{"id":"https://openalex.org/W3182648169","doi":"https://doi.org/10.1109/access.2021.3094566","title":"A Functional Clipping Approach for Policy Optimization Algorithms","display_name":"A Functional Clipping Approach for Policy Optimization Algorithms","publication_year":2021,"publication_date":"2021-01-01","ids":{"openalex":"https://openalex.org/W3182648169","doi":"https://doi.org/10.1109/access.2021.3094566","mag":"3182648169"},"language":"en","primary_location":{"id":"doi:10.1109/access.2021.3094566","is_oa":true,"landing_page_url":"https://doi.org/10.1109/access.2021.3094566","pdf_url":"https://ieeexplore.ieee.org/ielx7/6287639/9312710/09474478.pdf","source":{"id":"https://openalex.org/S2485537415","display_name":"IEEE Access","issn_l":"2169-3536","issn":["2169-3536"],"is_oa":true,"is_in_doaj":true,"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":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Access","raw_type":"journal-article"},"type":"article","indexed_in":["crossref","doaj"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://ieeexplore.ieee.org/ielx7/6287639/9312710/09474478.pdf","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5015266587","display_name":"Wangshu Zhu","orcid":"https://orcid.org/0000-0003-1950-202X"},"institutions":[{"id":"https://openalex.org/I30809798","display_name":"ShanghaiTech University","ror":"https://ror.org/030bhh786","country_code":"CN","type":"education","lineage":["https://openalex.org/I30809798"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Wangshu Zhu","raw_affiliation_strings":["Department of Computer Science, School of Information Science and Technology, Living Machines Laboratories, ShanghaiTech University, Shanghai, China"],"raw_orcid":"https://orcid.org/0000-0003-1950-202X","affiliations":[{"raw_affiliation_string":"Department of Computer Science, School of Information Science and Technology, Living Machines Laboratories, ShanghaiTech University, Shanghai, China","institution_ids":["https://openalex.org/I30809798"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5007414540","display_name":"Andr\u00e9 Rosendo","orcid":"https://orcid.org/0000-0003-4062-5390"},"institutions":[{"id":"https://openalex.org/I30809798","display_name":"ShanghaiTech University","ror":"https://ror.org/030bhh786","country_code":"CN","type":"education","lineage":["https://openalex.org/I30809798"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Andre Rosendo","raw_affiliation_strings":["Department of Computer Science, School of Information Science and Technology, Living Machines Laboratories, ShanghaiTech University, Shanghai, China"],"raw_orcid":"https://orcid.org/0000-0003-4062-5390","affiliations":[{"raw_affiliation_string":"Department of Computer Science, School of Information Science and Technology, Living Machines Laboratories, ShanghaiTech University, Shanghai, China","institution_ids":["https://openalex.org/I30809798"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5015266587"],"corresponding_institution_ids":["https://openalex.org/I30809798"],"apc_list":{"value":1850,"currency":"USD","value_usd":1850},"apc_paid":{"value":1850,"currency":"USD","value_usd":1850},"fwci":1.5392,"has_fulltext":true,"cited_by_count":16,"citation_normalized_percentile":{"value":0.86019348,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":94,"max":98},"biblio":{"volume":"9","issue":null,"first_page":"96056","last_page":"96063"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10462","display_name":"Reinforcement Learning in Robotics","score":0.9994999766349792,"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":0.9994999766349792,"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/T10848","display_name":"Advanced Multi-Objective Optimization Algorithms","score":0.996399998664856,"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/T11975","display_name":"Evolutionary Algorithms and Applications","score":0.9865999817848206,"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/clipping","display_name":"Clipping (morphology)","score":0.850245475769043},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.700594425201416},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.5505474209785461},{"id":"https://openalex.org/keywords/hyperparameter","display_name":"Hyperparameter","score":0.5278927087783813},{"id":"https://openalex.org/keywords/rollback","display_name":"Rollback","score":0.5091013312339783},{"id":"https://openalex.org/keywords/stability","display_name":"Stability (learning