{"id":"https://openalex.org/W3206369550","doi":"https://doi.org/10.1109/icra48506.2021.9560856","title":"Proximal Policy Optimization with Relative Pearson Divergence","display_name":"Proximal Policy Optimization with Relative Pearson Divergence","publication_year":2021,"publication_date":"2021-05-30","ids":{"openalex":"https://openalex.org/W3206369550","doi":"https://doi.org/10.1109/icra48506.2021.9560856","mag":"3206369550"},"language":"en","primary_location":{"id":"doi:10.1109/icra48506.2021.9560856","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icra48506.2021.9560856","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2021 IEEE International Conference on Robotics and Automation (ICRA)","raw_type":"proceedings-article"},"type":"preprint","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/A5051304187","display_name":"Taisuke Kobayashi","orcid":"https://orcid.org/0000-0002-3760-249X"},"institutions":[{"id":"https://openalex.org/I75917431","display_name":"Nara Institute of Science and Technology","ror":"https://ror.org/05bhada84","country_code":"JP","type":"education","lineage":["https://openalex.org/I75917431"]}],"countries":["JP"],"is_corresponding":true,"raw_author_name":"Taisuke Kobayashi","raw_affiliation_strings":["Division of Information Science, Nara Institute of Science and Technology, Nara, Japan"],"affiliations":[{"raw_affiliation_string":"Division of Information Science, Nara Institute of Science and Technology, Nara, Japan","institution_ids":["https://openalex.org/I75917431"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":["https://openalex.org/A5051304187"],"corresponding_institution_ids":["https://openalex.org/I75917431"],"apc_list":null,"apc_paid":null,"fwci":1.41103575,"has_fulltext":false,"cited_by_count":10,"citation_normalized_percentile":{"value":0.84783017,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":98},"biblio":{"volume":null,"issue":null,"first_page":null,"last_page":null},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10462","display_name":"Reinforcement Learning in Robotics","score":0.9995999932289124,"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":0.9995999932289124,"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":0.9941999912261963,"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/T10603","display_name":"Smart Grid Energy Management","score":0.9932000041007996,"subfield":{"id":"https://openalex.org/subfields/2208","display_name":"Electrical and Electronic Engineering"},"field":{"id":"https://openalex.org/fields/22","display_name":"Engineering"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/regularization","display_name":"Regularization (linguistics)","score":0.8278011083602905},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.5893018841743469},{"id":"https://openalex.org/keywords/benchmark","display_name":"Benchmark (surveying)","score":0.5732972621917725},{"id":"https://openalex.org/keywords/reinforcement-learning","display_name":"Reinforcement learning","score":0.560572624206543},{"id":"https://openalex.org/keywords/divergence","display_name":"Divergence (linguistics)","score":0.5362951159477234},{"id":"https://openalex.org/keywords/minification","display_name":"Minification","score":0.48808181285858154},{"id":"https://openalex.org/keywords/mathematical-optimization","display_name":"Mathematical optimization","score":0.42356210947036743},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.42104053497314453},{"id":"https://openalex.org/keywords/asymmetry","display_name":"Asymmetry","score":0.4133497476577759},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.3483329117298126},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.32672548294067383},{"id":"https://openalex.org/keywords/physics","display_name":"Physics","score":0.10562142729759216}],"concepts":[{"id":"https://openalex.org/C2776135515","wikidata":"https://www.wikidata.org/wiki/Q17143721","display_name":"Regularization (linguistics)","level":2,"score":0.8278011083602905},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5893018841743469},{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.5732972621917725},{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.560572624206543},{"id":"https://openalex.org/C207390915","wikidata":"https://www.wikidata.org/wiki/Q1230525","display_name":"Divergence (linguistics)","level":2,"score":0.5362951159477234},{"id":"https://openalex.org/C147764199","wikidata":"https://www.wikidata.org/wiki/Q6865248","display_name":"Minification","level":2,"score":0.48808181285858154},{"id":"https://openalex.org/C126255220","wikidata":"https://www.wikidata.org/wiki/Q141495","display_name":"Mathematical