{"id":"https://openalex.org/W4220774516","doi":"https://doi.org/10.1109/tnnls.2022.3155483","title":"Robust Actor-Critic With Relative Entropy Regulating Actor","display_name":"Robust Actor-Critic With Relative Entropy Regulating Actor","publication_year":2022,"publication_date":"2022-03-14","ids":{"openalex":"https://openalex.org/W4220774516","doi":"https://doi.org/10.1109/tnnls.2022.3155483","pmid":"https://pubmed.ncbi.nlm.nih.gov/35286268"},"language":"en","primary_location":{"id":"doi:10.1109/tnnls.2022.3155483","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tnnls.2022.3155483","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":"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/A5091364297","display_name":"Yuhu Cheng","orcid":"https://orcid.org/0000-0003-2022-9999"},"institutions":[{"id":"https://openalex.org/I25757504","display_name":"China University of Mining and Technology","ror":"https://ror.org/01xt2dr21","country_code":"CN","type":"education","lineage":["https://openalex.org/I25757504"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yuhu Cheng","raw_affiliation_strings":["Engineering Research Center of Intelligent Control for Underground Space, Ministry of Education, and the School of Information and Control Engineering, China University of Mining and Technology, Xuzhou, China"],"raw_orcid":"https://orcid.org/0000-0003-2022-9999","affiliations":[{"raw_affiliation_string":"Engineering Research Center of Intelligent Control for Underground Space, Ministry of Education, and the School of Information and Control Engineering, China University of Mining and Technology, Xuzhou, China","institution_ids":["https://openalex.org/I25757504"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5085372626","display_name":"Longyang Huang","orcid":"https://orcid.org/0000-0001-5123-5043"},"institutions":[{"id":"https://openalex.org/I25757504","display_name":"China University of Mining and Technology","ror":"https://ror.org/01xt2dr21","country_code":"CN","type":"education","lineage":["https://openalex.org/I25757504"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Longyang Huang","raw_affiliation_strings":["Engineering Research Center of Intelligent Control for Underground Space, Ministry of Education, and the School of Information and Control Engineering, China University of Mining and Technology, Xuzhou, China"],"raw_orcid":"https://orcid.org/0000-0001-5123-5043","affiliations":[{"raw_affiliation_string":"Engineering Research Center of Intelligent Control for Underground Space, Ministry of Education, and the School of Information and Control Engineering, China University of Mining and Technology, Xuzhou, China","institution_ids":["https://openalex.org/I25757504"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100643265","display_name":"C. L. Philip Chen","orcid":"https://orcid.org/0000-0001-5451-7230"},"institutions":[{"id":"https://openalex.org/I90610280","display_name":"South China University of Technology","ror":"https://ror.org/0530pts50","country_code":"CN","type":"education","lineage":["https://openalex.org/I90610280"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"C. L. Philip Chen","raw_affiliation_strings":["School of Computer Science and Engineering, South China University of Technology, Guangzhou, China"],"raw_orcid":"https://orcid.org/0000-0001-5451-7230","affiliations":[{"raw_affiliation_string":"School of Computer Science and Engineering, South China University of Technology, Guangzhou, China","institution_ids":["https://openalex.org/I90610280"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5108064895","display_name":"Xuesong Wang","orcid":"https://orcid.org/0000-0002-5327-1088"},"institutions":[{"id":"https://openalex.org/I25757504","display_name":"China University of Mining and Technology","ror":"https://ror.org/01xt2dr21","country_code":"CN","type":"education","lineage":["https://openalex.org/I25757504"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xuesong Wang","raw_affiliation_strings":["Engineering Research Center of Intelligent Control for Underground Space, Ministry of Education, and the School of Information and Control Engineering, China University of Mining and Technology, Xuzhou, China"],"raw_orcid":"https://orcid.org/0000-0002-5327-1088","affiliations":[{"raw_affiliation_string":"Engineering Research Center of Intelligent Control for Underground Space, Ministry of Education, and the School of Information and Control Engineering, China University of Mining and Technology, Xuzhou, China","institution_ids":["https://openalex.org/I25757504"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":1.5746,"has_fulltext":false,"cited_by_count":13,"citation_normalized_percentile":{"value":0.85185786,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":99},"biblio":{"volume":"34","issue":"11","first_page":"9054","last_page":"9063"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10462","display_name":"Reinforcement Learning in Robotics","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"}},"topics":[{"id":"https://openalex.org/T10462","display_name":"Reinforcement Learning in Robotics","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/T11574","display_name":"Artificial Intelligence in Games","score":0.9894999861717224,"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/T12002","display_name":"Computability, Logic, AI