{"id":"https://openalex.org/W4220909004","doi":"https://doi.org/10.3390/e24040440","title":"Relative Entropy of Correct Proximal Policy Optimization Algorithms with Modified Penalty Factor in Complex Environment","display_name":"Relative Entropy of Correct Proximal Policy Optimization Algorithms with Modified Penalty Factor in Complex Environment","publication_year":2022,"publication_date":"2022-03-22","ids":{"openalex":"https://openalex.org/W4220909004","doi":"https://doi.org/10.3390/e24040440","pmid":"https://pubmed.ncbi.nlm.nih.gov/35455103"},"language":"en","primary_location":{"id":"doi:10.3390/e24040440","is_oa":true,"landing_page_url":"https://doi.org/10.3390/e24040440","pdf_url":"https://www.mdpi.com/1099-4300/24/4/440/pdf?version=1647954095","source":{"id":"https://openalex.org/S195231649","display_name":"Entropy","issn_l":"1099-4300","issn":["1099-4300"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310310987","host_organization_name":"Multidisciplinary Digital Publishing Institute","host_organization_lineage":["https://openalex.org/P4310310987"],"host_organization_lineage_names":["Multidisciplinary Digital Publishing Institute"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Entropy","raw_type":"journal-article"},"type":"article","indexed_in":["crossref","doaj","pubmed"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://www.mdpi.com/1099-4300/24/4/440/pdf?version=1647954095","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5100442500","display_name":"Weimin Chen","orcid":"https://orcid.org/0000-0001-8331-933X"},"institutions":[{"id":"https://openalex.org/I39521962","display_name":"Hunan City University","ror":"https://ror.org/01vd7vb53","country_code":"CN","type":"education","lineage":["https://openalex.org/I39521962"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Weimin Chen","raw_affiliation_strings":["School of Information and Electronics, Hunan City University, Yiyang 413000, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Information and Electronics, Hunan City University, Yiyang 413000, China","institution_ids":["https://openalex.org/I39521962"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5072219555","display_name":"Kelvin K. L. Wong","orcid":"https://orcid.org/0000-0002-8600-1105"},"institutions":[{"id":"https://openalex.org/I39521962","display_name":"Hunan City University","ror":"https://ror.org/01vd7vb53","country_code":"CN","type":"education","lineage":["https://openalex.org/I39521962"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Kelvin Kian Loong Wong","raw_affiliation_strings":["School of Information and Electronics, Hunan City University, Yiyang 413000, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Information and Electronics, Hunan City University, Yiyang 413000, China","institution_ids":["https://openalex.org/I39521962"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5026805435","display_name":"Sifan Long","orcid":"https://orcid.org/0000-0003-4450-5345"},"institutions":[{"id":"https://openalex.org/I139660479","display_name":"Central South University","ror":"https://ror.org/00f1zfq44","country_code":"CN","type":"education","lineage":["https://openalex.org/I139660479"]},{"id":"https://openalex.org/I170215575","display_name":"National University of Defense Technology","ror":"https://ror.org/05d2yfz11","country_code":"CN","type":"education","lineage":["https://openalex.org/I170215575"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Sifan Long","raw_affiliation_strings":["School of Computer Science and Engineering, Central South University, Changsha 410075, China","School of Computer Science, National University of Defense Technology, Changsha 410073, China"],"raw_orcid":"https://orcid.org/0000-0003-4450-5345","affiliations":[{"raw_affiliation_string":"School of Computer Science and Engineering, Central South University, Changsha 410075, China","institution_ids":["https://openalex.org/I139660479"]},{"raw_affiliation_string":"School of Computer Science, National University of Defense Technology, Changsha 410073, China","institution_ids":["https://openalex.org/I170215575"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5058697093","display_name":"Zhili Sun","orcid":"https://orcid.org/0000-0002-1909-4946"},"institutions":[{"id":"https://openalex.org/I28290843","display_name":"University of Surrey","ror":"https://ror.org/00ks66431","country_code":"GB","type":"education","lineage":["https://openalex.org/I28290843"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Zhili Sun","raw_affiliation_strings":["5G&6G Innovation Centre, Department of Electrical and Electronic Engineering, Institute for Communication Systems, University of Surrey, Guildford GU2 7XH, UK"],"raw_orcid":"https://orcid.org/0000-0002-1909-4946","affiliations":[{"raw_affiliation_string":"5G&6G Innovation Centre, Department of Electrical and Electronic Engineering, Institute for Communication Systems, University of Surrey, Guildford GU2 