{"id":"https://openalex.org/W3026133783","doi":"https://doi.org/10.1109/tnnls.2021.3119853","title":"Gradient Monitored Reinforcement Learning","display_name":"Gradient Monitored Reinforcement Learning","publication_year":2021,"publication_date":"2021-10-25","ids":{"openalex":"https://openalex.org/W3026133783","doi":"https://doi.org/10.1109/tnnls.2021.3119853","mag":"3026133783","pmid":"https://pubmed.ncbi.nlm.nih.gov/34695008"},"language":"en","primary_location":{"id":"doi:10.1109/tnnls.2021.3119853","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tnnls.2021.3119853","pdf_url":null,"source":{"id":"https://openalex.org/S4210175523","display_name":"IEEE Transactions on Neural Networks and Learning Systems","issn_l":"2162-237X","issn":["2162-237X","2162-2388"],"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 Neural Networks and Learning Systems","raw_type":"journal-article"},"type":"preprint","indexed_in":["arxiv","crossref","datacite","pubmed"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2005.12108","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5076820104","display_name":"Mohammed Sharafath Abdul Hameed","orcid":"https://orcid.org/0000-0002-1792-7748"},"institutions":[{"id":"https://openalex.org/I3130920692","display_name":"South Westphalia University of Applied Sciences","ror":"https://ror.org/04t5phd24","country_code":"DE","type":"education","lineage":["https://openalex.org/I3130920692"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Mohammed Sharafath Abdul Hameed","raw_affiliation_strings":["Department of Automation Technology, South Westphalia University of Applied Sciences, Soest, Germany","South Westphalia Univ. of Applied Sciences (Germany)"],"raw_orcid":"https://orcid.org/0000-0002-1792-7748","affiliations":[{"raw_affiliation_string":"Department of Automation Technology, South Westphalia University of Applied Sciences, Soest, Germany","institution_ids":["https://openalex.org/I3130920692"]},{"raw_affiliation_string":"South Westphalia Univ. of Applied Sciences (Germany)","institution_ids":["https://openalex.org/I3130920692"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5067762331","display_name":"Gavneet Singh Chadha","orcid":"https://orcid.org/0000-0002-9374-9074"},"institutions":[{"id":"https://openalex.org/I3130920692","display_name":"South Westphalia University of Applied Sciences","ror":"https://ror.org/04t5phd24","country_code":"DE","type":"education","lineage":["https://openalex.org/I3130920692"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Gavneet Singh Chadha","raw_affiliation_strings":["Department of Automation Technology, South Westphalia University of Applied Sciences, Soest, Germany","South Westphalia Univ. of Applied Sciences (Germany)"],"raw_orcid":"https://orcid.org/0000-0002-9374-9074","affiliations":[{"raw_affiliation_string":"Department of Automation Technology, South Westphalia University of Applied Sciences, Soest, Germany","institution_ids":["https://openalex.org/I3130920692"]},{"raw_affiliation_string":"South Westphalia Univ. of Applied Sciences (Germany)","institution_ids":["https://openalex.org/I3130920692"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5025397538","display_name":"Andreas Schwung","orcid":"https://orcid.org/0000-0001-8405-0977"},"institutions":[{"id":"https://openalex.org/I3130920692","display_name":"South Westphalia University of Applied Sciences","ror":"https://ror.org/04t5phd24","country_code":"DE","type":"education","lineage":["https://openalex.org/I3130920692"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Andreas Schwung","raw_affiliation_strings":["Department of Automation Technology, South Westphalia University of Applied Sciences, Soest, Germany","South Westphalia Univ. of Applied Sciences (Germany)"],"raw_orcid":"https://orcid.org/0000-0001-8405-0977","affiliations":[{"raw_affiliation_string":"Department of Automation Technology, South Westphalia University of Applied Sciences, Soest, Germany","institution_ids":["https://openalex.org/I3130920692"]},{"raw_affiliation_string":"South Westphalia Univ. of Applied Sciences (Germany)","institution_ids":["https://openalex.org/I3130920692"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5046071840","display_name":"Steven X. Ding","orcid":"https://orcid.org/0000-0002-5149-5918"},"institutions":[{"id":"https://openalex.org/I62318514","display_name":"University of Duisburg-Essen","ror":"https://ror.org/04mz5ra38","country_code":"DE","type":"education","lineage":["https://openalex.org/I62318514"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Steven