{"id":"https://openalex.org/W2042296018","doi":"https://doi.org/10.1109/siu.2012.6204703","title":"Importance sampling for model-based reinforcement learning","display_name":"Importance sampling for model-based reinforcement learning","publication_year":2012,"publication_date":"2012-04-01","ids":{"openalex":"https://openalex.org/W2042296018","doi":"https://doi.org/10.1109/siu.2012.6204703","mag":"2042296018"},"language":"en","primary_location":{"id":"doi:10.1109/siu.2012.6204703","is_oa":false,"landing_page_url":"https://doi.org/10.1109/siu.2012.6204703","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2012 20th 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":"Orhan Sonmez","raw_affiliation_strings":["Bilgisayar M\u00fchendisli\u011fi B\u00f6l\u00fcm\u00fc, Bo\u011fazi\u00e7i \u00dcniversitesi, Turkey"],"affiliations":[{"raw_affiliation_string":"Bilgisayar M\u00fchendisli\u011fi B\u00f6l\u00fcm\u00fc, Bo\u011fazi\u00e7i \u00dcniversitesi, 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. Taylan Cemgil","raw_affiliation_strings":["Bilgisayar M\u00fchendisli\u011fi B\u00f6l\u00fcm\u00fc, Bo\u011fazi\u00e7i \u00dcniversitesi, Turkey"],"affiliations":[{"raw_affiliation_string":"Bilgisayar M\u00fchendisli\u011fi B\u00f6l\u00fcm\u00fc, Bo\u011fazi\u00e7i \u00dcniversitesi, 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":0,"citation_normalized_percentile":{"value":0.09814712,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":"56","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":0.9986000061035156,"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":0.9986000061035156,"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/T11975","display_name":"Evolutionary Algorithms and Applications","score":0.9876000285148621,"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":0.9688000082969666,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/reinforcement-learning","display_name":"Reinforcement learning","score":0.8670072555541992},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6963667869567871},{"id":"https://openalex.org/keywords/maximization","display_name":"Maximization","score":0.6364689469337463},{"id":"https://openalex.org/keywords/expectation\u2013maximization-algorithm","display_name":"Expectation\u2013maximization algorithm","score":0.5858621597290039},{"id":"https://openalex.org/keywords/inference","display_name":"Inference","score":0.5847533941268921},{"id":"https://openalex.org/keywords/probabilistic-logic","display_name":"Probabilistic logic","score":0.5712817907333374},{"id":"https://openalex.org/keywords/mathematical-optimization","display_name":"Mathematical optimization","score":0.5479200482368469},{"id":"https://openalex.org/keywords/importance-sampling","display_name":"Importance sampling","score":0.5232738256454468},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5027801990509033},{"id":"https://openalex.org/keywords/graphical-model","display_name":"Graphical model","score":0.49926137924194336},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.47145920991897583},{"id":"https://openalex.org/keywords/sampling","display_name":"Sampling (signal processing)","score":0.4703020453453064},{"id":"https://openalex.org/keywords/temporal-difference-learning","display_name":"Temporal difference learning","score":0.45446789264678955},{"id":"https://openalex.org/keywords/maximum-likelihood","display_name":"Maximum likelihood","score":0.24714943766593933},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.21931156516075134},{"id":"https://openalex.org/keywords/statistics","display_name":"Statistics","score":0.09636691212654114}],"concepts":[{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.8670072555541992},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6963667869567871},{"id":"https://openalex.org/C2776330181","wikidata":"https://www.wikidata.org/wiki/Q18358244","display_name":"Maximization","level":2,"score":0.6364689469337463},{"id":"https://openalex.org/C182081679","wikidata":"https://www.wikidata.org/wiki/Q1275153","display_name":"Expectation\u2013maximization