{"id":"https://openalex.org/W2809086758","doi":"https://doi.org/10.1109/tcyb.2018.2838595","title":"Abdominal-Waving Control of Tethered Bumblebees Based on Sarsa With Transformed Reward","display_name":"Abdominal-Waving Control of Tethered Bumblebees Based on Sarsa With Transformed Reward","publication_year":2018,"publication_date":"2018-06-22","ids":{"openalex":"https://openalex.org/W2809086758","doi":"https://doi.org/10.1109/tcyb.2018.2838595","mag":"2809086758","pmid":"https://pubmed.ncbi.nlm.nih.gov/29994492"},"language":"en","primary_location":{"id":"doi:10.1109/tcyb.2018.2838595","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tcyb.2018.2838595","pdf_url":null,"source":{"id":"https://openalex.org/S4210191041","display_name":"IEEE Transactions on Cybernetics","issn_l":"2168-2267","issn":["2168-2267","2168-2275"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Transactions on Cybernetics","raw_type":"journal-article"},"type":"article","indexed_in":["crossref","pubmed"],"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/A5040143894","display_name":"Nenggan Zheng","orcid":"https://orcid.org/0000-0002-0211-8817"},"institutions":[{"id":"https://openalex.org/I76130692","display_name":"Zhejiang University","ror":"https://ror.org/00a2xv884","country_code":"CN","type":"education","lineage":["https://openalex.org/I76130692"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Nenggan Zheng","raw_affiliation_strings":["Qiushi Academy for Advanced Studies, Zhejiang University, Hangzhou, China"],"raw_orcid":"https://orcid.org/0000-0002-0211-8817","affiliations":[{"raw_affiliation_string":"Qiushi Academy for Advanced Studies, Zhejiang University, Hangzhou, China","institution_ids":["https://openalex.org/I76130692"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5102850823","display_name":"Qian Ma","orcid":"https://orcid.org/0000-0002-6594-813X"},"institutions":[{"id":"https://openalex.org/I76130692","display_name":"Zhejiang University","ror":"https://ror.org/00a2xv884","country_code":"CN","type":"education","lineage":["https://openalex.org/I76130692"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Qian Ma","raw_affiliation_strings":["Qiushi Academy for Advanced Studies, Zhejiang University, Hangzhou, China"],"raw_orcid":"https://orcid.org/0000-0002-6594-813X","affiliations":[{"raw_affiliation_string":"Qiushi Academy for Advanced Studies, Zhejiang University, Hangzhou, China","institution_ids":["https://openalex.org/I76130692"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101935118","display_name":"Mengjie Jin","orcid":null},"institutions":[{"id":"https://openalex.org/I76130692","display_name":"Zhejiang University","ror":"https://ror.org/00a2xv884","country_code":"CN","type":"education","lineage":["https://openalex.org/I76130692"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Mengjie Jin","raw_affiliation_strings":["Qiushi Academy for Advanced Studies, Zhejiang University, Hangzhou, China"],"raw_orcid":"https://orcid.org/0000-0001-5467-2580","affiliations":[{"raw_affiliation_string":"Qiushi Academy for Advanced Studies, Zhejiang University, Hangzhou, China","institution_ids":["https://openalex.org/I76130692"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Shaomin Zhang","orcid":"https://orcid.org/0000-0001-9828-5187"},"institutions":[{"id":"https://openalex.org/I76130692","display_name":"Zhejiang University","ror":"https://ror.org/00a2xv884","country_code":"CN","type":"education","lineage":["https://openalex.org/I76130692"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Shaomin Zhang","raw_affiliation_strings":["Qiushi Academy for Advanced Studies, Zhejiang University, Hangzhou, China"],"raw_orcid":"https://orcid.org/0000-0001-9828-5187","affiliations":[{"raw_affiliation_string":"Qiushi Academy for Advanced Studies, Zhejiang University, Hangzhou, China","institution_ids":["https://openalex.org/I76130692"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5002245169","display_name":"Nan Guan","orcid":"https://orcid.org/0000-0003-3775-911X"},"institutions":[{"id":"https://openalex.org/I14243506","display_name":"Hong