{"id":"https://openalex.org/W4307772200","doi":"https://doi.org/10.1109/tnnls.2022.3215596","title":"Improving Exploration in Actor\u2013Critic With Weakly Pessimistic Value Estimation and Optimistic Policy Optimization","display_name":"Improving Exploration in Actor\u2013Critic With Weakly Pessimistic Value Estimation and Optimistic Policy Optimization","publication_year":2022,"publication_date":"2022-11-04","ids":{"openalex":"https://openalex.org/W4307772200","doi":"https://doi.org/10.1109/tnnls.2022.3215596","pmid":"https://pubmed.ncbi.nlm.nih.gov/36306289"},"language":"en","primary_location":{"id":"doi:10.1109/tnnls.2022.3215596","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tnnls.2022.3215596","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/A5029261237","display_name":"Fan Li","orcid":"https://orcid.org/0000-0001-8949-4905"},"institutions":[{"id":"https://openalex.org/I150229711","display_name":"University of Electronic Science and Technology of China","ror":"https://ror.org/04qr3zq92","country_code":"CN","type":"education","lineage":["https://openalex.org/I150229711"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Fan Li","raw_affiliation_strings":["School of Computer Science and Engineering, University of Electronic Science and Technology of China, Chengdu, China"],"raw_orcid":"https://orcid.org/0000-0001-8949-4905","affiliations":[{"raw_affiliation_string":"School of Computer Science and Engineering, University of Electronic Science and Technology of China, Chengdu, China","institution_ids":["https://openalex.org/I150229711"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5002397214","display_name":"Mingsheng Fu","orcid":"https://orcid.org/0000-0002-9257-126X"},"institutions":[{"id":"https://openalex.org/I150229711","display_name":"University of Electronic Science and Technology of China","ror":"https://ror.org/04qr3zq92","country_code":"CN","type":"education","lineage":["https://openalex.org/I150229711"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Mingsheng Fu","raw_affiliation_strings":["School of Computer Science and Engineering, University of Electronic Science and Technology of China, Chengdu, China"],"raw_orcid":"https://orcid.org/0000-0002-9257-126X","affiliations":[{"raw_affiliation_string":"School of Computer Science and Engineering, University of Electronic Science and Technology of China, Chengdu, China","institution_ids":["https://openalex.org/I150229711"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100687323","display_name":"Wenyu Chen","orcid":"https://orcid.org/0000-0002-9933-8014"},"institutions":[{"id":"https://openalex.org/I150229711","display_name":"University of Electronic Science and Technology of China","ror":"https://ror.org/04qr3zq92","country_code":"CN","type":"education","lineage":["https://openalex.org/I150229711"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Wenyu Chen","raw_affiliation_strings":["School of Computer Science and Engineering, University of Electronic Science and Technology of China, Chengdu, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Computer Science and Engineering, University of Electronic Science and Technology of China, Chengdu, China","institution_ids":["https://openalex.org/I150229711"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100403375","display_name":"Fan Zhang","orcid":"https://orcid.org/0000-0001-5894-3237"},"institutions":[{"id":"https://openalex.org/I150229711","display_name":"University of Electronic Science and Technology of China","ror":"https://ror.org/04qr3zq92","country_code":"CN","type":"education","lineage":["https://openalex.org/I150229711"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Fan Zhang","raw_affiliation_strings":["School of Computer Science and Engineering, University of Electronic Science and Technology of China, Chengdu, China"],"raw_orcid":"https://orcid.org/0000-0001-5894-3237","affiliations":[{"raw_affiliation_string":"School of Computer Science and Engineering, University of Electronic Science and Technology of China, Chengdu, China","institution_ids":["https://openalex.org/I150229711"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5064083580","display_name":"Haixian Zhang","orcid":"https://orcid.org/0000-0002-9821-508X"},"institutions":[{"id":"https://openalex.org/I24185976","display_name":"Sichuan