algorithm","level":3,"score":0.5858621597290039},{"id":"https://openalex.org/C2776214188","wikidata":"https://www.wikidata.org/wiki/Q408386","display_name":"Inference","level":2,"score":0.5847533941268921},{"id":"https://openalex.org/C49937458","wikidata":"https://www.wikidata.org/wiki/Q2599292","display_name":"Probabilistic logic","level":2,"score":0.5712817907333374},{"id":"https://openalex.org/C126255220","wikidata":"https://www.wikidata.org/wiki/Q141495","display_name":"Mathematical optimization","level":1,"score":0.5479200482368469},{"id":"https://openalex.org/C52740198","wikidata":"https://www.wikidata.org/wiki/Q1539564","display_name":"Importance sampling","level":3,"score":0.5232738256454468},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5027801990509033},{"id":"https://openalex.org/C155846161","wikidata":"https://www.wikidata.org/wiki/Q1143367","display_name":"Graphical model","level":2,"score":0.49926137924194336},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.47145920991897583},{"id":"https://openalex.org/C140779682","wikidata":"https://www.wikidata.org/wiki/Q210868","display_name":"Sampling (signal processing)","level":3,"score":0.4703020453453064},{"id":"https://openalex.org/C196340769","wikidata":"https://www.wikidata.org/wiki/Q7698910","display_name":"Temporal difference learning","level":3,"score":0.45446789264678955},{"id":"https://openalex.org/C49781872","wikidata":"https://www.wikidata.org/wiki/Q1045555","display_name":"Maximum likelihood","level":2,"score":0.24714943766593933},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.21931156516075134},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.09636691212654114},{"id":"https://openalex.org/C19499675","wikidata":"https://www.wikidata.org/wiki/Q232207","display_name":"Monte Carlo method","level":2,"score":0.0},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.0},{"id":"https://openalex.org/C106131492","wikidata":"https://www.wikidata.org/wiki/Q3072260","display_name":"Filter (signal processing)","level":2,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/siu.2012.6204703","is_oa":false,"landing_page_url":"https://doi.org/10.1109/siu.2012.6204703","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2012 20th Signal Processing and Communications Applications Conference (SIU)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":15,"referenced_works":["https://openalex.org/W35083779","https://openalex.org/W2073384958","https://openalex.org/W2080039641","https://openalex.org/W2098432798","https://openalex.org/W2123157758","https://openalex.org/W2520735695","https://openalex.org/W2751318774","https://openalex.org/W2963247855","https://openalex.org/W2963911891","https://openalex.org/W4211221179","https://openalex.org/W4244921287","https://openalex.org/W6630596490","https://openalex.org/W6680628607","https://openalex.org/W6727001741","https://openalex.org/W6991957103"],"related_works":["https://openalex.org/W2109986081","https://openalex.org/W4297589944","https://openalex.org/W2417308975","https://openalex.org/W2964129930","https://openalex.org/W4368755698","https://openalex.org/W4285040766","https://openalex.org/W4388627352","https://openalex.org/W1976188970","https://openalex.org/W2889559465","https://openalex.org/W2990541822"],"abstract_inverted_index":{"Most":[0],"of":[1,15,26,51],"the":[2,27,31,49,72,78],"state-of-the-art":[3],"reinforcement":[4,32],"learning":[5,33],"algorithms":[6],"are":[7],"based":[8],"on":[9],"Bellman":[10],"equations":[11],"and":[12,74],"make":[13],"use":[14],"fixed-point":[16],"iteration":[17],"methods":[18],"to":[19,21,70,76],"converge":[20],"suboptimal":[22],"solutions.":[23],"However,":[24],"some":[25],"recent":[28],"approaches":[29],"transform":[30],"problem":[34,40],"into":[35],"an":[36,58],"equivalent":[37],"likelihood":[38,73],"maximization":[39],"with":[41],"using":[42],"appropriate":[43],"graphical":[44],"models.":[45],"Hence,":[46],"it":[47],"allows":[48],"adoption":[50],"probabilistic":[52],"inference":[53],"methods.":[54],"Here,":[55],"we":[56],"propose":[57],"expectation-maximization":[59],"method":[60],"that":[61],"employs":[62],"importance":[63],"sampling":[64],"in":[65,68],"its":[66],"E-step":[67],"order":[69],"estimate":[71],"then":[75],"determine":[77],"optimal":[79],"policy.":[80]},"counts_by_year":[],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}