{"id":"https://openalex.org/W1562487267","doi":"https://doi.org/10.1007/978-3-642-04180-8_64","title":"Considering Unseen States as Impossible in Factored Reinforcement Learning","display_name":"Considering Unseen States as Impossible in Factored Reinforcement Learning","publication_year":2009,"publication_date":"2009-01-01","ids":{"openalex":"https://openalex.org/W1562487267","doi":"https://doi.org/10.1007/978-3-642-04180-8_64","mag":"1562487267"},"language":"en","primary_location":{"id":"doi:10.1007/978-3-642-04180-8_64","is_oa":false,"landing_page_url":"https://doi.org/10.1007/978-3-642-04180-8_64","pdf_url":null,"source":{"id":"https://openalex.org/S106296714","display_name":"Lecture notes in computer science","issn_l":"0302-9743","issn":["0302-9743","1611-3349"],"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":"book series"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Lecture Notes in Computer Science","raw_type":"book-chapter"},"type":"book-chapter","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/A5019849300","display_name":"Olga Kozlova","orcid":"https://orcid.org/0000-0002-5974-0228"},"institutions":[{"id":"https://openalex.org/I4210150358","display_name":"Institut Syst\u00e8mes Intelligents et de Robotique","ror":"https://ror.org/05neq8668","country_code":"FR","type":"facility","lineage":["https://openalex.org/I1294671590","https://openalex.org/I1294671590","https://openalex.org/I154526488","https://openalex.org/I39804081","https://openalex.org/I4210150358","https://openalex.org/I4210159245"]},{"id":"https://openalex.org/I2801356230","display_name":"Thales (Australia)","ror":"https://ror.org/00f7vya03","country_code":"AU","type":"company","lineage":["https://openalex.org/I2801356230","https://openalex.org/I4210140930"]},{"id":"https://openalex.org/I39804081","display_name":"Sorbonne Universit\u00e9","ror":"https://ror.org/02en5vm52","country_code":"FR","type":"education","lineage":["https://openalex.org/I39804081"]},{"id":"https://openalex.org/I1294671590","display_name":"Centre National de la Recherche Scientifique","ror":"https://ror.org/02feahw73","country_code":"FR","type":"funder","lineage":["https://openalex.org/I1294671590"]}],"countries":["AU","FR"],"is_corresponding":true,"raw_author_name":"Olga Kozlova","raw_affiliation_strings":["Institut des Syst\u00e8mes Intelligents et de Robotique, Universit\u00e9 Pierre et Marie Curie - Paris 6, CNRS UMR 7222, 4 place Jussieu, F-75005, Paris, France","Thales Security Solutions & Services, Simulation, 1 rue du G\u00e9n\u00e9ral de Gaulle, Osny BP 226, F95523, Cergy Pontoise, France"],"affiliations":[{"raw_affiliation_string":"Institut des Syst\u00e8mes Intelligents et de Robotique, Universit\u00e9 Pierre et Marie Curie - Paris 6, CNRS UMR 7222, 4 place Jussieu, F-75005, Paris, France","institution_ids":["https://openalex.org/I39804081","https://openalex.org/I4210150358","https://openalex.org/I1294671590"]},{"raw_affiliation_string":"Thales Security Solutions & Services, Simulation, 1 rue du G\u00e9n\u00e9ral de Gaulle, Osny BP 226, F95523, Cergy Pontoise, France","institution_ids":["https://openalex.org/I2801356230"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5042850624","display_name":"Olivier Sigaud","orcid":"https://orcid.org/0000-0002-8544-0229"},"institutions":[{"id":"https://openalex.org/I4210150358","display_name":"Institut Syst\u00e8mes Intelligents et de Robotique","ror":"https://ror.org/05neq8668","country_code":"FR","type":"facility","lineage":["https://openalex.org/I1294671590","https://openalex.org/I1294671590","https://openalex.org/I154526488","https://openalex.org/I39804081","https://openalex.org/I4210150358","https://openalex.org/I4210159245"]},{"id":"https://openalex.org/I39804081","display_name":"Sorbonne Universit\u00e9","ror":"https://ror.org/02en5vm52","country_code":"FR","type":"education","lineage":["https://openalex.org/I39804081"]},{"id":"https://openalex.org/I1294671590","display_name":"Centre