{"id":"https://openalex.org/W1976122296","doi":"https://doi.org/10.1109/icsmc.2010.5642415","title":"Dyna-like reinforcement learning based on accumulative and average rewards","display_name":"Dyna-like reinforcement learning based on accumulative and average rewards","publication_year":2010,"publication_date":"2010-10-01","ids":{"openalex":"https://openalex.org/W1976122296","doi":"https://doi.org/10.1109/icsmc.2010.5642415","mag":"1976122296"},"language":"en","primary_location":{"id":"doi:10.1109/icsmc.2010.5642415","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icsmc.2010.5642415","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2010 IEEE International Conference on Systems, Man and Cybernetics","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/A5061189209","display_name":"Kao\u2010Shing Hwang","orcid":"https://orcid.org/0000-0001-9234-4836"},"institutions":[{"id":"https://openalex.org/I148099254","display_name":"National Chung Cheng University","ror":"https://ror.org/0028v3876","country_code":"TW","type":"education","lineage":["https://openalex.org/I148099254"]}],"countries":["TW"],"is_corresponding":true,"raw_author_name":"Kao-Shing Hwang","raw_affiliation_strings":["Department of Electrical Engineering, National Chung Cheng University, Chiayi, Taiwan","Department of Electrical Engineering, National Chung-Cheng University, Chia-Yi, Taiwan"],"affiliations":[{"raw_affiliation_string":"Department of Electrical Engineering, National Chung Cheng University, Chiayi, Taiwan","institution_ids":["https://openalex.org/I148099254"]},{"raw_affiliation_string":"Department of Electrical Engineering, National Chung-Cheng University, Chia-Yi, Taiwan","institution_ids":["https://openalex.org/I148099254"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5110240481","display_name":"Chia-Yue Lo","orcid":null},"institutions":[{"id":"https://openalex.org/I148099254","display_name":"National Chung Cheng University","ror":"https://ror.org/0028v3876","country_code":"TW","type":"education","lineage":["https://openalex.org/I148099254"]}],"countries":["TW"],"is_corresponding":false,"raw_author_name":"Chia-Yue Lo","raw_affiliation_strings":["Department of Electrical Engineering, National Chung Cheng University, Chiayi, Taiwan","Department of Electrical Engineering, National Chung-Cheng University, Chia-Yi, Taiwan"],"affiliations":[{"raw_affiliation_string":"Department of Electrical Engineering, National Chung Cheng University, Chiayi, Taiwan","institution_ids":["https://openalex.org/I148099254"]},{"raw_affiliation_string":"Department of Electrical Engineering, National Chung-Cheng University, Chia-Yi, Taiwan","institution_ids":["https://openalex.org/I148099254"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5061189209"],"corresponding_institution_ids":["https://openalex.org/I148099254"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.07279664,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"1250","last_page":"1254"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10462","display_name":"Reinforcement Learning in Robotics","score":0.9983000159263611,"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":0.9983000159263611,"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/T12794","display_name":"Adaptive Dynamic Programming Control","score":0.9973000288009644,"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/T10791","display_name":"Advanced Control Systems Optimization","score":0.9456999897956848,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/reinforcement-learning","display_name":"Reinforcement learning","score":0.8627418279647827},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6958810091018677},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.6167836785316467},{"id":"https://openalex.org/keywords/temporal-difference-learning","display_name":"Temporal difference learning","score":0.6072715520858765},{"id":"https://openalex.org/keywords/inverted-pendulum","display_name":"Inverted