X. Ding","raw_affiliation_strings":["Department of Automatic Control and Complex Systems, University of Duisburg-Essen, Duisburg, Germany","University of Duisburg-Essen, Germany"],"raw_orcid":"https://orcid.org/0000-0002-5149-5918","affiliations":[{"raw_affiliation_string":"Department of Automatic Control and Complex Systems, University of Duisburg-Essen, Duisburg, Germany","institution_ids":["https://openalex.org/I62318514"]},{"raw_affiliation_string":"University of Duisburg-Essen, Germany","institution_ids":["https://openalex.org/I62318514"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":1,"citation_normalized_percentile":{"value":0.00545802,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":94},"biblio":{"volume":"34","issue":"8","first_page":"4106","last_page":"4119"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10462","display_name":"Reinforcement Learning in Robotics","score":0.9991999864578247,"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":0.9991999864578247,"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/T12676","display_name":"Machine Learning and ELM","score":0.9983999729156494,"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/T12611","display_name":"Neural Networks and Reservoir Computing","score":0.9980999827384949,"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":0.82331383228302},{"id":"https://openalex.org/keywords/generalization","display_name":"Generalization","score":0.6958186626434326},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.6836035251617432},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6404911279678345},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.562959611415863},{"id":"https://openalex.org/keywords/convergence","display_name":"Convergence (economics)","score":0.5499557256698608},{"id":"https://openalex.org/keywords/process","display_name":"Process (computing)","score":0.5454188585281372},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.49307844042778015},{"id":"https://openalex.org/keywords/gradient-method","display_name":"Gradient method","score":0.4617386758327484},{"id":"https://openalex.org/keywords/variance","display_name":"Variance (accounting)","score":0.4292856752872467},{"id":"https://openalex.org/keywords/momentum","display_name":"Momentum (technical analysis)","score":0.41364622116088867},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.4089556932449341},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.3154760003089905},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.20644015073776245},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.11671227216720581}],"concepts":[{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.82331383228302},{"id":"https://openalex.org/C177148314","wikidata":"https://www.wikidata.org/wiki/Q170084","display_name":"Generalization","level":2,"score":0.6958186626434326},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.6836035251617432},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6404911279678345},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.562959611415863},{"id":"https://openalex.org/C2777303404","wikidata":"https://www.wikidata.org/wiki/Q759757","display_name":"Convergence (economics)","level":2,"score":0.5499557256698608},{"id":"https://openalex.org/C98045186","wikidata":"https://www.wikidata.org/wiki/Q205663","display_name":"Process (computing)","level":2,"score":0.5454188585281372},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.49307844042778015},{"id":"https://openalex.org/C115680565","wikidata":"https://www.wikidata.org/wiki/Q5977448","display_name":"Gradient method","level":2,"score":0.4617386758327484},{"id":"https://openalex.org/C196083921","wikidata":"https://www.wikidata.org/wiki/Q7915758","display_name":"Variance (accounting)","level":2,"score":0.4292856752872467},{"id":"https://openalex.org/C60718061","wikidata":"https://www.wikidata.org/wiki/Q1414747","display_name":"Momentum (technical analysis)","level":2,"score":0.41364622116088867},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.4089556932449341},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.3154760003089905},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.20644015073776245},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.11671227216720581},{"id":"https://openalex.org/C10138342","wikidata":"https://www.wikidata.org/wiki/Q43015","display_name":"Finance","level":1,"score":0.0},{"id":"https://openalex.org/C121955636","wikidata":"https://www.wikidata.org/wiki/Q4116214","display_name":"Accounting","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},{"id":"https://openalex.org/C50522688","wikidata":"https://www.wikidata.org/wiki/Q189833","display_name":"Economic