{"id":"https://openalex.org/W3131019011","doi":"https://doi.org/10.1109/saci51354.2021.9465602","title":"Decaying Clipping Range in Proximal Policy Optimization","display_name":"Decaying Clipping Range in Proximal Policy Optimization","publication_year":2021,"publication_date":"2021-05-19","ids":{"openalex":"https://openalex.org/W3131019011","doi":"https://doi.org/10.1109/saci51354.2021.9465602","mag":"3131019011"},"language":"en","primary_location":{"id":"doi:10.1109/saci51354.2021.9465602","is_oa":false,"landing_page_url":"https://doi.org/10.1109/saci51354.2021.9465602","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2021 IEEE 15th International Symposium on Applied Computational Intelligence and Informatics (SACI)","raw_type":"proceedings-article"},"type":"article","indexed_in":["arxiv","crossref"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2102.10456","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":null,"display_name":"Monika Farsang","orcid":null},"institutions":[{"id":"https://openalex.org/I29770179","display_name":"Budapest University of Technology and Economics","ror":"https://ror.org/02w42ss30","country_code":"HU","type":"education","lineage":["https://openalex.org/I29770179"]}],"countries":["HU"],"is_corresponding":true,"raw_author_name":"Monika Farsang","raw_affiliation_strings":["Budapest University of Technology and Economics, Budapest, Hungary"],"affiliations":[{"raw_affiliation_string":"Budapest University of Technology and Economics, Budapest, Hungary","institution_ids":["https://openalex.org/I29770179"]}]},{"author_position":"last","author":{"id":null,"display_name":"Luca Szegletes","orcid":null},"institutions":[{"id":"https://openalex.org/I29770179","display_name":"Budapest University of Technology and Economics","ror":"https://ror.org/02w42ss30","country_code":"HU","type":"education","lineage":["https://openalex.org/I29770179"]}],"countries":["HU"],"is_corresponding":false,"raw_author_name":"Luca Szegletes","raw_affiliation_strings":["Budapest University of Technology and Economics, Budapest, Hungary"],"affiliations":[{"raw_affiliation_string":"Budapest University of Technology and Economics, Budapest, Hungary","institution_ids":["https://openalex.org/I29770179"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I29770179"],"apc_list":null,"apc_paid":null,"fwci":0.5599,"has_fulltext":false,"cited_by_count":6,"citation_normalized_percentile":{"value":0.7186587,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":96},"biblio":{"volume":null,"issue":null,"first_page":"000521","last_page":"000526"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10462","display_name":"Reinforcement Learning in Robotics","score":0.9998999834060669,"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":0.9998999834060669,"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/T11975","display_name":"Evolutionary Algorithms and Applications","score":0.989300012588501,"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":0.9815000295639038,"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/clipping","display_name":"Clipping (morphology)","score":0.8765000104904175},{"id":"https://openalex.org/keywords/reinforcement-learning","display_name":"Reinforcement learning","score":0.8145999908447266},{"id":"https://openalex.org/keywords/range","display_name":"Range (aeronautics)","score":0.5526000261306763},{"id":"https://openalex.org/keywords/control","display_name":"Control (management)","score":0.4325999915599823},{"id":"https://openalex.org/keywords/constant","display_name":"Constant (computer programming)","score":0.3889999985694885},{"id":"https://openalex.org/keywords/reinforcement","display_name":"Reinforcement","score":0.3824999928474426},{"id":"https://openalex.org/keywords/optimization-problem","display_name":"Optimization problem","score":0.3517000079154968}],"concepts":[{"id":"https://openalex.org/C2776848632","wikidata":"https://www.wikidata.org/wiki/Q853463","display_name":"Clipping (morphology)","level":2,"score":0.8765000104904175},{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.8145999908447266},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5540000200271606},{"id":"https://openalex.org/C204323151","wikidata":"https://www.wikidata.org/wiki/Q905424","display_name":"Range (aeronautics)","level":2,"score":0.5526000261306763},{"id":"https://openalex.org/C2775924081","wikidata":"https://www.wikidata.org/wiki/Q55608371","display_name":"Control (management)","level":2,"score":0.4325999915599823},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.40139999985694885},{"id":"https://openalex.org/C2777027219","wikidata":"https://www.wikidata.org/wiki/Q1284190","display_name":"Constant (computer programming)","level":2,"score":0.3889999985694885},{"id":"https://openalex.org/C126255220","wikidata":"https://www.wikidata.org/wiki/Q141495","display_name":"Mathematical