optimization","level":1,"score":0.42356210947036743},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.42104053497314453},{"id":"https://openalex.org/C38976095","wikidata":"https://www.wikidata.org/wiki/Q752641","display_name":"Asymmetry","level":2,"score":0.4133497476577759},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.3483329117298126},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.32672548294067383},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.10562142729759216},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"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/C13280743","wikidata":"https://www.wikidata.org/wiki/Q131089","display_name":"Geodesy","level":1,"score":0.0},{"id":"https://openalex.org/C62520636","wikidata":"https://www.wikidata.org/wiki/Q944","display_name":"Quantum mechanics","level":1,"score":0.0},{"id":"https://openalex.org/C205649164","wikidata":"https://www.wikidata.org/wiki/Q1071","display_name":"Geography","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icra48506.2021.9560856","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icra48506.2021.9560856","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2021 IEEE International Conference on Robotics and Automation (ICRA)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Peace, Justice and strong institutions","id":"https://metadata.un.org/sdg/16","score":0.4300000071525574}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":39,"referenced_works":["https://openalex.org/W41554520","https://openalex.org/W1771410628","https://openalex.org/W1990970321","https://openalex.org/W2022365837","https://openalex.org/W2101895600","https://openalex.org/W2121863487","https://openalex.org/W2131940723","https://openalex.org/W2141559645","https://openalex.org/W2145339207","https://openalex.org/W2257979135","https://openalex.org/W2613860617","https://openalex.org/W2736601468","https://openalex.org/W2781726626","https://openalex.org/W2899771611","https://openalex.org/W2900582619","https://openalex.org/W2903866873","https://openalex.org/W2914920107","https://openalex.org/W2919115771","https://openalex.org/W2921474818","https://openalex.org/W2952021385","https://openalex.org/W2962834855","https://openalex.org/W2965438240","https://openalex.org/W3005747346","https://openalex.org/W3080884797","https://openalex.org/W3081393816","https://openalex.org/W3104595455","https://openalex.org/W3111951952","https://openalex.org/W3140822320","https://openalex.org/W6638018090","https://openalex.org/W6741002519","https://openalex.org/W6747473740","https://openalex.org/W6756040250","https://openalex.org/W6759637383","https://openalex.org/W6760181788","https://openalex.org/W6773751056","https://openalex.org/W6780226713","https://openalex.org/W6780559895","https://openalex.org/W6782215836","https://openalex.org/W6792165185"],"related_works":["https://openalex.org/W1644661642","https://openalex.org/W1980563100","https://openalex.org/W3102935140","https://openalex.org/W4297670902","https://openalex.org/W2065779551","https://openalex.org/W2050217822","https://openalex.org/W2001403916","https://openalex.org/W2035154026","https://openalex.org/W2601376976","https://openalex.org/W2064827254"],"abstract_inverted_index":{"The":[0],"recent":[1],"remarkable":[2],"progress":[3],"of":[4,12,37,55,76,86,93,127,133,156],"deep":[5],"reinforcement":[6],"learning":[7],"(DRL)":[8],"stands":[9],"on":[10],"regularization":[11,75,91,101],"policy":[13,24,111],"for":[14,30],"stable":[15],"and":[16,40,130],"efficient":[17],"learning.":[18],"A":[19],"popular":[20],"method,":[21],"named":[22],"proximal":[23],"optimization":[25],"(PPO),":[26],"has":[27],"been":[28],"introduced":[29],"this":[31],"purpose.":[32],"PPO":[33,87],"clips":[34],"density":[35,65,134],"ratio":[36,66,135],"the":[38,57,64,77,103,109,113,119,125,128,131,151,157,161],"latest":[39,110],"baseline":[41,114],"policies":[42],"with":[43,124],"a":[44,83,90],"threshold,":[45],"while":[46,63],"its":[47,117],"minimization":[48,105],"target":[49],"is":[50,60,68],"unclear.":[51],"As":[52],"another":[53],"problem":[54,92],"PPO,":[56],"symmetric":[58],"threshold":[59,129],"given":[61],"numerically":[62],"itself":[67],"in":[69,154],"asymmetric":[70],"domain,":[71],"thereby":[72],"causing":[73],"unbalanced":[74],"policy.":[78,163],"This":[79,100],"paper":[80],"therefore":[81],"proposes":[82],"new":[84],"variant":[85],"by":[88,160],"considering":[89],"relative":[94],"Pearson":[95],"(RPE)":[96],"divergence,":[97],"so-called":[98],"PPO-RPE.":[99],"yields":[102],"clear":[104],"target,":[106],"which":[107],"constrains":[108],"to":[112],"one.":[115],"Through":[116,139],"analysis,":[118],"intuitive":[120],"threshold-based":[121],"design":[122],"consistent":[123],"asymmetry":[126],"domain":[132],"can":[136],"be":[137],"derived.":[138],"four":[140],"benchmark":[141],"tasks,":[142],"PPO-RPE":[143],"performed":[144],"as":[145,147],"well":[146],"or":[148],"better":[149],"than":[150],"conventional":[152],"methods":[153],"terms":[155],"task":[158],"performance":[159],"learned":[162]},"counts_by_year":[{"year":2024,"cited_by_count":3},{"year":2023,"cited_by_count":1},{"year":2022,"cited_by_count":5},{"year":2021,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}