Algorithms","score":0.9501000046730042,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/kullback\u2013leibler-divergence","display_name":"Kullback\u2013Leibler divergence","score":0.47966933250427246},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.408689945936203},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.2687340974807739}],"concepts":[{"id":"https://openalex.org/C171752962","wikidata":"https://www.wikidata.org/wiki/Q255166","display_name":"Kullback\u2013Leibler divergence","level":2,"score":0.47966933250427246},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.408689945936203},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.2687340974807739}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/tnnls.2022.3155483","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tnnls.2022.3155483","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:35286268","is_oa":false,"landing_page_url":"https://pubmed.ncbi.nlm.nih.gov/35286268","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}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G4756161396","display_name":null,"funder_award_id":"62176259","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G6792490895","display_name":null,"funder_award_id":"61976215","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"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":51,"referenced_works":["https://openalex.org/W1499669280","https://openalex.org/W1771410628","https://openalex.org/W2145339207","https://openalex.org/W2411727234","https://openalex.org/W2736601468","https://openalex.org/W2746553466","https://openalex.org/W2781726626","https://openalex.org/W2787938642","https://openalex.org/W2802164917","https://openalex.org/W2904246096","https://openalex.org/W2907385442","https://openalex.org/W2907537824","https://openalex.org/W2918343027","https://openalex.org/W2949561945","https://openalex.org/W2963849886","https://openalex.org/W2963864421","https://openalex.org/W2965140792","https://openalex.org/W2966349401","https://openalex.org/W2968831808","https://openalex.org/W2975395546","https://openalex.org/W3000642679","https://openalex.org/W3004430023","https://openalex.org/W3010740942","https://openalex.org/W3087081411","https://openalex.org/W3092253573","https://openalex.org/W3124201714","https://openalex.org/W3131678030","https://openalex.org/W3135203571","https://openalex.org/W4214717370","https://openalex.org/W4298857966","https://openalex.org/W4302570325","https://openalex.org/W4313069952","https://openalex.org/W6637967152","https://openalex.org/W6638018090","https://openalex.org/W6684205842","https://openalex.org/W6684921986","https://openalex.org/W6715342929","https://openalex.org/W6734517396","https://openalex.org/W6740471745","https://openalex.org/W6741002519","https://openalex.org/W6747473740","https://openalex.org/W6748839928","https://openalex.org/W6751792830","https://openalex.org/W6757592117","https://openalex.org/W6757947852","https://openalex.org/W6768017362","https://openalex.org/W6773740980","https://openalex.org/W6784732189","https://openalex.org/W6789934133","https://openalex.org/W6791906457","https://openalex.org/W6810568201"],"related_works":["https://openalex.org/W4391375266","https://openalex.org/W2899084033","https://openalex.org/W2748952813","https://openalex.org/W2390279801","https://openalex.org/W4391913857","https://openalex.org/W2358668433","https://openalex.org/W4396701345","https://openalex.org/W2376932109","https://openalex.org/W2001405890","https://openalex.org/W4396696052"],"abstract_inverted_index":{"The":[0,87,131],"accurate":[1],"estimation":[2],"of":[3,8,16,82,114],"Q-function":[4,54],"and":[5,68,154],"the":[6,22,46,51,61,65,69,75,80,83,92,96,102,111,122,127,140,151,155],"enhancement":[7],"agent's":[9],"exploration":[10,112],"ability":[11,113],"have":[12],"always":[13],"been":[14],"challenges":[15],"off-policy":[17],"actor-critic":[18,28],"algorithms.":[19,166],"To":[20],"address":[21],"two":[23],"concerns,":[24],"a":[25,38],"novel":[26],"robust":[27,39],"(RAC)":[29],"is":[30,99,104,107,118,134,143],"developed":[31,119,132],"in":[32,72,150],"this":[33],"article.":[34],"We":[35],"first":[36],"derive":[37],"policy":[40,49,57,67,73,84,97,103],"improvement":[41,129],"mechanism":[42],"(RPIM)":[43],"by":[44,120],"using":[45],"local":[47],"optimal":[48],"about":[50],"current":[52],"estimated":[53],"to":[55,94,109,125,136],"guide":[56],"improvement.":[58],"By":[59],"constraining":[60],"relative":[62],"entropy":[63,98],"between":[64],"new":[66],"previous":[70],"one":[71],"improvement,":[74],"proposed":[76,123,141],"RPIM":[77,124],"can":[78],"enhance":[79],"stability":[81],"update":[85],"process.":[86,130],"theoretical":[88],"analysis":[89],"shows":[90],"that":[91,159],"incentive":[93],"increase":[95],"endowed":[100],"when":[101],"updated,":[105],"which":[106],"conducive":[108],"enhancing":[110],"agents.":[115],"Then,":[116],"RAC":[117,133,142,160],"applying":[121],"regulate":[126],"actor":[128],"proven":[135],"be":[137],"convergent.":[138],"Finally,":[139],"evaluated":[144],"on":[145],"some":[146],"continuous-action":[147],"control":[148],"tasks":[149],"MuJoCo":[152],"platform":[153],"experimental":[156],"results":[157],"show":[158],"outperforms":[161],"several":[162],"state-of-the-art":[163],"reinforcement":[164],"learning":[165]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":6},{"year":2024,"cited_by_count":5},{"year":2023,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}