University","ror":"https://ror.org/011ashp19","country_code":"CN","type":"education","lineage":["https://openalex.org/I24185976"]},{"id":"https://openalex.org/I4210125143","display_name":"Chengdu University","ror":"https://ror.org/034z67559","country_code":"CN","type":"education","lineage":["https://openalex.org/I4210125143"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Haixian Zhang","raw_affiliation_strings":["School of Computer Science, Sichuan University, Chengdu, China"],"raw_orcid":"https://orcid.org/0000-0002-9821-508X","affiliations":[{"raw_affiliation_string":"School of Computer Science, Sichuan University, Chengdu, China","institution_ids":["https://openalex.org/I4210125143","https://openalex.org/I24185976"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5021975286","display_name":"Hong Qu","orcid":"https://orcid.org/0000-0001-6114-3441"},"institutions":[{"id":"https://openalex.org/I150229711","display_name":"University of Electronic Science and Technology of China","ror":"https://ror.org/04qr3zq92","country_code":"CN","type":"education","lineage":["https://openalex.org/I150229711"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Hong Qu","raw_affiliation_strings":["School of Computer Science and Engineering, University of Electronic Science and Technology of China, Chengdu, China"],"raw_orcid":"https://orcid.org/0000-0001-6114-3441","affiliations":[{"raw_affiliation_string":"School of Computer Science and Engineering, University of Electronic Science and Technology of China, Chengdu, China","institution_ids":["https://openalex.org/I150229711"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5100388188","display_name":"Yi Zhang","orcid":"https://orcid.org/0000-0002-5867-9322"},"institutions":[{"id":"https://openalex.org/I24185976","display_name":"Sichuan University","ror":"https://ror.org/011ashp19","country_code":"CN","type":"education","lineage":["https://openalex.org/I24185976"]},{"id":"https://openalex.org/I4210125143","display_name":"Chengdu University","ror":"https://ror.org/034z67559","country_code":"CN","type":"education","lineage":["https://openalex.org/I4210125143"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zhang Yi","raw_affiliation_strings":["School of Computer Science, Sichuan University, Chengdu, China"],"raw_orcid":"https://orcid.org/0000-0002-5867-9322","affiliations":[{"raw_affiliation_string":"School of Computer Science, Sichuan University, Chengdu, China","institution_ids":["https://openalex.org/I4210125143","https://openalex.org/I24185976"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":7,"corresponding_author_ids":["https://openalex.org/A5029261237"],"corresponding_institution_ids":["https://openalex.org/I150229711"],"apc_list":null,"apc_paid":null,"fwci":2.2197,"has_fulltext":false,"cited_by_count":17,"citation_normalized_percentile":{"value":0.89630713,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":96,"max":99},"biblio":{"volume":"35","issue":"7","first_page":"8783","last_page":"8796"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10462","display_name":"Reinforcement Learning in Robotics","score":0.9990000128746033,"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":0.9990000128746033,"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/T11689","display_name":"Adversarial Robustness in Machine Learning","score":0.9861999750137329,"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/T10036","display_name":"Advanced Neural Network Applications","score":0.982200026512146,"subfield":{"id":"https://openalex.org/subfields/1707","display_name":"Computer Vision and Pattern Recognition"},"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/pessimism","display_name":"Pessimism","score":0.7357597351074219},{"id":"https://openalex.org/keywords/notation","display_name":"Notation","score":0.5824381709098816},{"id":"https://openalex.org/keywords/value","display_name":"Value (mathematics)","score":0.566949725151062},{"id":"https://openalex.org/keywords/bounded-function","display_name":"Bounded function","score":0.5595523715019226},{"id":"https://openalex.org/keywords/bellman-equation","display_name":"Bellman equation","score":0.5137880444526672},{"id":"https://openalex.org/keywords/sample","display_name":"Sample (material)","score":0.4830963611602783},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.4734342098236084},{"id":"https://openalex.org/keywords/control","display_name":"Control (management)","score":0.4223948121070862},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.41332775354385376},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.3897758424282074},{"id":"https://openalex.org/keywords/mathematical-optimization","display_name":"Mathematical optimization","score":0.37554430961608887},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.34685665369033813},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.3027108907699585},{"id":"https://openalex.org/keywords/arithmetic","display_name":"Arithmetic","score":0.1677955687046051}],"concepts":[{"id":"https://openalex.org/C9992130","wikidata":"https://www.wikidata.org/wiki/Q484954","display_name":"Pessimism","level":2,"score":0.7357597351074219},{"id":"https://openalex.org/C45357846","wikidata":"https://www.wikidata.org/wiki/Q2001982","display_name":"Notation","level":2,"score":0.5824381709098816},{"id":"https://openalex.org/C2776291640","wikidata":"https://www.wikidata.org/wiki/Q2912517","display_name":"Value (mathematics)","level":2,"score":0.566949725151062},{"id":"https://openalex.org/C34388435","wikidata":"https://www.wikidata.org/wiki/Q2267362","display_name":"Bounded function","level":2,"score":0.5595523715019226},{"id":"https://openalex.org/C14646407","wikidata":"https://www.wikidata.org/wiki/Q1430750","display_name":"Bellman equation","level":2,"score":0.5137880444526672},{"id":"https://openalex.org/C198531522","wikidata":"https://www.wikidata.org/wiki/Q485146","display_name":"Sample (material)","level":2,"score":0.4830963611602783},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.4734342098236084},{"id":"https://openalex.org/C2775924081","wikidata":"https://www.wikidata.org/wiki/Q55608371","display_name":"Control (management)","level":2,"score":0.4223948121070862},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.41332775354385376},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3897758424282074},{"id":"https://openalex.org/C126255220","wikidata":"https://www.wikidata.org/wiki/Q141495","display_name":"Mathematical optimization","level":1,"score":0.37554430961608887},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.34685665369033813},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.3027108907699585},{"id":"https://openalex.org/C94375191","wikidata":"https://www.wikidata.org/wiki/Q11205","display_name":"Arithmetic","level":1,"score":0.1677955687046051},{"id":"https://openalex.org/C111472728","wikidata":"https://www.wikidata.org/wiki/Q9471","display_name":"Epistemology","level":1,"score":0.0},{"id":"https://openalex.org/C43617362","wikidata":"https://www.wikidata.org/wiki/Q170050","display_name":"Chromatography","level":1,"score":0.0},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"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/C134306372","wikidata":"https://www.wikidata.org/wiki/Q7754","display_name":"Mathematical analysis","level":1,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/tnnls.2022.3215596","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tnnls.2022.3215596","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:36306289","is_oa":false,"landing_page_url":"https://pubmed.ncbi.nlm.nih.gov/36306289","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":[{"display_name":"No poverty","id":"https://metadata.un.org/sdg/1","score":0.5}],"awards":[{"id":"https://openalex.org/G2262853887","display_name":null,"funder_award_id":"61836011","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G7167048579","display_name":null,"funder_award_id":"61976043","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":63,"referenced_works":["https://openalex.org/W41554520","https://openalex.org/W64088143","https://openalex.org/W1491843047","https://openalex.org/W2119567691","https://openalex.org/W2158782408","https://openalex.org/W2161966552","https://openalex.org/W2746553466","https://openalex.org/W2754517384","https://openalex.org/W2786010338","https://openalex.org/W2798705390","https://openalex.org/W2904246096","https://openalex.org/W2959895084","https://openalex.org/W2963523627","https://openalex.org/W2965140792","https://openalex.org/W2996449210","https://openalex.org/W3000642679","https://openalex.org/W3015082