{"id":"https://openalex.org/W2131056066","doi":"https://doi.org/10.1109/ijcnn.2008.4634208","title":"Tradeoff between exploration and exploitation of OQ(λ) with non-Markovian update in dynamic environments","display_name":"Tradeoff between exploration and exploitation of OQ(λ) with non-Markovian update in dynamic environments","publication_year":2008,"publication_date":"2008-06-01","ids":{"openalex":"https://openalex.org/W2131056066","doi":"https://doi.org/10.1109/ijcnn.2008.4634208","mag":"2131056066"},"language":"en","primary_location":{"id":"doi:10.1109/ijcnn.2008.4634208","is_oa":false,"landing_page_url":"https://doi.org/10.1109/ijcnn.2008.4634208","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2008 IEEE International Joint Conference on Neural Networks (IEEE World Congress on Computational Intelligence)","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/A5014872576","display_name":"Maryam Shokri","orcid":null},"institutions":[{"id":"https://openalex.org/I151746483","display_name":"University of Waterloo","ror":"https://ror.org/01aff2v68","country_code":"CA","type":"education","lineage":["https://openalex.org/I151746483"]}],"countries":["CA"],"is_corresponding":true,"raw_author_name":"Maryam Shokri","raw_affiliation_strings":["Department of Systems Design Engineering, University of Waterloo, Waterloo, ONT, Canada","Dept. of Syst. Design Eng., Univ. of Waterloo, Waterloo, ON"],"affiliations":[{"raw_affiliation_string":"Department of Systems Design Engineering, University of Waterloo, Waterloo, ONT, Canada","institution_ids":["https://openalex.org/I151746483"]},{"raw_affiliation_string":"Dept. of Syst. Design Eng., Univ. of Waterloo, Waterloo, ON","institution_ids":["https://openalex.org/I151746483"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5038566332","display_name":"Hamid R. Tizhoosh","orcid":"https://orcid.org/0000-0001-5488-601X"},"institutions":[{"id":"https://openalex.org/I151746483","display_name":"University of Waterloo","ror":"https://ror.org/01aff2v68","country_code":"CA","type":"education","lineage":["https://openalex.org/I151746483"]}],"countries":["CA"],"is_corresponding":false,"raw_author_name":"Hamid R. Tizhoosh","raw_affiliation_strings":["Department of Systems Design Engineering, University of Waterloo, Waterloo, ONT, Canada","Dept. of Syst. Design Eng., Univ. of Waterloo, Waterloo, ON"],"affiliations":[{"raw_affiliation_string":"Department of Systems Design Engineering, University of Waterloo, Waterloo, ONT, Canada","institution_ids":["https://openalex.org/I151746483"]},{"raw_affiliation_string":"Dept. of Syst. Design Eng., Univ. of Waterloo, Waterloo, ON","institution_ids":["https://openalex.org/I151746483"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5039318050","display_name":"Mohamed S. Kamel","orcid":"https://orcid.org/0000-0001-6173-8082"},"institutions":[{"id":"https://openalex.org/I151746483","display_name":"University of Waterloo","ror":"https://ror.org/01aff2v68","country_code":"CA","type":"education","lineage":["https://openalex.org/I151746483"]}],"countries":["CA"],"is_corresponding":false,"raw_author_name":"Mohamed S. Kamel","raw_affiliation_strings":["Department of Electrical and Computer Engineering, University of Waterloo, Waterloo, ONT, Canada","Dept. of Electr. & Comput. Eng., Univ. of Waterloo, Waterloo, ON#TAB#"],"affiliations":[{"raw_affiliation_string":"Department of Electrical and Computer Engineering, University of Waterloo, Waterloo, ONT, Canada","institution_ids":["https://openalex.org/I151746483"]},{"raw_affiliation_string":"Dept. of Electr. & Comput. Eng., Univ. of Waterloo, Waterloo, ON#TAB#","institution_ids":["https://openalex.org/I151746483"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5014872576"],"corresponding_institution_ids":["https://openalex.org/I151746483"],"apc_list":null,"apc_paid":null,"fwci":1.645,"has_fulltext":false,"cited_by_count":6,"citation_normalized_percentile":{"value":0.87199774,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":94},"biblio":{"volume":"16","issue":null,"first_page":"2915","last_page":"2921"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T14011","display_name":"Elevator Systems and Control","score":0.9962000250816345,"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"}},"topics":[{"id":"https://openalex.org/T14011","display_name":"Elevator Systems and Control","score":0.9962000250816345,"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"}},{"id":"https://openalex.org/T10462","display_name":"Reinforcement Learning in Robotics","score":0.9945999979972839,"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/T10551","display_name":"Scheduling and Optimization Algorithms","score":0.98580002784729,"subfield":{"id":"https://openalex.org/subfields/2209","display_name":"Industrial and Manufacturing 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/lambda","display_name":"Lambda","score":0.9196699261665344},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.49997472763061523},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.4462076723575592},{"id":"https://openalex.org/keywords/markov-process","display_name":"Markov