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5027553821"],"corresponding_institution_ids":["https://openalex.org/I4210091279"],"apc_list":null,"apc_paid":null,"fwci":0.8569,"has_fulltext":false,"cited_by_count":5,"citation_normalized_percentile":{"value":0.84553885,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":94},"biblio":{"volume":null,"issue":null,"first_page":"3837","last_page":"3844"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10462","display_name":"Reinforcement Learning in Robotics","score":0.9998999834060669,"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":0.9998999834060669,"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/T10142","display_name":"Formal Methods in Verification","score":0.9958000183105469,"subfield":{"id":"https://openalex.org/subfields/1703","display_name":"Computational Theory and Mathematics"},"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/T10791","display_name":"Advanced Control Systems Optimization","score":0.9937999844551086,"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/markov-decision-process","display_name":"Markov decision process","score":0.9278427362442017},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7726517915725708},{"id":"https://openalex.org/keywords/value","display_name":"Value (mathematics)","score":0.6307677626609802},{"id":"https://openalex.org/keywords/markov-process","display_name":"Markov process","score":0.565037190914154},{"id":"https://openalex.org/keywords/mathematical-optimization","display_name":"Mathematical optimization","score":0.5136575102806091},{"id":"https://openalex.org/keywords/process","display_name":"Process (computing)","score":0.5069356560707092},{"id":"https://openalex.org/keywords/markov-chain","display_name":"Markov chain","score":0.46966469287872314},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.2585740089416504},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.1748369038105011}],"concepts":[{"id":"https://openalex.org/C106189395","wikidata":"https://www.wikidata.org/wiki/Q176789","display_name":"Markov decision process","level":3,"score":0.9278427362442017},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7726517915725708},{"id":"https://openalex.org/C2776291640","wikidata":"https://www.wikidata.org/wiki/Q2912517","display_name":"Value (mathematics)","level":2,"score":0.6307677626609802},{"id":"https://openalex.org/C159886148","wikidata":"https://www.wikidata.org/wiki/Q176645","display_name":"Markov process","level":2,"score":0.565037190914154},{"id":"https://openalex.org/C126255220","wikidata":"https://www.wikidata.org/wiki/Q141495","display_name":"Mathematical optimization","level":1,"score":0.5136575102806091},{"id":"https://openalex.org/C98045186","wikidata":"https://www.wikidata.org/wiki/Q205663","display_name":"Process (computing)","level":2,"score":0.5069356560707092},{"id":"https://openalex.org/C98763669","wikidata":"https://www.wikidata.org/wiki/Q176645","display_name":"Markov chain","level":2,"score":0.46966469287872314},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.2585740089416504},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.1748369038105011},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.0},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/ijcnn.2016.7727695","is_oa":false,"landing_page_url":"https://doi.org/10.1109/ijcnn.2016.7727695","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2016 International Joint Conference on Neural Networks (IJCNN)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/16","score":0.7200000286102295,"display_name":"Peace, Justice and strong institutions"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":17,"referenced_works":["https://openalex.org/W9932698","https://openalex.org/W107583932","https://openalex.org/W115994101","https://openalex.org/W1541317966","https://openalex.org/W1999874108","https://openalex.org/W2058066080","https://openalex.org/W2061562262","https://openalex.org/W2113351146","https://openalex.org/W2120518702","https://openalex.org/W2201483316","https://openalex.org/W2334782222","https://openalex.org/W2405100124","https://openalex.org/W4241521318","https://openalex.org/W6600390444","https://openalex.org/W6604623309","https://openalex.org/W6650265722","https://openalex.org/W6713597259"],"related_works":["https://openalex.org/W1660242800","https://openalex.org/W2379651310","https://openalex.org/W2113019827","https://openalex.org/W1541249122","https://openalex.org/W2413828414","https://openalex.org/W2315999538","https://openalex.org/W2367222340","https://openalex.org/W187740018","https://openalex.org/W2162286586","https://openalex.org/W4255368532"],"abstract_inverted_index":{"This":[0,44],"paper":[1],"addresses":[2],"approximating":[3],"the":[4,40,51,62,76,83],"optimal":[5],"policy":[6],"in":[7],"Markov":[8],"Decision":[9],"Process":[10],"with":[11,60],"unknown":[12],"rewards.":[13],"The":[14],"MDP":[15,21],"is":[16,32,73],"transformed":[17],"into":[18],"a":[19,25],"Vector-Valued":[20],"(VVMDP).":[22],"We":[23,56],"introduce":[24],"new":[26],"interactive":[27],"algorithm":[28,45,79],"ABVI,":[29],"whose":[30],"principle":[31],"using":[33],"value":[34,58,77],"iteration":[35,59,78],"on":[36],"VVMDPs":[37],"and":[38,80],"querying":[39,61],"user":[41,63],"when":[42],"necessary.":[43],"uses":[46],"classification":[47],"method":[48],"to":[49,64,74,81],"reduce":[50,82],"number":[52,84],"of":[53,85],"proposed":[54],"queries.":[55,86],"integrate":[57],"select":[65],"appropriate":[66],"backups.":[67],"In":[68],"this":[69],"paper,":[70],"our":[71],"goal":[72],"accelerate":[75]},"counts_by_year":[{"year":2022,"cited_by_count":1},{"year":2021,"cited_by_count":1},{"year":2020,"cited_by_count":1},{"year":2019,"cited_by_count":1},{"year":2016,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}