Kong Polytechnic University","ror":"https://ror.org/0030zas98","country_code":"HK","type":"education","lineage":["https://openalex.org/I14243506"]}],"countries":["HK"],"is_corresponding":false,"raw_author_name":"Nan Guan","raw_affiliation_strings":["Department of Computing, Hong Kong Polytechnic University, Hong Kong"],"raw_orcid":"https://orcid.org/0000-0003-3775-911X","affiliations":[{"raw_affiliation_string":"Department of Computing, Hong Kong Polytechnic University, Hong Kong","institution_ids":["https://openalex.org/I14243506"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100636290","display_name":"Qiang Yang","orcid":"https://orcid.org/0000-0002-0761-4692"},"institutions":[{"id":"https://openalex.org/I76130692","display_name":"Zhejiang University","ror":"https://ror.org/00a2xv884","country_code":"CN","type":"education","lineage":["https://openalex.org/I76130692"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Qiang Yang","raw_affiliation_strings":["College of Electrical Engineering, Zhejiang University, Hangzhou, China"],"raw_orcid":"https://orcid.org/0000-0002-0761-4692","affiliations":[{"raw_affiliation_string":"College of Electrical Engineering, Zhejiang University, Hangzhou, China","institution_ids":["https://openalex.org/I76130692"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5070031719","display_name":"Jianhua Dai","orcid":"https://orcid.org/0000-0003-1459-0833"},"institutions":[{"id":"https://openalex.org/I173759888","display_name":"Hunan Normal University","ror":"https://ror.org/053w1zy07","country_code":"CN","type":"education","lineage":["https://openalex.org/I173759888"]},{"id":"https://openalex.org/I3130607311","display_name":"Changsha Normal University","ror":"https://ror.org/02sqk3z62","country_code":"CN","type":"education","lineage":["https://openalex.org/I3130607311"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jianhua Dai","raw_affiliation_strings":["College of Information Science and Engineering, Hunan Normal University, Changsha, China"],"raw_orcid":"https://orcid.org/0000-0003-1459-0833","affiliations":[{"raw_affiliation_string":"College of Information Science and Engineering, Hunan Normal University, Changsha, China","institution_ids":["https://openalex.org/I173759888","https://openalex.org/I3130607311"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":4,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.9811,"has_fulltext":false,"cited_by_count":20,"citation_normalized_percentile":{"value":0.72540016,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":94,"max":98},"biblio":{"volume":"49","issue":"8","first_page":"3064","last_page":"3073"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10581","display_name":"Neural dynamics and brain function","score":0.9973999857902527,"subfield":{"id":"https://openalex.org/subfields/2805","display_name":"Cognitive Neuroscience"},"field":{"id":"https://openalex.org/fields/28","display_name":"Neuroscience"},"domain":{"id":"https://openalex.org/domains/1","display_name":"Life Sciences"}},"topics":[{"id":"https://openalex.org/T10581","display_name":"Neural dynamics and brain function","score":0.9973999857902527,"subfield":{"id":"https://openalex.org/subfields/2805","display_name":"Cognitive Neuroscience"},"field":{"id":"https://openalex.org/fields/28","display_name":"Neuroscience"},"domain":{"id":"https://openalex.org/domains/1","display_name":"Life Sciences"}},{"id":"https://openalex.org/T10462","display_name":"Reinforcement Learning in Robotics","score":0.9950000047683716,"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/T11252","display_name":"Evolutionary Game Theory and Cooperation","score":0.9708999991416931,"subfield":{"id":"https://openalex.org/subfields/3312","display_name":"Sociology and Political Science"},"field":{"id":"https://openalex.org/fields/33","display_name":"Social 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":0.7153987288475037},{"id":"https://openalex.org/keywords/markov-decision-process","display_name":"Markov decision process","score":0.6255091428756714},{"id":"https://openalex.org/keywords/context","display_name":"Context (archaeology)","score":0.5869876146316528},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.543769121170044},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.5422428846359253},{"id":"https://openalex.org/keywords/process","display_name":"Process (computing)","score":0.5005030632019043},{"id":"https://openalex.org/keywords/state","display_name":"State (computer science)","score":0.4217250943183899},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.34535276889801025},{"id":"https://openalex.org/keywords/markov-process","display_name":"Markov process","score":0.2864640951156616},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.17466473579406738},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.11903244256973267},{"id":"https://openalex.org/keywords/biology","display_name":"Biology","score":0.10799401998519897}],"concepts":[{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.7153987288475037},{"id":"https://openalex.org/C106189395","wikidata":"https://www.wikidata.org/wiki/Q176789","display_name":"Markov decision process","level":3,"score":0.6255091428756714},{"id":"https://openalex.org/C2779343474","wikidata":"https://www.wikidata.org/wiki/Q3109175","display_name":"Context (archaeology)","level":2,"score":0.5869876146316528},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.543769121170044},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5422428846359253},{"id":"https://openalex.org/C98045186","wikidata":"https://www.wikidata.org/wiki/Q205663","display_name":"Process (computing)","level":2,"score":0.5005030632019043},{"id":"https://openalex.org/C48103436","wikidata":"https://www.wikidata.org/wiki/Q599031","display_name":"State (computer science)","level":2,"score":0.4217250943183899},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.34535276889801025},{"id":"https://openalex.org/C159886148","wikidata":"https://www.wikidata.org/wiki/Q176645","display_name":"Markov process","level":2,"score":0.2864640951156616},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.17466473579406738},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.11903244256973267},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.10799401998519897},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.0},{"id":"https://openalex.org/C151730666","wikidata":"https://www.wikidata.org/wiki/Q7205","display_name":"Paleontology","level":1,"score":0.0},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.0}],"mesh":[{"descriptor_ui":"D000069550","descriptor_name":"Machine Learning","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D000069550","descriptor_name":"Machine Learning","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D000069550","descriptor_name":"Machine Learning","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D000465","descriptor_name":"Algorithms","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D000465","descriptor_name":"Algorithms","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D000465","descriptor_name":"Algorithms","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D000818","descriptor_name":"Animals","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D000818","descriptor_name":"Animals","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D000818","descriptor_name":"Animals","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D001516","descriptor_name":"Bees","qualifier_ui":"Q000502","qualifier_name":"physiology","is_major_topic":false},{"descriptor_ui":"D001516","descriptor_name":"Bees","qualifier_ui":"Q000502","qualifier_name":"physiology","is_major_topic":false},{"descriptor_ui":"D001516","descriptor_name":"Bees","qualifier_ui":"Q000502","qualifier_name":"physiology","is_major_topic":false},{"descriptor_ui":"D003491","descriptor_name":"Cybernetics","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D003491","descriptor_name":"Cybernetics","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D003491","descriptor_name":"Cybernetics","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D008390","descriptor_name":"Markov