{"id":"https://openalex.org/W2144643808","doi":"https://doi.org/10.1109/is.2012.6335136","title":"Simultaneous discovery of multiple alternative optimal policies by reinforcement learning","display_name":"Simultaneous discovery of multiple alternative optimal policies by reinforcement learning","publication_year":2012,"publication_date":"2012-09-01","ids":{"openalex":"https://openalex.org/W2144643808","doi":"https://doi.org/10.1109/is.2012.6335136","mag":"2144643808"},"language":"en","primary_location":{"id":"doi:10.1109/is.2012.6335136","is_oa":false,"landing_page_url":"https://doi.org/10.1109/is.2012.6335136","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2012 6th IEEE INTERNATIONAL CONFERENCE INTELLIGENT SYSTEMS","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/A5036281885","display_name":"Petar Kormushev","orcid":"https://orcid.org/0000-0002-6677-3044"},"institutions":[{"id":"https://openalex.org/I30771326","display_name":"Italian Institute of Technology","ror":"https://ror.org/042t93s57","country_code":"IT","type":"facility","lineage":["https://openalex.org/I30771326"]}],"countries":["IT"],"is_corresponding":true,"raw_author_name":"Petar Kormushev","raw_affiliation_strings":["Department of Advanced Robotics, Istituto Italiano di Tecnologia, Genoa, Italy","Department of Advanced Robotics, Istituto Italiano di Tecnologia, via Morego, 30,16163 Genova, Italy"],"affiliations":[{"raw_affiliation_string":"Department of Advanced Robotics, Istituto Italiano di Tecnologia, Genoa, Italy","institution_ids":["https://openalex.org/I30771326"]},{"raw_affiliation_string":"Department of Advanced Robotics, Istituto Italiano di Tecnologia, via Morego, 30,16163 Genova, Italy","institution_ids":["https://openalex.org/I30771326"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5044243940","display_name":"Darwin G. Caldwell","orcid":"https://orcid.org/0000-0002-6233-9961"},"institutions":[{"id":"https://openalex.org/I30771326","display_name":"Italian Institute of Technology","ror":"https://ror.org/042t93s57","country_code":"IT","type":"facility","lineage":["https://openalex.org/I30771326"]}],"countries":["IT"],"is_corresponding":false,"raw_author_name":"Darwin G. Caldwell","raw_affiliation_strings":["Department of Advanced Robotics, Istituto Italiano di Tecnologia, Genoa, Italy","Department of Advanced Robotics, Istituto Italiano di Tecnologia, via Morego, 30,16163 Genova, Italy"],"affiliations":[{"raw_affiliation_string":"Department of Advanced Robotics, Istituto Italiano di Tecnologia, Genoa, Italy","institution_ids":["https://openalex.org/I30771326"]},{"raw_affiliation_string":"Department of Advanced Robotics, Istituto Italiano di Tecnologia, via Morego, 30,16163 Genova, Italy","institution_ids":["https://openalex.org/I30771326"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5036281885"],"corresponding_institution_ids":["https://openalex.org/I30771326"],"apc_list":null,"apc_paid":null,"fwci":2.5689,"has_fulltext":false,"cited_by_count":7,"citation_normalized_percentile":{"value":0.90608157,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":89,"max":96},"biblio":{"volume":"18","issue":null,"first_page":"202","last_page":"207"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10462","display_name":"Reinforcement Learning in Robotics","score":0.9997000098228455,"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":0.9997000098228455,"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":0.9962000250816345,"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/T12535","display_name":"Machine Learning and Data Classification","score":0.9961000084877014,"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":0.918142557144165},{"id":"https://openalex.org/keywords/initialization","display_name":"Initialization","score":0.8697332739830017},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.700069785118103},{"id":"https://openalex.org/keywords/mathematical-optimization","display_name":"Mathematical optimization","score":0.6469550132751465},{"id":"https://openalex.org/keywords/local-optimum","display_name":"Local optimum","score":0.6136366128921509},{"id":"https://openalex.org/keywords/maximization","display_name":"Maximization","score":0.574110746383667},{"id":"https://openalex.org/keywords/dependency","display_name":"Dependency (UML)","score":0.5300832986831665},{"id":"https://openalex.org/keywords/state-space","display_name":"State space","score":0.5149267911911011},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4352051913738251},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.37572503089904785},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.20059683918952942},{"id":"https://openalex.org/keywords/statistics","display_name":"Statistics","score":0.06785345077514648}],"concepts":[{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.918142557144165},{"id":"https://openalex.org/C114466953","wikidata":"https://www.wikidata.org/wiki/Q6034165","display_name":"Initialization","level":2,"score":0.8697332739830017},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.700069785118103},{"id":"https://openalex.org/C126255220","wikidata":"https://www.wikidata.org/wiki/Q141495","display_name":"Mathematical