7XH, UK","institution_ids":["https://openalex.org/I28290843"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5072219555"],"corresponding_institution_ids":["https://openalex.org/I39521962"],"apc_list":{"value":2000,"currency":"CHF","value_usd":2227},"apc_paid":{"value":2000,"currency":"CHF","value_usd":2227},"fwci":1.2763,"has_fulltext":false,"cited_by_count":13,"citation_normalized_percentile":{"value":0.81939961,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":96,"max":98},"biblio":{"volume":"24","issue":"4","first_page":"440","last_page":"440"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10462","display_name":"Reinforcement Learning in Robotics","score":0.9988999962806702,"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":0.9988999962806702,"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":0.9921000003814697,"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"}},{"id":"https://openalex.org/T12676","display_name":"Machine Learning and ELM","score":0.9883000254631042,"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/mathematical-optimization","display_name":"Mathematical optimization","score":0.6278262138366699},{"id":"https://openalex.org/keywords/kullback\u2013leibler-divergence","display_name":"Kullback\u2013Leibler divergence","score":0.6104223728179932},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.5799020528793335},{"id":"https://openalex.org/keywords/entropy","display_name":"Entropy (arrow of time)","score":0.5628284811973572},{"id":"https://openalex.org/keywords/reinforcement-learning","display_name":"Reinforcement learning","score":0.55995774269104},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.5224796533584595},{"id":"https://openalex.org/keywords/robustness","display_name":"Robustness (evolution)","score":0.4538610279560089},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.3790023624897003},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.2391301393508911}],"concepts":[{"id":"https://openalex.org/C126255220","wikidata":"https://www.wikidata.org/wiki/Q141495","display_name":"Mathematical optimization","level":1,"score":0.6278262138366699},{"id":"https://openalex.org/C171752962","wikidata":"https://www.wikidata.org/wiki/Q255166","display_name":"Kullback\u2013Leibler divergence","level":2,"score":0.6104223728179932},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5799020528793335},{"id":"https://openalex.org/C106301342","wikidata":"https://www.wikidata.org/wiki/Q4117933","display_name":"Entropy (arrow of time)","level":2,"score":0.5628284811973572},{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.55995774269104},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.5224796533584595},{"id":"https://openalex.org/C63479239","wikidata":"https://www.wikidata.org/wiki/Q7353546","display_name":"Robustness (evolution)","level":3,"score":0.4538610279560089},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.3790023624897003},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.2391301393508911},{"id":"https://openalex.org/C55493867","wikidata":"https://www.wikidata.org/wiki/Q7094","display_name":"Biochemistry","level":1,"score":0.0},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0},{"id":"https://openalex.org/C104317684","wikidata":"https://www.wikidata.org/wiki/Q7187","display_name":"Gene","level":2,"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/C62520636","wikidata":"https://www.wikidata.org/wiki/Q944","display_name":"Quantum mechanics","level":1,"score":0.0}],"mesh":[],"locations_count":5,"locations":[{"id":"doi:10.3390/e24040440","is_oa":true,"landing_page_url":"https://doi.org/10.3390/e24040440","pdf_url":"https://www.mdpi.com/1099-4300/24/4/440/pdf?version=1647954095","source":{"id":"https://openalex.org/S195231649","display_name":"Entropy","issn_l":"1099-4300","issn":["1099-4300"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310310987","host_organization_name":"Multidisciplinary Digital Publishing Institute","host_organization_lineage":["https://openalex.org/P4310310987"],"host_organization_lineage_names":["Multidisciplinary Digital Publishing Institute"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Entropy","raw_type":"journal-article"},{"id":"pmid:35455103","is_oa":false,"landing_page_url":"https://pubmed.ncbi.nlm.nih.gov/35455103","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":"Entropy (Basel, Switzerland)","raw_type":null},{"id":"pmh:oai:doaj.org/article:d8082414ba02443fa1405999ddaa4166","is_oa":true,"landing_page_url":"https://doaj.org/article/d8082414ba02443fa1405999ddaa4166","pdf_url":null,"source":{"id":"https://openalex.org/S4306401280","display_name":"DOAJ (DOAJ: Directory of Open Access Journals)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by-sa","license_id":"https://openalex.org/licenses/cc-by-sa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Entropy, Vol 24, Iss 4, p 440 (2022)","raw_type":"article"},{"id":"pmh:oai:mdpi.com:/1099-4300/24/4/440/","is_oa":true,"landing_page_url":"https://dx.doi.org/10.3390/e24040440","pdf_url":null,"source":{"id":"https://openalex.org/S4306400947","display_name":"MDPI (MDPI AG)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I4210097602","host_organization_name":"Multidisciplinary Digital Publishing Institute (Switzerland)","host_organization_lineage":["https://openalex.org/I4210097602"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Entropy; Volume 24; Issue 4; Pages: 440","raw_type":"Text"},{"id":"pmh:oai:pubmedcentral.nih.gov:9031020","is_oa":true,"landing_page_url":"https://www.ncbi.nlm.nih.gov/pmc/articles/9031020","pdf_url":null,"source":{"id":"https://openalex.org/S2764455111","display_name":"PubMed Central","issn_l":null,"issn":null,"is_oa":true,"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":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Entropy (Basel)","raw_type":"Text"}],"best_oa_location":{"id":"doi:10.3390/e24040440","is_oa":true,"landing_page_url":"https://doi.org/10.3390/e24040440","pdf_url":"https://www.mdpi.com/1099-4300/24/4/440/pdf?version=1647954095","source":{"id":"https://openalex.org/S195231649","display_name":"Entropy","issn_l":"1099-4300","issn":["1099-4300"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310310987","host_organization_name":"Multidisciplinary Digital Publishing Institute","host_organization_lineage":["https://openalex.org/P4310310987"],"host_organization_lineage_names":["Multidisciplinary Digital Publishing Institute"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Entropy","raw_type":"journal-article"},"sustainable_development_goals":[{"display_name":"Peace, Justice and strong institutions","id":"https://metadata.un.org/sdg/16","score":0.6100000143051147}],"awards":[],"funders":[],"has_content":{"pdf":true,"grobid_xml":false},"content_urls":{"pdf":"https://content.openalex.org/works/W4220909004.pdf"},"referenced_works_count":27,"referenced_works":["https://openalex.org/W1771410628","https://openalex.org/W1989549063","https://openalex.org/W2145339207","https://openalex.org/W2319521425","https://openalex.org/W2342662072","https://openalex.org/W2512973121","https://openalex.org/W2565516711","https://openalex.org/W2585039351","https://openalex.org/W2593309265","https://openalex.org/W2737597558","https://openalex.org/W2740384884","https://openalex.org/W2744171414","https://openalex.org/W2766447205","https://openalex.org/W2775482448","https://openalex.org/W2789008277","https://openalex.org/W2949519357","https://openalex.org/W3005399447","https://openalex.org/W3085043910","https://openalex.org/W3164145521","https://openalex.org/W3174010949","https://openalex.org/W3207743369","https://openalex.org/W4200368956","https://openalex.org/W4212890525","https://openalex.org/W4327566517","https://openalex.org/W6638018090","https://openalex.org/W6795084654","https://openalex.org/W6851243003"],"related_works":["https://openalex.org/W4362501864","https://openalex.org/W4306904969","https://openalex.org/W4380318855","https://openalex.org/W2138720691","https://openalex.org/W2031695474","https://openalex.org/W2586732548","https://openalex.org/W2163103544","https://openalex.org/W2551182807","https://openalex.org/W3033899355","https://openalex.org/W4383822431"],"abstract_inverted_index":{"and":[0,9,55,60,99,107,161,164],"relative":[1,63,112,175],"entropy":[2,64,113,176],"in":[3],"order":[4],"to":[5,49,67,130],"solve":[6],"the":[7,16,29,34,44,51,56,69,78,82,103,108,111,116,125,134,143,146,150,174],"robustness":[8],"stationarity":[10],"of":[11,18,62,110,127,145,171],"traditional":[12,104],"algorithms.":[13],"Firstly,":[14],"In":[15,118],"process":[17],"reinforcement":[19],"learning,":[20],"this":[21],"paper":[22,141],"establishes":[23],"a":[24,95],"strategy":[25],"evaluation":[26],"mechanism":[27],"through":[28,77],"policy":[30,46,53,147],"distribution":[31,148],"function.":[32],"Secondly,":[33],"state":[35],"space":[36],"function":[37,58,71],"is":[38,47,65,92],"quantified":[39],"by":[40],"introducing":[41],"entropy,":[42],"whereby":[43],"approximation":[45],"used":[48,66],"approximate":[50],"real":[52],"distribution,":[54],"kernel":[57],"estimation":[59],"calculation":[61],"fit":[68],"reward":[70],"based":[72],"on":[73,81],"complex":[74,128],"problem.":[75],"Finally,":[76],"comparative":[79],"analysis":[80],"classic":[83],"test":[84],"cases,":[85],"we":[86,165],"demonstrated":[87],"that":[88],"our":[89,140],"proposed":[90,151],"algorithm":[91],"effective,":[93],"has":[94],"faster":[96],"convergence":[97,162],"speed":[98],"better":[100],"performance":[101,172],"than":[102],"PPO":[105],"algorithm,":[106],"measure":[109,170],"can":[114,121,139,153],"show":[115],"differences.":[117],"addition,":[119],"it":[120],"more":[122],"efficiently":[123],"use":[124],"information":[126],"environment":[129],"learn":[131],"policies.":[132],"At":[133],"same":[135],"time,":[136],"not":[137],"only":[138],"explain":[142],"rationality":[144],"theory,":[149],"framework":[152],"also":[154,166],"balance":[155],"between":[156],"iteration":[157],"steps,":[158],"computational":[159],"complexity":[160],"speed,":[163],"introduced":[167],"an":[168],"effective":[169],"using":[173],"concept.":[177]},"counts_by_year":[{"year":2026,"cited_by_count":2},{"year":2025,"cited_by_count":3},{"year":2024,"cited_by_count":5},{"year":2023,"cited_by_count":3}],"updated_date":"2026-07-22T07:51:19.307946","created_date":"2025-10-10T00:00:00"}