optimization","level":1,"score":0.384799987077713},{"id":"https://openalex.org/C67203356","wikidata":"https://www.wikidata.org/wiki/Q1321905","display_name":"Reinforcement","level":2,"score":0.3824999928474426},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.36059999465942383},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.36000001430511475},{"id":"https://openalex.org/C137836250","wikidata":"https://www.wikidata.org/wiki/Q984063","display_name":"Optimization problem","level":2,"score":0.3517000079154968},{"id":"https://openalex.org/C2780586882","wikidata":"https://www.wikidata.org/wiki/Q7520643","display_name":"Simple (philosophy)","level":2,"score":0.3515999913215637},{"id":"https://openalex.org/C47446073","wikidata":"https://www.wikidata.org/wiki/Q5165890","display_name":"Control theory (sociology)","level":3,"score":0.3352000117301941},{"id":"https://openalex.org/C2778112365","wikidata":"https://www.wikidata.org/wiki/Q3511065","display_name":"Sequence (biology)","level":2,"score":0.2913999855518341},{"id":"https://openalex.org/C2778915421","wikidata":"https://www.wikidata.org/wiki/Q3643177","display_name":"Performance improvement","level":2,"score":0.2913999855518341},{"id":"https://openalex.org/C34585555","wikidata":"https://www.wikidata.org/wiki/Q1368723","display_name":"Learning curve","level":2,"score":0.2858999967575073},{"id":"https://openalex.org/C147764199","wikidata":"https://www.wikidata.org/wiki/Q6865248","display_name":"Minification","level":2,"score":0.27480000257492065},{"id":"https://openalex.org/C188116033","wikidata":"https://www.wikidata.org/wiki/Q2664563","display_name":"Q-learning","level":3,"score":0.25870001316070557}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/saci51354.2021.9465602","is_oa":false,"landing_page_url":"https://doi.org/10.1109/saci51354.2021.9465602","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2021 IEEE 15th International Symposium on Applied Computational Intelligence and Informatics (SACI)","raw_type":"proceedings-article"},{"id":"pmh:oai:arXiv.org:2102.10456","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2102.10456","pdf_url":"https://arxiv.org/pdf/2102.10456","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2102.10456","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2102.10456","pdf_url":"https://arxiv.org/pdf/2102.10456","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":15,"referenced_works":["https://openalex.org/W1967834347","https://openalex.org/W2119717200","https://openalex.org/W2123859855","https://openalex.org/W2127653865","https://openalex.org/W2294316001","https://openalex.org/W4229720873","https://openalex.org/W6638018090","https://openalex.org/W6639949747","https://openalex.org/W6675999342","https://openalex.org/W6678114464","https://openalex.org/W6679257226","https://openalex.org/W6692846177","https://openalex.org/W6704571135","https://openalex.org/W6759527892","https://openalex.org/W7061792134"],"related_works":[],"abstract_inverted_index":{"Proximal":[0],"Policy":[1],"Optimization":[2],"(PPO)":[3],"is":[4,48],"among":[5],"the":[6,28,33,37,57,71,83,89,92,108,115,123],"most":[7],"widely":[8],"used":[9],"algorithms":[10],"in":[11,18,99,127],"reinforcement":[12,129],"learning,":[13],"which":[14],"achieves":[15],"state-of-the-art":[16],"performance":[17,98],"many":[19,128],"challenging":[20],"problems.":[21],"The":[22,43],"keys":[23],"to":[24,49,56,78,122],"its":[25],"success":[26],"are":[27,119],"reliable":[29],"policy":[30],"updates":[31],"through":[32],"clipping":[34,67,125],"mechanism":[35],"and":[36,64,85,103,118],"multiple":[38],"epochs":[39],"of":[40,45,91],"minibatch":[41],"updates.":[42],"aim":[44],"this":[46],"research":[47],"give":[50],"new":[51],"simple":[52],"but":[53],"effective":[54,120],"alternatives":[55,121],"former.":[58],"For":[59],"this,":[60],"we":[61,75,110],"propose":[62],"linearly":[63],"exponentially":[65],"decaying":[66],"range":[68],"approaches":[69],"throughout":[70],"training.":[72],"With":[73],"these,":[74],"would":[76],"like":[77],"provide":[79],"higher":[80],"exploration":[81],"at":[82,88],"beginning":[84],"stronger":[86],"restrictions":[87],"end":[90],"learning":[93,130],"phase.":[94],"We":[95],"investigate":[96],"their":[97],"several":[100],"classical":[101],"control":[102],"locomotive":[104],"robotic":[105],"environments.":[106],"During":[107],"analysis,":[109],"found":[111],"that":[112],"they":[113],"influence":[114],"achieved":[116],"rewards":[117],"constant":[124],"method":[126],"tasks.":[131]},"counts_by_year":[{"year":2025,"cited_by_count":2},{"year":2024,"cited_by_count":1},{"year":2023,"cited_by_count":1},{"year":2022,"cited_by_count":1},{"year":2021,"cited_by_count":1}],"updated_date":"2026-03-20T23:20:44.827607","created_date":"2021-03-01T00:00:00"}