National de la Recherche Scientifique","ror":"https://ror.org/02feahw73","country_code":"FR","type":"funder","lineage":["https://openalex.org/I1294671590"]}],"countries":["FR"],"is_corresponding":false,"raw_author_name":"Olivier Sigaud","raw_affiliation_strings":["Institut des Syst\u00e8mes Intelligents et de Robotique, Universit\u00e9 Pierre et Marie Curie - Paris 6, CNRS UMR 7222, 4 place Jussieu, F-75005, Paris, France"],"affiliations":[{"raw_affiliation_string":"Institut des Syst\u00e8mes Intelligents et de Robotique, Universit\u00e9 Pierre et Marie Curie - Paris 6, CNRS UMR 7222, 4 place Jussieu, F-75005, Paris, France","institution_ids":["https://openalex.org/I39804081","https://openalex.org/I4210150358","https://openalex.org/I1294671590"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5013543532","display_name":"Pierre-Henri Wuillemin","orcid":"https://orcid.org/0000-0003-3691-4886"},"institutions":[{"id":"https://openalex.org/I1294671590","display_name":"Centre National de la Recherche Scientifique","ror":"https://ror.org/02feahw73","country_code":"FR","type":"funder","lineage":["https://openalex.org/I1294671590"]},{"id":"https://openalex.org/I39804081","display_name":"Sorbonne Universit\u00e9","ror":"https://ror.org/02en5vm52","country_code":"FR","type":"education","lineage":["https://openalex.org/I39804081"]},{"id":"https://openalex.org/I4210159731","display_name":"Laboratoire de Recherche en Informatique de Paris 6","ror":"https://ror.org/05krcen59","country_code":"FR","type":"facility","lineage":["https://openalex.org/I1294671590","https://openalex.org/I1294671590","https://openalex.org/I39804081","https://openalex.org/I4210159245","https://openalex.org/I4210159731"]}],"countries":["FR"],"is_corresponding":false,"raw_author_name":"Pierre-Henri Wuillemin","raw_affiliation_strings":["Laboratoire d\u2019Informatique de Paris 6, Universit\u00e9 Pierre et Marie Curie - Paris 6, CNRS UMR 7606, 4 place Jussieu, F-75005, Paris, France","Laboratoire d'Informatique de Paris 6, Universit\u00e9 Pierre et Marie Curie - Paris 6, CNRS UMR 7606, 4 place Jussieu, F-75005, Paris, France"],"affiliations":[{"raw_affiliation_string":"Laboratoire d\u2019Informatique de Paris 6, Universit\u00e9 Pierre et Marie Curie - Paris 6, CNRS UMR 7606, 4 place Jussieu, F-75005, Paris, France","institution_ids":["https://openalex.org/I39804081","https://openalex.org/I4210159731","https://openalex.org/I1294671590"]},{"raw_affiliation_string":"Laboratoire d'Informatique de Paris 6, Universit\u00e9 Pierre et Marie Curie - Paris 6, CNRS UMR 7606, 4 place Jussieu, F-75005, Paris, France","institution_ids":["https://openalex.org/I39804081","https://openalex.org/I4210159731","https://openalex.org/I1294671590"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5027257508","display_name":"Christophe Meyer","orcid":"https://orcid.org/0000-0002-7214-9598"},"institutions":[{"id":"https://openalex.org/I4210140930","display_name":"Thales (France)","ror":"https://ror.org/04emwm605","country_code":"FR","type":"company","lineage":["https://openalex.org/I4210140930"]}],"countries":["FR"],"is_corresponding":false,"raw_author_name":"Christophe Meyer","raw_affiliation_strings":["Thales Security Solutions & Services, ThereSIS Research and Innovation Office, Campus Polytechnique 1, avenue Augustin Fresnel, 91767, Palaiseau, France"],"affiliations":[{"raw_affiliation_string":"Thales Security Solutions & Services, ThereSIS Research and Innovation Office, Campus Polytechnique 1, avenue Augustin Fresnel, 91767, Palaiseau, France","institution_ids":["https://openalex.org/I4210140930"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5019849300"],"corresponding_institution_ids":["https://openalex.org/I1294671590","https://openalex.org/I2801356230","https://openalex.org/I39804081","https://openalex.org/I4210150358"],"apc_list":{"value":5000,"currency":"EUR","value_usd":5392},"apc_paid":null,"fwci":0.2888,"has_fulltext":false,"cited_by_count":3,"citation_normalized_percentile":{"value":0.56998955,"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":"721","last_page":"735"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10462","display_name":"Reinforcement