pendulum","score":0.5806358456611633},{"id":"https://openalex.org/keywords/robustness","display_name":"Robustness (evolution)","score":0.5512356758117676},{"id":"https://openalex.org/keywords/q-learning","display_name":"Q-learning","score":0.5490747094154358},{"id":"https://openalex.org/keywords/trajectory","display_name":"Trajectory","score":0.5164778232574463},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.506304144859314},{"id":"https://openalex.org/keywords/learning-classifier-system","display_name":"Learning classifier system","score":0.4471896290779114},{"id":"https://openalex.org/keywords/function-approximation","display_name":"Function approximation","score":0.4300840198993683},{"id":"https://openalex.org/keywords/control-theory","display_name":"Control theory (sociology)","score":0.4189970791339874},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.3858988583087921},{"id":"https://openalex.org/keywords/nonlinear-system","display_name":"Nonlinear system","score":0.3785827159881592},{"id":"https://openalex.org/keywords/control","display_name":"Control (management)","score":0.30744796991348267}],"concepts":[{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.8627418279647827},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6958810091018677},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.6167836785316467},{"id":"https://openalex.org/C196340769","wikidata":"https://www.wikidata.org/wiki/Q7698910","display_name":"Temporal difference learning","level":3,"score":0.6072715520858765},{"id":"https://openalex.org/C192921069","wikidata":"https://www.wikidata.org/wiki/Q550134","display_name":"Inverted pendulum","level":3,"score":0.5806358456611633},{"id":"https://openalex.org/C63479239","wikidata":"https://www.wikidata.org/wiki/Q7353546","display_name":"Robustness (evolution)","level":3,"score":0.5512356758117676},{"id":"https://openalex.org/C188116033","wikidata":"https://www.wikidata.org/wiki/Q2664563","display_name":"Q-learning","level":3,"score":0.5490747094154358},{"id":"https://openalex.org/C13662910","wikidata":"https://www.wikidata.org/wiki/Q193139","display_name":"Trajectory","level":2,"score":0.5164778232574463},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.506304144859314},{"id":"https://openalex.org/C199190896","wikidata":"https://www.wikidata.org/wiki/Q3509276","display_name":"Learning classifier system","level":3,"score":0.4471896290779114},{"id":"https://openalex.org/C91873725","wikidata":"https://www.wikidata.org/wiki/Q3445816","display_name":"Function approximation","level":3,"score":0.4300840198993683},{"id":"https://openalex.org/C47446073","wikidata":"https://www.wikidata.org/wiki/Q5165890","display_name":"Control theory (sociology)","level":3,"score":0.4189970791339874},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.3858988583087921},{"id":"https://openalex.org/C158622935","wikidata":"https://www.wikidata.org/wiki/Q660848","display_name":"Nonlinear system","level":2,"score":0.3785827159881592},{"id":"https://openalex.org/C2775924081","wikidata":"https://www.wikidata.org/wiki/Q55608371","display_name":"Control (management)","level":2,"score":0.30744796991348267},{"id":"https://openalex.org/C104317684","wikidata":"https://www.wikidata.org/wiki/Q7187","display_name":"Gene","level":2,"score":0.0},{"id":"https://openalex.org/C62520636","wikidata":"https://www.wikidata.org/wiki/Q944","display_name":"Quantum mechanics","level":1,"score":0.0},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0},{"id":"https://openalex.org/C1276947","wikidata":"https://www.wikidata.org/wiki/Q333","display_name":"Astronomy","level":1,"score":0.0},{"id":"https://openalex.org/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","level":0,"score":0.0},{"id":"https://openalex.org/C55493867","wikidata":"https://www.wikidata.org/wiki/Q7094","display_name":"Biochemistry","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icsmc.2010.5642415","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icsmc.2010.5642415","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2010 IEEE International