theory)","score":0.47925639152526855},{"id":"https://openalex.org/keywords/benchmarking","display_name":"Benchmarking","score":0.47448042035102844},{"id":"https://openalex.org/keywords/inefficiency","display_name":"Inefficiency","score":0.46121156215667725},{"id":"https://openalex.org/keywords/reinforcement-learning","display_name":"Reinforcement learning","score":0.4545532763004303},{"id":"https://openalex.org/keywords/mathematical-optimization","display_name":"Mathematical optimization","score":0.4441235065460205},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.2861449122428894},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.27183955907821655},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.1912444531917572},{"id":"https://openalex.org/keywords/database-transaction","display_name":"Database transaction","score":0.0763024389743805}],"concepts":[{"id":"https://openalex.org/C2776848632","wikidata":"https://www.wikidata.org/wiki/Q853463","display_name":"Clipping (morphology)","level":2,"score":0.850245475769043},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.700594425201416},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.5505474209785461},{"id":"https://openalex.org/C8642999","wikidata":"https://www.wikidata.org/wiki/Q4171168","display_name":"Hyperparameter","level":2,"score":0.5278927087783813},{"id":"https://openalex.org/C174220543","wikidata":"https://www.wikidata.org/wiki/Q395307","display_name":"Rollback","level":3,"score":0.5091013312339783},{"id":"https://openalex.org/C112972136","wikidata":"https://www.wikidata.org/wiki/Q7595718","display_name":"Stability (learning theory)","level":2,"score":0.47925639152526855},{"id":"https://openalex.org/C86251818","wikidata":"https://www.wikidata.org/wiki/Q816754","display_name":"Benchmarking","level":2,"score":0.47448042035102844},{"id":"https://openalex.org/C2778869765","wikidata":"https://www.wikidata.org/wiki/Q6028363","display_name":"Inefficiency","level":2,"score":0.46121156215667725},{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.4545532763004303},{"id":"https://openalex.org/C126255220","wikidata":"https://www.wikidata.org/wiki/Q141495","display_name":"Mathematical optimization","level":1,"score":0.4441235065460205},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.2861449122428894},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.27183955907821655},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.1912444531917572},{"id":"https://openalex.org/C75949130","wikidata":"https://www.wikidata.org/wiki/Q848010","display_name":"Database transaction","level":2,"score":0.0763024389743805},{"id":"https://openalex.org/C162853370","wikidata":"https://www.wikidata.org/wiki/Q39809","display_name":"Marketing","level":1,"score":0.0},{"id":"https://openalex.org/C175444787","wikidata":"https://www.wikidata.org/wiki/Q39072","display_name":"Microeconomics","level":1,"score":0.0},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","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/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","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/C144133560","wikidata":"https://www.wikidata.org/wiki/Q4830453","display_name":"Business","level":0,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/access.2021.3094566","is_oa":true,"landing_page_url":"https://doi.org/10.1109/access.2021.3094566","pdf_url":"https://ieeexplore.ieee.org/ielx7/6287639/9312710/09474478.pdf","source":{"id":"https://openalex.org/S2485537415","display_name":"IEEE Access","issn_l":"2169-3536","issn":["2169-3536"],"is_oa":true,"is_in_doaj":true,"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":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Access","raw_type":"journal-article"},{"id":"pmh:oai:doaj.org/article:38f20ef12085440b9d67d25543fc3b14","is_oa":true,"landing_page_url":"https://doaj.org/article/38f20ef12085440b9d67d25543fc3b14","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":"IEEE Access, Vol 9, Pp 96056-96063 (2021)","raw_type":"article"}],"best_oa_location":{"id":"doi:10.1109/access.2021.3094566","is_oa":true,"landing_page_url":"https://doi.org/10.1109/access.2021.3094566","pdf_url":"https://ieeexplore.ieee.org/ielx7/6287639/9312710/09474478.pdf","source":{"id":"https://openalex.org/S2485537415","display_name":"IEEE Access","issn_l":"2169-3536","issn":["2169-3536"],"is_oa":true,"is_in_doaj":true,"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":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Access","raw_type":"journal-article"},"sustainable_development_goals":[{"score":0.7099999785423279,"display_name":"Peace, Justice and strong