Learning in Robotics","score":0.9994000196456909,"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":0.9994000196456909,"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/T10328","display_name":"Supply Chain and Inventory Management","score":0.968500018119812,"subfield":{"id":"https://openalex.org/subfields/1404","display_name":"Management Information Systems"},"field":{"id":"https://openalex.org/fields/14","display_name":"Business, Management and Accounting"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}},{"id":"https://openalex.org/T10639","display_name":"Advanced Software Engineering Methodologies","score":0.9567000269889832,"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":0.8967033624649048},{"id":"https://openalex.org/keywords/markov-decision-process","display_name":"Markov decision process","score":0.7666913270950317},{"id":"https://openalex.org/keywords/heuristics","display_name":"Heuristics","score":0.7282071113586426},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6995742321014404},{"id":"https://openalex.org/keywords/benchmark","display_name":"Benchmark (surveying)","score":0.6810306906700134},{"id":"https://openalex.org/keywords/representation","display_name":"Representation (politics)","score":0.5278506278991699},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5153746008872986},{"id":"https://openalex.org/keywords/markov-process","display_name":"Markov process","score":0.5122813582420349},{"id":"https://openalex.org/keywords/state","display_name":"State (computer science)","score":0.47610151767730713},{"id":"https://openalex.org/keywords/random-variable","display_name":"Random variable","score":0.4438268840312958},{"id":"https://openalex.org/keywords/markov-chain","display_name":"Markov chain","score":0.4425760507583618},{"id":"https://openalex.org/keywords/mathematical-optimization","display_name":"Mathematical optimization","score":0.3632947504520416},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.280505895614624},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.23286473751068115},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.2025388479232788},{"id":"https://openalex.org/keywords/statistics","display_name":"Statistics","score":0.0615217387676239}],"concepts":[{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.8967033624649048},{"id":"https://openalex.org/C106189395","wikidata":"https://www.wikidata.org/wiki/Q176789","display_name":"Markov decision process","level":3,"score":0.7666913270950317},{"id":"https://openalex.org/C127705205","wikidata":"https://www.wikidata.org/wiki/Q5748245","display_name":"Heuristics","level":2,"score":0.7282071113586426},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6995742321014404},{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.6810306906700134},{"id":"https://openalex.org/C2776359362","wikidata":"https://www.wikidata.org/wiki/Q2145286","display_name":"Representation (politics)","level":3,"score":0.5278506278991699},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5153746008872986},{"id":"https://openalex.org/C159886148","wikidata":"https://www.wikidata.org/wiki/Q176645","display_name":"Markov process","level":2,"score":0.5122813582420349},{"id":"https://openalex.org/C48103436","wikidata":"https://www.wikidata.org/wiki/Q599031","display_name":"State (computer science)","level":2,"score":0.47610151767730713},{"id":"https://openalex.org/C122123141","wikidata":"https://www.wikidata.org/wiki/Q176623","display_name":"Random variable","level":2,"score":0.4438268840312958},{"id":"https://openalex.org/C98763669","wikidata":"https://www.wikidata.org/wiki/Q176645","display_name":"Markov