{"id":"https://openalex.org/W1966238688","doi":"https://doi.org/10.1109/siu.2013.6531412","title":"Sequential Monte Carlo samplers for model-based reinforcement learning","display_name":"Sequential Monte Carlo samplers for model-based reinforcement learning","publication_year":2013,"publication_date":"2013-04-01","ids":{"openalex":"https://openalex.org/W1966238688","doi":"https://doi.org/10.1109/siu.2013.6531412","mag":"1966238688"},"language":"en","primary_location":{"id":"doi:10.1109/siu.2013.6531412","is_oa":false,"landing_page_url":"https://doi.org/10.1109/siu.2013.6531412","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2013 21st Signal Processing and Communications Applications Conference (SIU)","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/A5055657271","display_name":"Orhan S\u00f6nmez","orcid":null},"institutions":[{"id":"https://openalex.org/I4405392","display_name":"Bo\u011fazi\u00e7i University","ror":"https://ror.org/03z9tma90","country_code":"TR","type":"education","lineage":["https://openalex.org/I4405392"]}],"countries":["TR"],"is_corresponding":true,"raw_author_name":"O. Sonmez","raw_affiliation_strings":["Bilgisayar M\u00fchendisli\u011fi B\u00f6l\u00fcm\u00fc, Bo\u011fazi\u00e7i \u00dcniversitesi, Istanbul, Turkey","Bilgisayar Muhendisligi Bolumu, Bogazici Univ., Istanbul, Turkey"],"affiliations":[{"raw_affiliation_string":"Bilgisayar M\u00fchendisli\u011fi B\u00f6l\u00fcm\u00fc, Bo\u011fazi\u00e7i \u00dcniversitesi, Istanbul, Turkey","institution_ids":["https://openalex.org/I4405392"]},{"raw_affiliation_string":"Bilgisayar Muhendisligi Bolumu, Bogazici Univ., Istanbul, Turkey","institution_ids":["https://openalex.org/I4405392"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5064633247","display_name":"Ali Taylan Cemgil","orcid":"https://orcid.org/0000-0003-4463-8455"},"institutions":[{"id":"https://openalex.org/I4405392","display_name":"Bo\u011fazi\u00e7i University","ror":"https://ror.org/03z9tma90","country_code":"TR","type":"education","lineage":["https://openalex.org/I4405392"]}],"countries":["TR"],"is_corresponding":false,"raw_author_name":"A. T. Cemgil","raw_affiliation_strings":["Bilgisayar M\u00fchendisli\u011fi B\u00f6l\u00fcm\u00fc, Bo\u011fazi\u00e7i \u00dcniversitesi, Istanbul, Turkey","Bilgisayar Muhendisligi Bolumu, Bogazici Univ., Istanbul, Turkey"],"affiliations":[{"raw_affiliation_string":"Bilgisayar M\u00fchendisli\u011fi B\u00f6l\u00fcm\u00fc, Bo\u011fazi\u00e7i \u00dcniversitesi, Istanbul, Turkey","institution_ids":["https://openalex.org/I4405392"]},{"raw_affiliation_string":"Bilgisayar Muhendisligi Bolumu, Bogazici Univ., Istanbul, Turkey","institution_ids":["https://openalex.org/I4405392"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5055657271"],"corresponding_institution_ids":["https://openalex.org/I4405392"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":2,"citation_normalized_percentile":{"value":0.05391183,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":95},"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"4"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10462","display_name":"Reinforcement Learning in Robotics","score":0.9990000128746033,"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":0.9990000128746033,"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/T10848","display_name":"Advanced Multi-Objective Optimization Algorithms","score":0.993399977684021,"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/T11195","display_name":"Simulation Techniques and Applications","score":0.9919000267982483,"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/reinforcement-learning","display_name":"Reinforcement learning","score":0.781899094581604},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6767300367355347},{"id":"https://openalex.org/keywords/monte-carlo-method","display_name":"Monte Carlo method","score":0.6531465649604797},{"id":"https://openalex.org/keywords/mathematical-optimization","display_name":"Mathematical optimization","score":0.6485235095024109},{"id":"https://openalex.org/keywords/maximization","display_name":"Maximization","score":0.6233370304107666},{"id":"https://openalex.org/keywords/probabilistic-logic","display_name":"Probabilistic logic","score":0.5589174032211304},{"id":"https://openalex.org/keywords/benchmark","display_name":"Benchmark (surveying)","score":0.541823148727417},{"id":"https://openalex.org/keywords/inference","display_name":"Inference","score":0.4412803053855896},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.3933406472206116},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.3670819401741028},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.25098609924316406},{"id":"https://openalex.org/keywords/statistics","display_name":"Statistics","score":0.0706256628036499}],"concepts":[{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.781899094581604},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6767300367355347},{"id":"https://openalex.org/C19499675","wikidata":"https://www.wikidata.org/wiki/Q232207","display_name":"Monte Carlo method","level":2,"score":0.6531465649604797},{"id":"https://openalex.org/C126255220","wikidata":"https://www.wikidata.org/wiki/Q141495","display_name":"Mathematical optimization","level":1,"score":0.6485235095024109},{"id":"https://openalex.org/C2776330181","wikidata":"https://www.wikidata.org/wiki/Q18358244","display_name":"Maximization","level":2,"score":0.6233370304107666},{"id":"https://openalex.org/C49937458","wikidata":"https://www.wikidata.org/wiki/Q2599292","display_name":"Probabilistic logic","level":2,"score":0.5589174032211304},{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.541823148727417},{"id":"https://openalex.org/C2776214188","wikidata":"https://www.wikidata.org/wiki/Q408386","display_name":"Inference","level":2,"score":0.4412803053855896},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3933406472206116},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.3670819401741028},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.25098609924316406},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.0706256628036499},{"id":"https://openalex.org/C205649164","wikidata":"https://www.wikidata.org/wiki/Q1071","display_name":"Geography","level":0,"score":0.0},{"id":"https://openalex.org/C13280743","wikidata":"https://www.wikidata.org/wiki/Q131089","display_name":"Geodesy","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/siu.2013.6531412","is_oa":false,"landing_page_url":"https://doi.org/10.1109/siu.2013.6531412","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2013 21st Signal Processing and Communications Applications Conference (SIU)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":11,"referenced_works":["https://openalex.org/W2098432798","https://openalex.org/W2121863487","https://openalex.org/W2122111042","https://openalex.org/W2123157758","https://openalex.org/W2147357149","https://openalex.org/W2520735695","https://openalex.org/W2963247855","https://openalex.org/W4214717370","https://openalex.org/W4386294121","https://openalex.org/W6630596490","https://openalex.org/W6727001741"],"related_works":["https://openalex.org/W2378211422","https://openalex.org/W4321353415","https://openalex.org/W2745001401","https://openalex.org/W2130974462","https://openalex.org/W2028665553","https://openalex.org/W2086519370","https://openalex.org/W4246352526","https://openalex.org/W2121910908","https://openalex.org/W915438175","https://openalex.org/W2163814182"],"abstract_inverted_index":{"Reinforcement":[0],"learning":[1,75],"problems":[2],"are":[3],"generally":[4],"solved":[5],"by":[6],"using":[7],"fixed-point":[8],"iterations":[9],"that":[10,44],"converge":[11],"to":[12,24,57],"the":[13,59],"suboptimal":[14],"solutions":[15],"of":[16],"Bellman":[17],"equations.":[18],"However,":[19],"it":[20],"is":[21,71],"also":[22],"possible":[23],"formalize":[25],"this":[26],"problem":[27,33,69],"as":[28],"an":[29,41],"equivalent":[30],"likelihood":[31],"maximization":[32],"and":[34],"employ":[35],"probabilistic":[36],"inference":[37],"methods.":[38],"We":[39],"proposed":[40],"expectation-maximization":[42],"algorithm":[43,66],"utilizes":[45],"sequential":[46],"Monte":[47],"Carlo":[48],"samplers":[49],"with":[50],"Metropolis-Hastings":[51],"kernels":[52],"in":[53],"its":[54],"expectation":[55],"step":[56],"solve":[58],"model-based":[60],"version.":[61],"Then,":[62],"we":[63],"evaluate":[64],"our":[65],"on":[67],"mountain-car":[68],"which":[70],"a":[72],"benchmark":[73],"reinforcement":[74],"problem.":[76]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2021,"cited_by_count":1}],"updated_date":"2026-01-13T01:12:25.745995","created_date":"2025-10-10T00:00:00"}