Conference on Systems, Man and Cybernetics","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":9,"referenced_works":["https://openalex.org/W32403112","https://openalex.org/W1549353711","https://openalex.org/W1592847719","https://openalex.org/W2080759927","https://openalex.org/W2091565802","https://openalex.org/W2117941808","https://openalex.org/W2121863487","https://openalex.org/W2166591778","https://openalex.org/W4214717370"],"related_works":["https://openalex.org/W2955790965","https://openalex.org/W4289355352","https://openalex.org/W3140225428","https://openalex.org/W2610686804","https://openalex.org/W3148138296","https://openalex.org/W2088618689","https://openalex.org/W4253074907","https://openalex.org/W2152445738","https://openalex.org/W4206305295","https://openalex.org/W55500148"],"abstract_inverted_index":{"An":[0],"approach":[1,113],"to":[2,45,63,85,146,204,214,233,278],"accelerating":[3],"the":[4,8,25,59,86,94,109,112,141,148,177,225,227,240,244,248,262,286,292],"learning":[5,10,14,34,67,78,101,123,129,199,255],"process":[6],"of":[7,27,58,93,107,119,159,171,187,243,264],"actor-critic":[9],"algorithm":[11,18,42,61,157],"for":[12,99,121,209],"reinforcement":[13,222],"is":[15,97,163,179,185,201,259,269],"presented.":[16],"The":[17,40,56,151,197,283],"was":[19,43,62],"derived":[20,41,149],"from":[21,224],"principles":[22],"based":[23,80,131],"on":[24,81,274,298],"prediction":[26],"average":[28],"rewards":[29,120,135],"and":[30,37,133,143,176,193,219,291],"temporal":[31],"difference":[32],"(TD)":[33],"with":[35,236,302],"averaged":[36,134],"discounted":[38,132],"rewards.":[39],"applied":[44,203],"neural":[46,72],"networks,":[47],"demonstrating":[48],"their":[49],"effective":[50],"operation":[51],"in":[52,124,140],"nonlinear":[53,300],"control":[54,104,142,205,279],"problems.":[55],"motivation":[57],"proposed":[60,152,198],"elaborate":[64],"how":[65],"a":[66,90,116,172,206,211,234,253,265,275,299],"scheme,":[68],"implemented":[69],"by":[70],"artificial":[71],"networks":[73],"(ANNs),":[74],"can":[75,246,295],"speed":[76],"up":[77],"processes":[79],"an":[82,169,180,230],"arrangement":[83],"akin":[84],"Dyna-Q":[87],"learning,":[88],"where":[89],"simulative":[91],"model":[92],"controlled":[95],"plant":[96,235,245],"established":[98],"virtual":[100,122],"between":[102],"two":[103,160,188],"cycles.":[105,256],"Instead":[106],"modeling":[108],"complicated":[110],"plant,":[111],"just":[114],"introduced":[115],"simple":[117],"predictor":[118],"simulation":[125,144],"mode.":[126],"Two":[127],"TD":[128],"methods":[130],"respectively,":[136],"are":[137],"used":[138,260],"alternatively":[139],"mode":[145],"facilitate":[147],"algorithm.":[150],"Alternative":[153],"Learning":[154],"Critic":[155],"(ALC)":[156],"consists":[158],"sub-systems:":[161],"one":[162,250],"Evaluation":[164],"Predictor":[165,195],"(EP),":[166],"which":[167,184,268],"performs":[168],"approximation":[170],"long-term":[173],"evaluation":[174],"function,":[175],"other":[178],"immediate":[181],"action":[182,232],"selector,":[183],"composed":[186],"ANNs:":[189],"Action":[190],"Controller":[191],"(AC)":[192],"Reinforcement":[194],"(RP).":[196],"scheme":[200],"then":[202],"pendulum":[207,281],"system":[208,228,301],"tracking":[210],"desired":[212,249],"trajectory":[213],"demonstrate":[215],"its":[216],"applausive":[217],"performance":[218],"robustness.":[220],"Through":[221],"signals":[223],"environment,":[226],"takes":[229],"appropriate":[231],"unknown":[237,303],"dynamics":[238],"so":[239],"actual":[241],"output":[242],"track":[247],"concisely":[251],"within":[252],"short":[254],"Further,":[257],"ALC":[258,290],"as":[261],"compensator":[263],"PI":[266,293],"controller,":[267],"actually":[270],"only":[271],"working":[272],"well":[273],"linear":[276],"system,":[277,288],"that":[280],"system.":[282],"results":[284],"show":[285],"affined":[287],"trained":[289],"controller":[294],"manipulate":[296],"together":[297],"dynamics.":[304]},"counts_by_year":[],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}