optimization","level":1,"score":0.6469550132751465},{"id":"https://openalex.org/C141934464","wikidata":"https://www.wikidata.org/wiki/Q3305386","display_name":"Local optimum","level":2,"score":0.6136366128921509},{"id":"https://openalex.org/C2776330181","wikidata":"https://www.wikidata.org/wiki/Q18358244","display_name":"Maximization","level":2,"score":0.574110746383667},{"id":"https://openalex.org/C19768560","wikidata":"https://www.wikidata.org/wiki/Q320727","display_name":"Dependency (UML)","level":2,"score":0.5300832986831665},{"id":"https://openalex.org/C72434380","wikidata":"https://www.wikidata.org/wiki/Q230930","display_name":"State space","level":2,"score":0.5149267911911011},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4352051913738251},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.37572503089904785},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.20059683918952942},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.06785345077514648},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/is.2012.6335136","is_oa":false,"landing_page_url":"https://doi.org/10.1109/is.2012.6335136","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2012 6th IEEE INTERNATIONAL CONFERENCE INTELLIGENT SYSTEMS","raw_type":"proceedings-article"},{"id":"pmh:oai:spiral.imperial.ac.uk:10044/1/26051","is_oa":false,"landing_page_url":"http://hdl.handle.net/10044/1/26051","pdf_url":null,"source":{"id":"https://openalex.org/S4306401396","display_name":"Spiral (Imperial College London)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I47508984","host_organization_name":"Imperial College London","host_organization_lineage":["https://openalex.org/I47508984"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"2012 6th IEEE International Conference Intelligent Systems (IS)","raw_type":"Conference Paper"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.6299999952316284,"id":"https://metadata.un.org/sdg/16","display_name":"Peace, Justice and strong institutions"}],"awards":[],"funders":[{"id":"https://openalex.org/F4320338370","display_name":"FP7 Information and Communication Technologies","ror":null}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":29,"referenced_works":["https://openalex.org/W1483307070","https://openalex.org/W1582224092","https://openalex.org/W1663973292","https://openalex.org/W1685912164","https://openalex.org/W1925816294","https://openalex.org/W2006139934","https://openalex.org/W2098613108","https://openalex.org/W2103393159","https://openalex.org/W2106733731","https://openalex.org/W2119717200","https://openalex.org/W2120070743","https://openalex.org/W2126736494","https://openalex.org/W2131865378","https://openalex.org/W2138294682","https://openalex.org/W2140135625","https://openalex.org/W2141597721","https://openalex.org/W2142916680","https://openalex.org/W2161872510","https://openalex.org/W2170229019","https://openalex.org/W2172968643","https://openalex.org/W2336416123","https://openalex.org/W2594639291","https://openalex.org/W2622604310","https://openalex.org/W3005581722","https://openalex.org/W6637259795","https://openalex.org/W6640290305","https://openalex.org/W6675456536","https://openalex.org/W6679875354","https://openalex.org/W6680657880"],"related_works":["https://openalex.org/W3204184292","https://openalex.org/W3176564347","https://openalex.org/W1985458517","https://openalex.org/W2355833770","https://openalex.org/W3031039437","https://openalex.org/W183202219","https://openalex.org/W3095877357","https://openalex.org/W2072565696","https://openalex.org/W2050451745","https://openalex.org/W2378903222"],"abstract_inverted_index":{"Conventional":[0],"reinforcement":[1,54,130],"learning":[2,55,131],"algorithms":[3],"for":[4,57],"direct":[5,58],"policy":[6,36,45,59,83,91],"search":[7,81],"are":[8],"limited":[9],"to":[10,27,30,97,119],"finding":[11,66],"only":[12,29],"a":[13,31,52,120,126],"single":[14,32],"optimal":[15,69,101],"policy.":[16,102],"This":[17],"is":[18,62,73],"caused":[19],"by":[20],"their":[21],"local-search":[22],"nature,":[23],"which":[24,61],"allows":[25],"them":[26,40],"converge":[28],"local":[33],"optimum":[34],"in":[35,82],"space,":[37,84],"and":[38,78,93,109,115,125],"makes":[39],"heavily":[41],"dependent":[42],"on":[43,75,89,107],"the":[44,87,90,95,99,105],"initialization.":[46],"In":[47],"this":[48],"paper,":[49],"we":[50],"propose":[51],"novel":[53],"algorithm":[56,72],"search,":[60],"capable":[63],"of":[64],"simultaneously":[65],"multiple":[67,113],"alternative":[68],"policies.":[70],"The":[71],"based":[74,129],"particle":[76],"filtering":[77],"performs":[79],"global":[80,121],"therefore":[85],"eliminating":[86],"dependency":[88],"initialization,":[92],"having":[94],"ability":[96],"find":[98],"globally":[100],"We":[103],"validate":[104],"approach":[106],"one-":[108],"two-dimensional":[110],"problems":[111],"with":[112],"optima,":[114],"compare":[116],"its":[117],"performance":[118],"random":[122],"sampling":[123],"method,":[124],"state-of-the-art":[127],"Expectation-Maximization":[128],"algorithm.":[132]},"counts_by_year":[{"year":2022,"cited_by_count":1},{"year":2015,"cited_by_count":1},{"year":2014,"cited_by_count":1},{"year":2013,"cited_by_count":2},{"year":2012,"cited_by_count":2}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}