{"id":"https://openalex.org/W4309669389","doi":"https://doi.org/10.1109/tpami.2022.3223407","title":"Reward-Adaptive Reinforcement Learning: Dynamic Policy Gradient Optimization for Bipedal Locomotion","display_name":"Reward-Adaptive Reinforcement Learning: Dynamic Policy Gradient Optimization for Bipedal Locomotion","publication_year":2022,"publication_date":"2022-11-21","ids":{"openalex":"https://openalex.org/W4309669389","doi":"https://doi.org/10.1109/tpami.2022.3223407","pmid":"https://pubmed.ncbi.nlm.nih.gov/36409817"},"language":"en","primary_location":{"id":"doi:10.1109/tpami.2022.3223407","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tpami.2022.3223407","pdf_url":null,"source":{"id":"https://openalex.org/S199944782","display_name":"IEEE Transactions on Pattern Analysis and Machine Intelligence","issn_l":"0162-8828","issn":["0162-8828","1939-3539","2160-9292"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310320439","host_organization_name":"IEEE Computer Society","host_organization_lineage":["https://openalex.org/P4310320439","https://openalex.org/P4310319808"],"host_organization_lineage_names":["IEEE Computer Society","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 Pattern Analysis and Machine Intelligence","raw_type":"journal-article"},"type":"article","indexed_in":["crossref","pubmed"],"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/A5046865333","display_name":"Changxin Huang","orcid":"https://orcid.org/0000-0002-9588-064X"},"institutions":[{"id":"https://openalex.org/I157773358","display_name":"Sun Yat-sen University","ror":"https://ror.org/0064kty71","country_code":"CN","type":"education","lineage":["https://openalex.org/I157773358"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Changxin Huang","raw_affiliation_strings":["School of Intelligent Systems Engineering, Sun Yat-sen University, Guangzhou, China"],"raw_orcid":"https://orcid.org/0000-0002-9588-064X","affiliations":[{"raw_affiliation_string":"School of Intelligent Systems Engineering, Sun Yat-sen University, Guangzhou, China","institution_ids":["https://openalex.org/I157773358"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5052611320","display_name":"Guangrun Wang","orcid":"https://orcid.org/0000-0001-7760-1339"},"institutions":[{"id":"https://openalex.org/I40120149","display_name":"University of Oxford","ror":"https://ror.org/052gg0110","country_code":"GB","type":"education","lineage":["https://openalex.org/I40120149"]},{"id":"https://openalex.org/I4210146410","display_name":"Science Oxford","ror":"https://ror.org/04j8yhy50","country_code":"GB","type":"nonprofit","lineage":["https://openalex.org/I4210146410"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Guangrun Wang","raw_affiliation_strings":["Department of Engineering Science, University of Oxford, Oxford, United Kingdom"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Engineering Science, University of Oxford, Oxford, United Kingdom","institution_ids":["https://openalex.org/I4210146410","https://openalex.org/I40120149"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5110959641","display_name":"Zhibo Zhou","orcid":"https://orcid.org/0009-0006-4034-4221"},"institutions":[{"id":"https://openalex.org/I157773358","display_name":"Sun Yat-sen University","ror":"https://ror.org/0064kty71","country_code":"CN","type":"education","lineage":["https://openalex.org/I157773358"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zhibo Zhou","raw_affiliation_strings":["School of Computer Science and Engineering, Sun Yat-sen University, Guangzhou, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Computer Science and Engineering, Sun Yat-sen University, Guangzhou, China","institution_ids":["https://openalex.org/I157773358"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5029387407","display_name":"Ronghui Zhang","orcid":"https://orcid.org/0000-0001-6107-4044"},"institutions":[{"id":"https://openalex.org/I157773358","display_name":"Sun Yat-sen University","ror":"https://ror.org/0064kty71","country_code":"CN","type":"education","lineage":["https://openalex.org/I157773358"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Ronghui Zhang","raw_affiliation_strings":["School of Intelligent Systems Engineering, Sun Yat-sen University, Guangzhou, China"],"raw_orcid":"https://orcid.org/0000-0001-6107-4044","affiliations":[{"raw_affiliation_string":"School of Intelligent Systems Engineering, Sun Yat-sen University, Guangzhou, China","institution_ids":["https://openalex.org/I157773358"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5100412937","display_name":"Liang Lin","orcid":"https://orcid.org/0000-0003-2248-3755"},"institutions":[{"id":"https://openalex.org/I157773358","display_name":"Sun Yat-sen University","ror":"https://ror.org/0064kty71","country_code":"CN","type":"education","lineage":["https://openalex.org/I157773358"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Liang Lin","raw_affiliation_strings":["School of Computer Science and Engineering, Sun Yat-sen University, Guangzhou, China"],"raw_orcid":"https://orcid.org/0000-0003-2248-3755","affiliations":[{"raw_affiliation_string":"School of Computer Science and Engineering, Sun Yat-sen University, Guangzhou, China","institution_ids":["https://openalex.org/I157773358"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":5,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":2.8605,"has_fulltext":false,"cited_by_count":38,"citation_normalized_percentile":{"value":0.91262319,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":98,"max":100},"biblio":{"volume":"45","issue":"6","first_page":"7686","last_page":"7695"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10879","display_name":"Robotic Locomotion and Control","score":0.9991999864578247,"subfield":{"id":"https://openalex.org/subfields/2204","display_name":"Biomedical Engineering"},"field":{"id":"https://openalex.org/fields/22","display_name":"Engineering"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},"topics":[{"id":"https://openalex.org/T10879","display_name":"Robotic Locomotion and Control","score":0.9991999864578247,"subfield":{"id":"https://openalex.org/subfields/2204","display_name":"Biomedical Engineering"},"field":{"id":"https://openalex.org/fields/22","display_name":"Engineering"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T11023","display_name":"Prosthetics and Rehabilitation Robotics","score":0.9815000295639038,"subfield":{"id":"https://openalex.org/subfields/2204","display_name":"Biomedical