{"id":"https://openalex.org/W3188220908","doi":"https://doi.org/10.1109/tsmc.2021.3098451","title":"Proximal Policy Optimization With Policy Feedback","display_name":"Proximal Policy Optimization With Policy Feedback","publication_year":2021,"publication_date":"2021-07-29","ids":{"openalex":"https://openalex.org/W3188220908","doi":"https://doi.org/10.1109/tsmc.2021.3098451","mag":"3188220908"},"language":"en","primary_location":{"id":"doi:10.1109/tsmc.2021.3098451","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tsmc.2021.3098451","pdf_url":null,"source":{"id":"https://openalex.org/S4210209078","display_name":"IEEE Transactions on Systems Man and Cybernetics Systems","issn_l":"2168-2216","issn":["2168-2216","2168-2232"],"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 Systems, Man, and Cybernetics: Systems","raw_type":"journal-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/A5101732156","display_name":"Yang Gu","orcid":"https://orcid.org/0000-0002-6698-479X"},"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":"Yang Gu","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":null,"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/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/A5100643265","display_name":"C. L. Philip Chen","orcid":"https://orcid.org/0000-0001-5451-7230"},"institutions":[{"id":"https://openalex.org/I204512498","display_name":"University of Macau","ror":"https://ror.org/01r4q9n85","country_code":"MO","type":"education","lineage":["https://openalex.org/I204512498"]},{"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","MO"],"is_corresponding":false,"raw_author_name":"C. L. Philip Chen","raw_affiliation_strings":["College of Computer Science and Engineering, South China University of Technology, Guangzhou, China","Department of Computer and Information Science, Faculty of Science and Technology, University of Macau, Macau, China"],"raw_orcid":"https://orcid.org/0000-0001-5451-7230","affiliations":[{"raw_affiliation_string":"College of Computer Science and Engineering, South China University of Technology, Guangzhou, China","institution_ids":["https://openalex.org/I90610280"]},{"raw_affiliation_string":"Department of Computer and Information Science, Faculty of Science and Technology, University of Macau, Macau, China","institution_ids":["https://openalex.org/I204512498"]}]},{"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":2,"institutions_distinct_count":3,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":8.4411,"has_fulltext":false,"cited_by_count":213,"citation_normalized_percentile":{"value":0.97985471,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":94,"max":100},"biblio":{"volume":"52","issue":"7","first_page":"4600","last_page":"4610"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10462","display_name":"Reinforcement Learning in Robotics","score":0.9998000264167786,"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":0.9998000264167786,"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":0.9860000014305115,"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/reinforcement-learning","display_name":"Reinforcement learning","score":0.7944657802581787},{"id":"https://openalex.org/keywords/value","display_name":"Value (mathematics)","score":0.7181859612464905},{"id":"https://openalex.org/keywords/bellman-equation","display_name":"Bellman equation","score":0.7127000689506531},{"id":"https://openalex.org/keywords/function","display_name":"Function (biology)","score":0.6766232252120972},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6210804581642151},{"id":"https://openalex.org/keywords/architecture","display_name":"Architecture","score":0.5744257569313049},{"id":"https://openalex.org/keywords/variance","display_name":"Variance (accounting)","score":0.5531060099601746},{"id":"https://openalex.org/keywords/process","display_name":"Process (computing)","score":0.4964612126350403},{"id":"https://openalex.org/keywords/value-network","display_name":"Value network","score":0.48374128341674805},{"id":"https://openalex.org/keywords/convergence","display_name":"Convergence (economics)","score":0.4405602216720581},{"id":"https://openalex.org/keywords/mathematical-optimization","display_name":"Mathematical