Chains","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D008390","descriptor_name":"Markov Chains","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D008390","descriptor_name":"Markov Chains","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D012201","descriptor_name":"Reward","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D012201","descriptor_name":"Reward","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D012201","descriptor_name":"Reward","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true}],"locations_count":2,"locations":[{"id":"doi:10.1109/tcyb.2018.2838595","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tcyb.2018.2838595","pdf_url":null,"source":{"id":"https://openalex.org/S4210191041","display_name":"IEEE Transactions on Cybernetics","issn_l":"2168-2267","issn":["2168-2267","2168-2275"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Transactions on Cybernetics","raw_type":"journal-article"},{"id":"pmid:29994492","is_oa":false,"landing_page_url":"https://pubmed.ncbi.nlm.nih.gov/29994492","pdf_url":null,"source":{"id":"https://openalex.org/S4306525036","display_name":"PubMed","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I1299303238","host_organization_name":"National Institutes of Health","host_organization_lineage":["https://openalex.org/I1299303238"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE transactions on cybernetics","raw_type":null}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.6200000047683716,"id":"https://metadata.un.org/sdg/16","display_name":"Peace, Justice and strong institutions"}],"awards":[{"id":"https://openalex.org/G1815900017","display_name":"\u57fa\u4e8e\u524d\u89c6\u8282\u5fae\u7535\u523a\u6fc0\u7684\u718a\u8702\u673a\u5668\u4eba\u7cbe\u786e\u63a7\u5236\u6307\u4ee4\u96c6\u7814\u7a76","funder_award_id":"61572433","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G3992937643","display_name":null,"funder_award_id":"LZ14F020002","funder_id":"https://openalex.org/F4320338464","funder_display_name":"Natural Science Foundation of Zhejiang Province"},{"id":"https://openalex.org/G6779670841","display_name":null,"funder_award_id":"31627802","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G6806792462","display_name":null,"funder_award_id":"61473259","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"}],"funders":[{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"},{"id":"https://openalex.org/F4320338464","display_name":"Natural Science Foundation of Zhejiang Province","ror":"https://ror.org/01h0zpd94"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":68,"referenced_works":["https://openalex.org/W22201145","https://openalex.org/W87517536","https://openalex.org/W201683192","https://openalex.org/W1499408472","https://openalex.org/W1604037130","https://openalex.org/W1777239053","https://openalex.org/W1968233311","https://openalex.org/W1970647717","https://openalex.org/W1974740629","https://openalex.org/W1974883306","https://openalex.org/W1977016567","https://openalex.org/W1977655452","https://openalex.org/W1978375026","https://openalex.org/W1978942630","https://openalex.org/W1987254382","https://openalex.org/W1989279035","https://openalex.org/W1999874108","https://openalex.org/W2007658183","https://openalex.org/W2024341915","https://openalex.org/W2040860803","https://openalex.org/W2055363583","https://openalex.org/W2065220835","https://openalex.org/W2070938724","https://openalex.org/W2079998853","https://openalex.org/W2086207362","https://openalex.org/W2088877363","https://openalex.org/W2090158947","https://openalex.org/W2096018174","https://openalex.org/W2100945295","https://openalex.org/W2105681776","https://openalex.org/W2105726658","https://openalex.org/W2111787305","https://openalex.org/W2117341272","https://openalex.org/W2121863487","https://openalex.org/W2123167643","https://openalex.org/W2123657698","https://openalex.org/W2124657875","https://openalex.org/W2127240487","https://openalex.org/W2148570603","https://openalex.org/W2149096964","https://openalex.org/W2151250975","https://openalex.org/W2152188737","https://openalex.org/W2152662857","https://openalex.org/W2153