process","score":0.43367132544517517},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.37811705470085144},{"id":"https://openalex.org/keywords/mathematical-optimization","display_name":"Mathematical optimization","score":0.3379175066947937},{"id":"https://openalex.org/keywords/physics","display_name":"Physics","score":0.1695234477519989},{"id":"https://openalex.org/keywords/statistics","display_name":"Statistics","score":0.10761868953704834}],"concepts":[{"id":"https://openalex.org/C2778113609","wikidata":"https://www.wikidata.org/wiki/Q10897","display_name":"Lambda","level":2,"score":0.9196699261665344},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.49997472763061523},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.4462076723575592},{"id":"https://openalex.org/C159886148","wikidata":"https://www.wikidata.org/wiki/Q176645","display_name":"Markov process","level":2,"score":0.43367132544517517},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.37811705470085144},{"id":"https://openalex.org/C126255220","wikidata":"https://www.wikidata.org/wiki/Q141495","display_name":"Mathematical optimization","level":1,"score":0.3379175066947937},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.1695234477519989},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.10761868953704834},{"id":"https://openalex.org/C120665830","wikidata":"https://www.wikidata.org/wiki/Q14620","display_name":"Optics","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/ijcnn.2008.4634208","is_oa":false,"landing_page_url":"https://doi.org/10.1109/ijcnn.2008.4634208","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2008 IEEE International Joint Conference on Neural Networks (IEEE World Congress on Computational Intelligence)","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":32,"referenced_works":["https://openalex.org/W182596629","https://openalex.org/W190427941","https://openalex.org/W1512069656","https://openalex.org/W1556756526","https://openalex.org/W1681299129","https://openalex.org/W1899059484","https://openalex.org/W1949804828","https://openalex.org/W1996738877","https://openalex.org/W2011033111","https://openalex.org/W2072837080","https://openalex.org/W2107726111","https://openalex.org/W2109592579","https://openalex.org/W2116372557","https://openalex.org/W2117185138","https://openalex.org/W2117341272","https://openalex.org/W2118756286","https://openalex.org/W2121863487","https://openalex.org/W2122410182","https://openalex.org/W2130105540","https://openalex.org/W2132825413","https://openalex.org/W2138289776","https://openalex.org/W2139053308","https://openalex.org/W2143183257","https://openalex.org/W2155791599","https://openalex.org/W2162745921","https://openalex.org/W2169015875","https://openalex.org/W2169183587","https://openalex.org/W4214717370","https://openalex.org/W4246177449","https://openalex.org/W6677180584","https://openalex.org/W6677347465","https://openalex.org/W6683164292"],"related_works":["https://openalex.org/W4391375266","https://openalex.org/W1979597421","https://openalex.org/W2007980826","https://openalex.org/W2051487156","https://openalex.org/W2061531152","https://openalex.org/W3002753104","https://openalex.org/W2077600819","https://openalex.org/W2142036596","https://openalex.org/W2072657027","https://openalex.org/W2600246793"],"abstract_inverted_index":{"This":[0],"paper":[1],"presents":[2],"some":[3],"investigations":[4],"on":[5,105],"tradeoff":[6,77],"between":[7,78],"exploration":[8,79],"and":[9,59,80],"exploitation":[10,81],"of":[11,54,88,96,118],"opposition-based":[12],"Q(lambda)":[13,124],"with":[14,123],"non-Markovian":[15],"update":[16],"(NOQ(lambda))":[17],"in":[18],"a":[19,45,75],"dynamic":[20,60],"environment.":[21,61],"In":[22,35],"the":[23,26,31,41,52,55,65,70,83,89,94,106,113],"previous":[24],"work":[25],"authors":[27],"applied":[28],"NOQ(lambda)":[29,42,66,84,119,130],"to":[30,50,73],"deterministic":[32],"GridWorld":[33],"problem.":[34],"this":[36],"paper,":[37],"we":[38],"have":[39],"implemented":[40],"algorithm":[43,56,67],"for":[44,57,82,109],"simple":[46],"elevator":[47],"control":[48],"problem":[49],"test":[51],"behavior":[53],"non-deterministic":[58],"We":[62],"also":[63],"extend":[64],"by":[68],"introducing":[69],"opposition":[71,90],"weight":[72,91],"find":[74],"better":[76,132],"technique.":[85,125],"The":[86,116,126],"value":[87],"increases":[92],"as":[93,112],"number":[95],"steps":[97],"increases.":[98],"Hence,":[99],"it":[100],"has":[101],"more":[102],"positive":[103],"effects":[104],"Q-value":[107],"updates":[108],"opposite":[110],"actions":[111],"learning":[114],"progresses.":[115],"performance":[117],"method":[120],"is":[121],"compared":[122],"experiments":[127],"indicate":[128],"that":[129],"performs":[131],"than":[133],"Q(lambda).":[134]},"counts_by_year":[{"year":2019,"cited_by_count":1},{"year":2017,"cited_by_count":1},{"year":2014,"cited_by_count":1},{"year":2012,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}