optimization","score":0.43232786655426025},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.32920700311660767},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.24672314524650574},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.19382479786872864},{"id":"https://openalex.org/keywords/economics","display_name":"Economics","score":0.1762252151966095}],"concepts":[{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.7944657802581787},{"id":"https://openalex.org/C2776291640","wikidata":"https://www.wikidata.org/wiki/Q2912517","display_name":"Value (mathematics)","level":2,"score":0.7181859612464905},{"id":"https://openalex.org/C14646407","wikidata":"https://www.wikidata.org/wiki/Q1430750","display_name":"Bellman equation","level":2,"score":0.7127000689506531},{"id":"https://openalex.org/C14036430","wikidata":"https://www.wikidata.org/wiki/Q3736076","display_name":"Function (biology)","level":2,"score":0.6766232252120972},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6210804581642151},{"id":"https://openalex.org/C123657996","wikidata":"https://www.wikidata.org/wiki/Q12271","display_name":"Architecture","level":2,"score":0.5744257569313049},{"id":"https://openalex.org/C196083921","wikidata":"https://www.wikidata.org/wiki/Q7915758","display_name":"Variance (accounting)","level":2,"score":0.5531060099601746},{"id":"https://openalex.org/C98045186","wikidata":"https://www.wikidata.org/wiki/Q205663","display_name":"Process (computing)","level":2,"score":0.4964612126350403},{"id":"https://openalex.org/C89249532","wikidata":"https://www.wikidata.org/wiki/Q7912758","display_name":"Value network","level":3,"score":0.48374128341674805},{"id":"https://openalex.org/C2777303404","wikidata":"https://www.wikidata.org/wiki/Q759757","display_name":"Convergence (economics)","level":2,"score":0.4405602216720581},{"id":"https://openalex.org/C126255220","wikidata":"https://www.wikidata.org/wiki/Q141495","display_name":"Mathematical optimization","level":1,"score":0.43232786655426025},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.32920700311660767},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.24672314524650574},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.19382479786872864},{"id":"https://openalex.org/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","level":0,"score":0.1762252151966095},{"id":"https://openalex.org/C187736073","wikidata":"https://www.wikidata.org/wiki/Q2920921","display_name":"Management","level":1,"score":0.0},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.0},{"id":"https://openalex.org/C4216890","wikidata":"https://www.wikidata.org/wiki/Q815823","display_name":"Business model","level":2,"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/C153349607","wikidata":"https://www.wikidata.org/wiki/Q36649","display_name":"Visual arts","level":1,"score":0.0},{"id":"https://openalex.org/C142362112","wikidata":"https://www.wikidata.org/wiki/Q735","display_name":"Art","level":0,"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/C78458016","wikidata":"https://www.wikidata.org/wiki/Q840400","display_name":"Evolutionary biology","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}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/tsmc.2021.3098451","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tsmc.2021.3098451","pdf_url":null,"source":{"id":"https://openalex.org/S4210209078","display_name":"IEEE Transactions on Systems Man and Cybernetics Systems","issn_l":"2168-2216","issn":["2168-2216","2168-2232"],"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 Systems, Man, and Cybernetics: Systems","raw_type":"journal-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G5750115239","display_name":null,"funder_award_id":"U1813203","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"},{"id":"https://openalex.org/G7031480287","display_name":"\u57fa\u4e8e\u5c5e\u6027\u5b66\u4e60\u7684\u96f6\u6837\u672c\u56fe\u50cf\u5206\u7c7b\u7814\u7a76","funder_award_id":"61772532","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":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":44,"referenced_works":["https://openalex.org/W41554520","https://openalex.org/W1536323281","https://openalex.org/W1680797894","https://openalex.org/W1890963104","https://openalex.org/W1983264093","https://openalex.org/W2098584016","https://openalex.org/W2100752967","https://openalex.org/W2121110499","https://openalex.org/W2127107099","https://openalex.org/W2145339207","https://openalex.org/W2157174816","https://openalex.org/W2194966727","https://openalex.org/W2201581102","https://openalex.org/W2609650878","https://openalex.org/W2724169821","https://openalex.org/W2727279496","https://openalex.org/W2736601468","https://openalex.org/W2746553466","https://openalex.org/W2781726626","https://openalex.org/W2899806036","https://openalex.org/W2905334533","https://openalex.org/W2936135090","https://openalex.org/W2950395671","https://openalex.org/W2951799221","https://openalex.org/W2955358943","https://openalex.org/W2963849886","https://openalex.org/W2964337555","https://openalex.org/W2966349401","https://openalex.org/W2968831808","https://openalex.org/W2971587637","https://openalex.org/W2973229164","https://openalex.org/W2995036248","https://openalex.org/W2999176108","https://openalex.org/W3048983622","https://openalex.org/W4298857966","https://openalex.org/W4394661925","https://openalex.org/W6634413486","https://openalex.org/W6638018090","https://openalex.org/W6676023451","https://openalex.org/W6684205842","https://openalex.org/W6734206676","https://openalex.org/W6734517396","https://openalex.org/W6748011039","https://openalex.org/W6751535212"],"related_works":["https://openalex.org/W4306904969","https://openalex.org/W2138720691","https://openalex.org/W4362501864","https://openalex.org/W2386410636","https://openalex.org/W3038962357","https://openalex.org/W2025663273","https://openalex.org/W3099153698","https://openalex.org/W3184322736","https://openalex.org/W3188986767","https://openalex.org/W3201942433"],"abstract_inverted_index":{"Proximal":[0],"policy":[1,39,58,97,103,118,157,175,193,202],"optimization":[2],"(PPO)":[3],"is":[4,25,53],"a":[5,92,174],"deep":[6],"reinforcement":[7],"learning":[8,170],"algorithm":[9],"based":[10,178],"on":[11,179,215],"the":[12,17,21,29,33,38,42,49,57,64,74,82,85,102,105,109,115,122,125,147,150,154,161,168,180,188,192,201,207,211],"actor\u2013critic":[13],"(AC)":[14],"architecture.":[15],"In":[16,143],"classic":[18,50,69],"AC":[19,51,70,94],"architecture,":[20,124],"Critic":[22],"(value)":[23],"network":[24,36,194,197],"used":[26],"to":[27,41,145,153,159,198,224],"estimate":[28],"value":[30,44,65,75,110,129,151,165,196],"function":[31,66,76,111,130,152],"while":[32],"Actor":[34],"(policy)":[35],"optimizes":[37],"according":[40],"estimated":[43],"function.":[45],"The":[46,68],"efficiency":[47],"of":[48,84,108,149,156,163,191,204,210,236],"architecture":[52,71,95],"limited":[54],"due":[55],"that":[56,200,222],"does":[59],"not":[60],"directly":[61],"participate":[62],"in":[63],"update.":[67],"will":[72,80],"make":[73],"estimation":[77,166,209],"inaccurate,":[78],"which":[79],"affect":[81],"performance":[83],"PPO":[86,116],"algorithm.":[87],"For":[88,121],"improvement,":[89],"we":[90,172,185],"designed":[91,136],"novel":[93],"with":[96,117],"feedback":[98,119],"(AC-PF)":[99],"by":[100,137],"introducing":[101],"into":[104],"update":[106,176,203],"process":[107],"and":[112,131,158,195,218,233],"further":[113],"proposed":[114,173],"(PPO-PF).":[120],"AC-PF":[123],"policy-based":[126],"expected":[127,141],"(PBE)":[128],"discount":[132,182],"reward":[133],"formulas":[134],"are":[135],"drawing":[138],"inspiration":[139],"from":[140],"Sarsa.":[142],"order":[144],"enhance":[146],"sensitivity":[148],"change":[155],"improve":[160],"accuracy":[162],"PBE":[164],"at":[167],"early":[169],"stage,":[171],"method":[177],"clipped":[181],"factor.":[183],"Moreover,":[184],"specifically":[186],"defined":[187],"loss":[189],"functions":[190],"ensure":[199],"PPO-PF":[205,226],"satisfies":[206],"unbiased":[208],"trust":[212],"region.":[213],"Experiments":[214],"Atari":[216],"games":[217],"control":[219],"tasks":[220],"show":[221],"compared":[223],"PPO,":[225],"has":[227],"faster":[228],"convergence":[229],"speed,":[230],"higher":[231],"reward,":[232],"smaller":[234],"variance":[235],"reward.":[237]},"counts_by_year":[{"year":2026,"cited_by_count":44},{"year":2025,"cited_by_count":106},{"year":2024,"cited_by_count":50},{"year":2023,"cited_by_count":11},{"year":2022,"cited_by_count":2}],"updated_date":"2026-08-10T07:06:39.071514","created_date":"2025-10-10T00:00:00"}