424","https://openalex.org/W3035064526","https://openalex.org/W3041202696","https://openalex.org/W3134939669","https://openalex.org/W3135865540","https://openalex.org/W3196740181","https://openalex.org/W3205942598","https://openalex.org/W3210825568","https://openalex.org/W4287754111","https://openalex.org/W4297791094","https://openalex.org/W6602057636","https://openalex.org/W6631190155","https://openalex.org/W6677916085","https://openalex.org/W6683195989","https://openalex.org/W6683603353","https://openalex.org/W6684205842","https://openalex.org/W6684921986","https://openalex.org/W6695011786","https://openalex.org/W6704571135","https://openalex.org/W6734097942","https://openalex.org/W6734517396","https://openalex.org/W6736209634","https://openalex.org/W6747473740","https://openalex.org/W6748839928","https://openalex.org/W6750645735","https://openalex.org/W6752725515","https://openalex.org/W6763329203","https://openalex.org/W6764053384","https://openalex.org/W6765407481","https://openalex.org/W6767334564","https://openalex.org/W6767569084","https://openalex.org/W6771656438","https://openalex.org/W6771936881","https://openalex.org/W6774583691","https://openalex.org/W6779129966","https://openalex.org/W6779265984","https://openalex.org/W6779795787","https://openalex.org/W6780523241","https://openalex.org/W6780559895","https://openalex.org/W6780641033","https://openalex.org/W6784938585","https://openalex.org/W6791334070","https://openalex.org/W6791700142","https://openalex.org/W6795425552","https://openalex.org/W6798881143","https://openalex.org/W6803413806","https://openalex.org/W6922480057"],"related_works":["https://openalex.org/W4380987628","https://openalex.org/W2418537576","https://openalex.org/W2557514562","https://openalex.org/W214945085","https://openalex.org/W1987935396","https://openalex.org/W3126025002","https://openalex.org/W2354456418","https://openalex.org/W3197683035","https://openalex.org/W2006807542","https://openalex.org/W2374935031"],"abstract_inverted_index":{"Deep":[0],"off-policy":[1],"actor-critic":[2,40],"algorithms":[3],"have":[4],"been":[5],"successfully":[6],"applied":[7],"to":[8,83,155],"challenging":[9],"tasks":[10,173],"in":[11,29,74,86],"continuous":[12,53,171],"control.":[13,54],"However,":[14],"these":[15,144],"methods":[16],"typically":[17],"suffer":[18],"from":[19,174],"the":[20,68,103,118,168],"poor":[21],"sample":[22,160,178],"efficiency":[23,161,179],"problem,":[24],"limiting":[25],"their":[26],"widespread":[27],"adoption":[28],"real-world":[30],"domains.":[31],"To":[32],"mitigate":[33],"this":[34],"issue,":[35],"we":[36],"propose":[37],"a":[38,61],"novel":[39],"algorithm":[41,96],"with":[42],"weakly":[43,62,120],"pessimistic":[44,63,121],"value":[45,64,76,122,139],"estimation":[46,123],"and":[47,90,127,130,150,158,180],"optimistic":[48,93],"policy":[49,94,104],"optimization":[50,95],"(WPVOP)":[51],"for":[52,111],"WPVOP":[55,166],"integrates":[56],"two":[57,145],"key":[58],"ingredients:":[59],"1)":[60],"estimation,":[65],"which":[66],"compensates":[67],"pessimism":[69],"of":[70,162,170],"lower":[71,126],"confidence":[72],"bound":[73],"conventional":[75],"function":[77],"(i.e.,":[78],"clipped":[79],"double":[80],"Q":[81,109],"-learning)":[82],"trigger":[84],"exploration":[85],"low-value":[87],"state-action":[88],"regions":[89],"2)":[91],"an":[92],"by":[97],"sampling":[98],"actions":[99],"that":[100,117,133,143],"could":[101,135],"benefit":[102],"learning":[105],"most":[106],"toward":[107],"optimal":[108],"-values":[110],"efficient":[112],"exploration.":[113,163],"We":[114,141,164],"theoretically":[115],"analyze":[116],"proposed":[119],"method":[124],"is":[125],"upper":[128],"bounded,":[129],"empirically":[131],"show":[132,142],"it":[134],"avoid":[136],"extremely":[137],"over-optimistic":[138],"estimates.":[140],"ideas":[146],"are":[147],"largely":[148],"complementary,":[149],"can":[151],"be":[152],"fruitfully":[153],"integrated":[154],"improve":[156],"performance":[157],"promote":[159],"evaluate":[165],"on":[167],"suite":[169],"control":[172],"MuJoCo,":[175],"achieving":[176],"state-of-the-art":[177],"performance.":[181]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":8},{"year":2024,"cited_by_count":5},{"year":2023,"cited_by_count":3}],"updated_date":"2026-03-27T05:58:40.876381","created_date":"2025-10-10T00:00:00"}