chain","level":2,"score":0.4425760507583618},{"id":"https://openalex.org/C126255220","wikidata":"https://www.wikidata.org/wiki/Q141495","display_name":"Mathematical optimization","level":1,"score":0.3632947504520416},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.280505895614624},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.23286473751068115},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.2025388479232788},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.0615217387676239},{"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/C94625758","wikidata":"https://www.wikidata.org/wiki/Q7163","display_name":"Politics","level":2,"score":0.0},{"id":"https://openalex.org/C199539241","wikidata":"https://www.wikidata.org/wiki/Q7748","display_name":"Law","level":1,"score":0.0},{"id":"https://openalex.org/C13280743","wikidata":"https://www.wikidata.org/wiki/Q131089","display_name":"Geodesy","level":1,"score":0.0},{"id":"https://openalex.org/C17744445","wikidata":"https://www.wikidata.org/wiki/Q36442","display_name":"Political science","level":0,"score":0.0},{"id":"https://openalex.org/C205649164","wikidata":"https://www.wikidata.org/wiki/Q1071","display_name":"Geography","level":0,"score":0.0}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.1007/978-3-642-04180-8_64","is_oa":false,"landing_page_url":"https://doi.org/10.1007/978-3-642-04180-8_64","pdf_url":null,"source":{"id":"https://openalex.org/S106296714","display_name":"Lecture notes in computer science","issn_l":"0302-9743","issn":["0302-9743","1611-3349"],"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":"book series"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Lecture Notes in Computer Science","raw_type":"book-chapter"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.640.645","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.640.645","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://www.isir.upmc.fr/files/57810721.pdf","raw_type":"text"},{"id":"pmh:oai:HAL:hal-01296687v1","is_oa":false,"landing_page_url":"https://hal.science/hal-01296687","pdf_url":null,"source":{"id":"https://openalex.org/S4306402512","display_name":"HAL (Le Centre pour la Communication Scientifique Directe)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I1294671590","host_organization_name":"Centre National de la Recherche Scientifique","host_organization_lineage":["https://openalex.org/I1294671590"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"European Conference on Machine Learning, Sep 2009, Bled, Slovenia. pp.721-735, &#x27E8;10.1007/978-3-642-04180-8_64&#x27E9;","raw_type":"Conference papers"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/16","display_name":"Peace, Justice and strong institutions","score":0.8299999833106995}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":18,"referenced_works":["https://openalex.org/W1491961724","https://openalex.org/W1515851193","https://openalex.org/W1530444831","https://openalex.org/W1535392723","https://openalex.org/W1650504995","https://openalex.org/W1926561559","https://openalex.org/W1980035368","https://openalex.org/W1997477668","https://openalex.org/W2020294948","https://openalex.org/W2031594824","https://openalex.org/W2112841646","https://openalex.org/W2121863487","https://openalex.org/W2131660762","https://openalex.org/W2138186376","https://openalex.org/W2144744117","https://openalex.org/W2170400507","https://openalex.org/W3103882218","https://openalex.org/W4214717370"],"related_works":["https://openalex.org/W4400868993","https://openalex.org/W3096874164","https://openalex.org/W1985560493","https://openalex.org/W2386410636","https://openalex.org/W2357975469","https://openalex.org/W2145363145","https://openalex.org/W1626977535","https://openalex.org/W2341346307","https://openalex.org/W3168977894","https://openalex.org/W2315999538"],"abstract_inverted_index":null,"counts_by_year":[{"year":2016,"cited_by_count":1},{"year":2014,"cited_by_count":1}],"updated_date":"2026-04-05T17:49:38.594831","created_date":"2025-10-10T00:00:00"}