institutions","id":"https://metadata.un.org/sdg/16"}],"awards":[{"id":"https://openalex.org/G5321983622","display_name":null,"funder_award_id":"61850410527","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":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W3182648169.pdf","grobid_xml":"https://content.openalex.org/works/W3182648169.grobid-xml"},"referenced_works_count":52,"referenced_works":["https://openalex.org/W1191599655","https://openalex.org/W1499669280","https://openalex.org/W1522301498","https://openalex.org/W1757796397","https://openalex.org/W1771410628","https://openalex.org/W2119717200","https://openalex.org/W2125612430","https://openalex.org/W2145339207","https://openalex.org/W2155007355","https://openalex.org/W2155027007","https://openalex.org/W2155968351","https://openalex.org/W2156387975","https://openalex.org/W2158782408","https://openalex.org/W2185709919","https://openalex.org/W2257979135","https://openalex.org/W2342662072","https://openalex.org/W2569805627","https://openalex.org/W2736601468","https://openalex.org/W2746553466","https://openalex.org/W2754517384","https://openalex.org/W2811292668","https://openalex.org/W2914808443","https://openalex.org/W2921474818","https://openalex.org/W2952063594","https://openalex.org/W2952523895","https://openalex.org/W2963641140","https://openalex.org/W2963871073","https://openalex.org/W2964161785","https://openalex.org/W2968717280","https://openalex.org/W2970851609","https://openalex.org/W3037207827","https://openalex.org/W3135387626","https://openalex.org/W4289303873","https://openalex.org/W4298857966","https://openalex.org/W6627932998","https://openalex.org/W6631190155","https://openalex.org/W6637967152","https://openalex.org/W6638018090","https://openalex.org/W6682849425","https://openalex.org/W6682889407","https://openalex.org/W6683204974","https://openalex.org/W6686239993","https://openalex.org/W6704571135","https://openalex.org/W6720923776","https://openalex.org/W6731402942","https://openalex.org/W6741002519","https://openalex.org/W6744123322","https://openalex.org/W6752736450","https://openalex.org/W6759527892","https://openalex.org/W6760181788","https://openalex.org/W6771730547","https://openalex.org/W6780559895"],"related_works":["https://openalex.org/W4238897586","https://openalex.org/W435179959","https://openalex.org/W2619091065","https://openalex.org/W2341842940","https://openalex.org/W1490753184","https://openalex.org/W2284465472","https://openalex.org/W2291782699","https://openalex.org/W1993948687","https://openalex.org/W2059640416","https://openalex.org/W2329895846"],"abstract_inverted_index":{"Proximal":[0,75],"policy":[1,9,37,71],"optimization":[2,52,72],"(PPO)":[3],"has":[4],"yielded":[5],"state-of-the-art":[6],"results":[7],"in":[8,141,157],"search,":[10],"a":[11,26,67,89,95,109],"subfield":[12],"of":[13,18,25,58,88,94],"reinforcement":[14],"learning,":[15],"with":[16,103],"one":[17],"its":[19,82],"key":[20],"points":[21],"being":[22],"the":[23,32,44,55,59,86,132,154],"use":[24,87],"surrogate":[27],"objective":[28],"function":[29],"to":[30],"restrict":[31],"step":[33],"size":[34],"at":[35],"each":[36],"update.":[38],"Although":[39],"such":[40],"restriction":[41],"is":[42,85],"helpful,":[43],"algorithm":[45],"still":[46],"suffers":[47],"from":[48,54],"performance":[49,138],"instability":[50],"and":[51,81,105,113,139],"inefficiency":[53],"sudden":[56],"flattening":[57],"curve.":[60],"To":[61],"address":[62],"this":[63],"issue":[64],"we":[65,147],"present":[66],"novel":[68],"functional":[69,90],"clipping":[70,91,97,111],"algorithm,":[73],"named":[74],"Policy":[76],"Optimization":[77],"Smoothed":[78],"Algorithm":[79],"(PPOS),":[80],"critical":[83],"improvement":[84],"method":[92],"instead":[93],"flat":[96],"method.":[98],"We":[99,127],"compare":[100],"our":[101,116,158],"approach":[102,117],"PPO":[104,125,134],"PPORB,":[106],"which":[107],"adopts":[108],"rollback":[110],"method,":[112],"prove":[114],"that":[115,129],"can":[118],"conduct":[119],"more":[120],"accurate":[121],"updates":[122],"than":[123],"other":[124],"methods.":[126],"show":[128],"it":[130],"outperforms":[131],"latest":[133],"variants":[135],"on":[136],"both":[137],"stability":[140],"challenging":[142],"continuous":[143],"control":[144],"tasks.":[145],"Moreover,":[146],"provide":[148],"an":[149],"instructive":[150],"guideline":[151],"for":[152],"tuning":[153],"main":[155],"hyperparameter":[156],"algorithm.":[159]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":4},{"year":2024,"cited_by_count":5},{"year":2023,"cited_by_count":4},{"year":2022,"cited_by_count":2}],"updated_date":"2026-05-06T08:25:59.206177","created_date":"2025-10-10T00:00:00"}