growth","level":1,"score":0.0},{"id":"https://openalex.org/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","level":0,"score":0.0},{"id":"https://openalex.org/C144133560","wikidata":"https://www.wikidata.org/wiki/Q4830453","display_name":"Business","level":0,"score":0.0},{"id":"https://openalex.org/C134306372","wikidata":"https://www.wikidata.org/wiki/Q7754","display_name":"Mathematical analysis","level":1,"score":0.0},{"id":"https://openalex.org/C201995342","wikidata":"https://www.wikidata.org/wiki/Q682496","display_name":"Systems engineering","level":1,"score":0.0}],"mesh":[],"locations_count":5,"locations":[{"id":"doi:10.1109/tnnls.2021.3119853","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tnnls.2021.3119853","pdf_url":null,"source":{"id":"https://openalex.org/S4210175523","display_name":"IEEE Transactions on Neural Networks and Learning Systems","issn_l":"2162-237X","issn":["2162-237X","2162-2388"],"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 Neural Networks and Learning Systems","raw_type":"journal-article"},{"id":"pmid:34695008","is_oa":false,"landing_page_url":"https://pubmed.ncbi.nlm.nih.gov/34695008","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 neural networks and learning systems","raw_type":null},{"id":"pmh:oai:arXiv.org:2005.12108","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2005.12108","pdf_url":"https://arxiv.org/pdf/2005.12108","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"text"},{"id":"mag:3026133783","is_oa":true,"landing_page_url":"http://export.arxiv.org/pdf/2005.12108","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"arXiv (Cornell University)","raw_type":null},{"id":"doi:10.48550/arxiv.2005.12108","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2005.12108","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":null,"is_accepted":false,"is_published":null,"raw_source_name":null,"raw_type":"Preprint"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2005.12108","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2005.12108","pdf_url":"https://arxiv.org/pdf/2005.12108","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"text"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":89,"referenced_works":["https://openalex.org/W4919037","https://openalex.org/W179875071","https://openalex.org/W1533861849","https://openalex.org/W1677182931","https://openalex.org/W1815076433","https://openalex.org/W1826234144","https://openalex.org/W2022740958","https://openalex.org/W2069143585","https://openalex.org/W2107544712","https://openalex.org/W2108682071","https://openalex.org/W2114766824","https://openalex.org/W2145339207","https://openalex.org/W2150468603","https://openalex.org/W2156387975","https://openalex.org/W2158782408","https://openalex.org/W2163321856","https://openalex.org/W2250904038","https://openalex.org/W2522489477","https://openalex.org/W2556833785","https://openalex.org/W2575705757","https://openalex.org/W2596758708","https://openalex.org/W2766447205","https://openalex.org/W2770799853","https://openalex.org/W2859870583","https://openalex.org/W2891790128","https://openalex.org/W2912260645","https://openalex.org/W2913180865","https://openalex.org/W2913340405","https://openalex.org/W2947644971","https://openalex.org/W2962887844","https://openalex.org/W2962902376","https://openalex.org/W2963247446","https://openalex.org/W2963376662","https://openalex.org/W2963518130","https://openalex.org/W2963523627","https://openalex.org/W2963674932","https://openalex.org/W2963815651","https://openalex.org/W2963923407","https://openalex.org/W2963940579","https://openalex.org/W2964121744","https://openalex.org/W2970214542","https://openalex.org/W2970971581","https://openalex.org/W2994747431","https://openalex.org/W2996577930","https://openalex.org/W3036329728","https://openalex.org/W3038041907","https://openalex.org/W4250965498","https://openalex.org/W6600213771","https://openalex.org/W6631190155","https://openalex.org/W6631943919","https://openalex.org/W6638018090","https://openalex.org/W6638545294","https://openalex.org/W6638667902","https://openalex.org/W6638836233","https://openalex.org/W6674330103","https://openalex.org/W6674385629","https://openalex.org/W6676023451","https://openalex.org/W6677088747","https://openalex.org/W6678