525021","https://openalex.org/W2160337655","https://openalex.org/W2161009228","https://openalex.org/W2169209873","https://openalex.org/W2332970852","https://openalex.org/W2345097924","https://openalex.org/W2606548817","https://openalex.org/W2766447205","https://openalex.org/W2770799853","https://openalex.org/W2772709170","https://openalex.org/W3143867070","https://openalex.org/W4214717370","https://openalex.org/W4243954004","https://openalex.org/W6608308295","https://openalex.org/W6638088447","https://openalex.org/W6647940287","https://openalex.org/W6664597903","https://openalex.org/W6676332899","https://openalex.org/W6676780147","https://openalex.org/W6677347465","https://openalex.org/W6678636561","https://openalex.org/W6685331716","https://openalex.org/W6703067494","https://openalex.org/W6745620495","https://openalex.org/W6746177919"],"related_works":["https://openalex.org/W4400868993","https://openalex.org/W3096874164","https://openalex.org/W1985560493","https://openalex.org/W2386410636","https://openalex.org/W2357975469","https://openalex.org/W2145363145","https://openalex.org/W1626977535","https://openalex.org/W4284974072","https://openalex.org/W2341346307","https://openalex.org/W4404955202"],"abstract_inverted_index":{"Cyborg":[0],"insects":[1,31,50],"have":[2,11],"attracted":[3],"great":[4],"attention":[5],"as":[6,149],"the":[7,38,43,58,70,73,80,86,99,127,133,137,158,164,168,172,184,191,200,205,219],"flight":[8,128],"performance":[9],"they":[10],"is":[12,76,119,147,160,187],"incomparable":[13],"by":[14,203],"micro":[15],"aerial":[16],"vehicles":[17],"and":[18,41,93,101,106,122,152],"play":[19],"a":[20,104,140,150],"critical":[21],"role":[22],"in":[23,85,136],"supporting":[24],"extensive":[25],"applications.":[26],"Approaches":[27],"to":[28,162,171,189,199,217],"construct":[29],"cyborg":[30,49,109],"consist":[32],"of":[33,60,82,88,91,103,130,139,207],"two":[34],"major":[35],"issues:":[36],"1)":[37],"stimulating":[39],"paradigm":[40,118],"2)":[42],"control":[44,74,193],"policy.":[45,194],"At":[46],"present,":[47],"most":[48],"are":[51,197],"constructed":[52],"based":[53,112],"on":[54,113],"invasive":[55],"methods,":[56],"requiring":[57],"implantation":[59],"electrodes":[61],"into":[62],"neural":[63],"or":[64],"muscle":[65],"systems,":[66],"which":[67,83,180],"would":[68],"harm":[69],"insects.":[71],"As":[72],"policy":[75],"basically":[77],"manual":[78],"control,":[79],"shortcomings":[81],"lie":[84],"requirement":[87],"excessive":[89],"amount":[90],"experiments":[92],"focused":[94],"attention.":[95],"This":[96],"paper":[97],"presents":[98],"design":[100],"implementation":[102],"noninvasive":[105],"much":[107],"safer":[108],"insect":[110],"system":[111],"visual":[114],"stimulation.":[115],"The":[116,145],"tethered":[117],"adopted":[120],"here":[121],"we":[123],"look":[124],"at":[125],"controlling":[126],"behavior":[129,166],"bumblebees,":[131,209],"especially":[132],"abdominal-waving":[134,165,212],"behavior,":[135],"context":[138],"model-free":[141],"reinforcement":[142],"learning":[143,185],"problem.":[144],"problem":[146],"formulated":[148],"finite":[151],"deterministic":[153],"Markov":[154],"decision":[155],"process,":[156],"where":[157],"agent":[159],"designed":[161],"change":[163],"from":[167],"initial":[169],"state":[170,213,221],"target":[173,220],"state.":[174],"Sarsa":[175],"with":[176,223],"transformed":[177],"reward":[178],"function":[179],"can":[181,214],"speed":[182],"up":[183],"process":[186],"employed":[188],"learn":[190],"optimal":[192],"Learned":[195],"policies":[196],"compared":[198],"stochastic":[201],"one":[202],"evaluating":[204],"results":[206],"ten":[208],"demonstrating":[210],"that":[211],"be":[215],"modulated":[216],"approximate":[218],"quickly":[222],"small":[224],"deviation.":[225]},"counts_by_year":[{"year":2025,"cited_by_count":2},{"year":2024,"cited_by_count":4},{"year":2023,"cited_by_count":2},{"year":2022,"cited_by_count":3},{"year":2021,"cited_by_count":4},{"year":2020,"cited_by_count":3},{"year":2019,"cited_by_count":2}],"updated_date":"2026-07-22T07:51:19.307946","created_date":"2025-10-10T00:00:00"}