583879","https://openalex.org/W6682889407","https://openalex.org/W6684113996","https://openalex.org/W6684921986","https://openalex.org/W6685757253","https://openalex.org/W6692846177","https://openalex.org/W6729972426","https://openalex.org/W6730169791","https://openalex.org/W6735506055","https://openalex.org/W6741002519","https://openalex.org/W6747092830","https://openalex.org/W6747473740","https://openalex.org/W6748581759","https://openalex.org/W6748839928","https://openalex.org/W6753325967","https://openalex.org/W6754521519","https://openalex.org/W6755166560","https://openalex.org/W6756840741","https://openalex.org/W6758432988","https://openalex.org/W6758731277","https://openalex.org/W6761328699","https://openalex.org/W6762947928","https://openalex.org/W6764345721","https://openalex.org/W6766978945","https://openalex.org/W6767141496","https://openalex.org/W6771570156","https://openalex.org/W6771738409","https://openalex.org/W6772129282","https://openalex.org/W6774302960","https://openalex.org/W6780559895","https://openalex.org/W6863618527"],"related_works":["https://openalex.org/W3209616537","https://openalex.org/W2967645217","https://openalex.org/W3088331655","https://openalex.org/W1966805688","https://openalex.org/W2290354866","https://openalex.org/W2752954743","https://openalex.org/W2935588605","https://openalex.org/W2989988749","https://openalex.org/W1997816436","https://openalex.org/W3185109031","https://openalex.org/W2230869072","https://openalex.org/W2971705906","https://openalex.org/W2077194309","https://openalex.org/W2808421695","https://openalex.org/W3095594668","https://openalex.org/W2369463503","https://openalex.org/W2975260096","https://openalex.org/W2947612938","https://openalex.org/W1561685851","https://openalex.org/W2962779867"],"abstract_inverted_index":{"This":[0],"article":[1],"presents":[2],"a":[3,43,58,69,114,166],"novel":[4],"neural":[5,70],"network":[6,71,125,178],"training":[7,28,81,181],"approach":[8],"for":[9,113,144,171],"faster":[10],"convergence":[11],"and":[12,29,77,200,203,213,226],"better":[13],"generalization":[14,235],"abilities":[15],"in":[16,32,64,123,232],"deep":[17,177],"reinforcement":[18],"learning":[19,46,63,129,149,156],"(RL).":[20],"Particularly,":[21],"we":[22,52,93],"focus":[23],"on":[24,73,127,158],"the":[25,62,65,74,80,89,97,101,105,118,124,134,137,159,162,175,183,224,230],"enhancement":[26],"of":[27,68,88,100,104,117,120,150,174,229,234],"evaluation":[30],"performance":[31,99,227],"RL":[33],"algorithms":[34],"by":[35],"systematically":[36],"reducing":[37],"gradient's":[38],"variance":[39],"and,":[40],"thereby,":[41],"providing":[42],"more":[44,154],"targeted":[45],"process.":[47],"The":[48,189,219],"proposed":[49,106],"method,":[50,141],"which":[51,142],"term":[53],"gradient":[54],"monitoring":[55],"(GM),":[56],"is":[57,191],"method":[59,91,135,184,190],"to":[60,95,193],"steer":[61],"weight":[66],"parameters":[67],"based":[72,126],"dynamic":[75],"development":[76],"feedback":[78,160],"from":[79,161],"process":[82],"itself.":[83],"We":[84,131],"propose":[85],"different":[86],"variants":[87],"GM":[90,110],"that":[92],"prove":[94],"increase":[96],"underlying":[98],"model.":[102],"One":[103],"variants,":[107],"momentum":[108],"with":[109,136],"(M-WGM),":[111],"allows":[112,143,170],"continuous":[115,205],"adjustment":[116,146],"quantum":[119],"backpropagated":[121],"gradients":[122],"certain":[128,151],"parameters.":[130],"further":[132],"enhance":[133],"adaptive":[138],"M-WGM":[139],"(AM-WGM)":[140],"automatic":[145,172],"between":[147],"focused":[148],"weights":[152],"versus":[153],"dispersed":[155],"depending":[157],"rewards":[163],"collected.":[164],"As":[165],"by-product,":[167],"it":[168],"also":[169],"derivation":[173],"required":[176],"sizes":[179],"during":[180],"as":[182],"automatically":[185],"freezes":[186],"trained":[187],"weights.":[188],"applied":[192],"two":[194],"discrete":[195],"(real-world":[196],"multirobot":[197],"coordination":[198],"problems":[199],"Atari":[201],"games)":[202],"one":[204],"control":[206],"task":[207],"(MuJoCo)":[208],"using":[209],"advantage":[210],"actor-critic":[211],"(A2C)":[212],"proximal":[214],"policy":[215],"optimization":[216],"(PPO),":[217],"respectively.":[218],"results":[220],"obtained":[221],"particularly":[222],"underline":[223],"applicability":[225],"improvements":[228],"methods":[231],"terms":[233],"capability.":[236]},"counts_by_year":[{"year":2020,"cited_by_count":1}],"updated_date":"2026-07-01T08:55:40.977307","created_date":"2025-10-10T00:00:00"}