Engineering"},"field":{"id":"https://openalex.org/fields/22","display_name":"Engineering"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T11663","display_name":"Viral Infectious Diseases and Gene Expression in Insects","score":0.9607999920845032,"subfield":{"id":"https://openalex.org/subfields/1312","display_name":"Molecular Biology"},"field":{"id":"https://openalex.org/fields/13","display_name":"Biochemistry, Genetics and Molecular Biology"},"domain":{"id":"https://openalex.org/domains/1","display_name":"Life Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/reinforcement-learning","display_name":"Reinforcement learning","score":0.9083415865898132},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.676467776298523},{"id":"https://openalex.org/keywords/generalization","display_name":"Generalization","score":0.5884039402008057},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.577034592628479},{"id":"https://openalex.org/keywords/robot","display_name":"Robot","score":0.5563755631446838},{"id":"https://openalex.org/keywords/bellman-equation","display_name":"Bellman equation","score":0.5218456983566284},{"id":"https://openalex.org/keywords/component","display_name":"Component (thermodynamics)","score":0.42799896001815796},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.3581901788711548},{"id":"https://openalex.org/keywords/mathematical-optimization","display_name":"Mathematical optimization","score":0.31024280190467834},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.186649352312088}],"concepts":[{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.9083415865898132},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.676467776298523},{"id":"https://openalex.org/C177148314","wikidata":"https://www.wikidata.org/wiki/Q170084","display_name":"Generalization","level":2,"score":0.5884039402008057},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.577034592628479},{"id":"https://openalex.org/C90509273","wikidata":"https://www.wikidata.org/wiki/Q11012","display_name":"Robot","level":2,"score":0.5563755631446838},{"id":"https://openalex.org/C14646407","wikidata":"https://www.wikidata.org/wiki/Q1430750","display_name":"Bellman equation","level":2,"score":0.5218456983566284},{"id":"https://openalex.org/C168167062","wikidata":"https://www.wikidata.org/wiki/Q1117970","display_name":"Component (thermodynamics)","level":2,"score":0.42799896001815796},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.3581901788711548},{"id":"https://openalex.org/C126255220","wikidata":"https://www.wikidata.org/wiki/Q141495","display_name":"Mathematical optimization","level":1,"score":0.31024280190467834},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.186649352312088},{"id":"https://openalex.org/C134306372","wikidata":"https://www.wikidata.org/wiki/Q7754","display_name":"Mathematical analysis","level":1,"score":0.0},{"id":"https://openalex.org/C97355855","wikidata":"https://www.wikidata.org/wiki/Q11473","display_name":"Thermodynamics","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}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/tpami.2022.3223407","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tpami.2022.3223407","pdf_url":null,"source":{"id":"https://openalex.org/S199944782","display_name":"IEEE Transactions on Pattern Analysis and Machine Intelligence","issn_l":"0162-8828","issn":["0162-8828","1939-3539","2160-9292"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310320439","host_organization_name":"IEEE Computer Society","host_organization_lineage":["https://openalex.org/P4310320439","https://openalex.org/P4310319808"],"host_organization_lineage_names":["IEEE Computer Society","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 Pattern Analysis and Machine Intelligence","raw_type":"journal-article"},{"id":"pmid:36409817","is_oa":false,"landing_page_url":"https://pubmed.ncbi.nlm.nih.gov/36409817","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":"IEEE transactions on pattern analysis and machine intelligence","raw_type":null}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G1295000622","display_name":null,"funder_award_id":"61836012","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G1365118710","display_name":null,"funder_award_id":"2017A030312006","funder_id":"https://openalex.org/F4320337111","funder_display_name":"Basic and Applied Basic Research Foundation of Guangdong Province"},{"id":"https://openalex.org/G1506100783","display_name":null,"funder_award_id":"U21A20470","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G3577923441","display_name":null,"funder_award_id":"U1811463","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G3955732362","display_name":null,"funder_award_id":"62006255","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G5543444180","display_name":null,"funder_award_id":"62206314","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G8486830386","display_name":null,"funder_award_id":"2022A1515011835","funder_id":"https://openalex.org/F4320337111","funder_display_name":"Basic and Applied Basic Research Foundation of Guangdong Province"},{"id":"https://openalex.org/G8558289817","display_name":null,"funder_award_id":"61876224","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"},{"id":"https://openalex.org/F4320337111","display_name":"Basic and Applied Basic Research Foundation of Guangdong Province","ror":null}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":51,"referenced_works":["https://openalex.org/W566530810","https://openalex.org/W1522301498","https://openalex.org/W2017957151","https://openalex.org/W2074042377","https://openalex.org/W2133859362","https://openalex.org/W2142641780","https://openalex.org/W2157087522","https://openalex.org/W2162109810","https://openalex.org/W2171879251","https://openalex.org/W2381269752","https://openalex.org/W2569324215","https://openalex.org/W2606568940","https://openalex.org/W2617339591","https://openalex.org/W2624731731","https://openalex.org/W2736601468","https://openalex.org/W2739330054","https://openalex.org/W2763052367","https://openalex.org/W2784449021","https://openalex.org/W2791500836","https://openalex.org/W2792099719","https://openalex.org/W2906204569","https://openalex.org/W2950892788","https://openalex.org/W2952996256","https://openalex.org/W2963864421","https://openalex.org/W2964114602","https://openalex.org/W2964671970","https://openalex.org/W2968717280","https://openalex.org/W2979820775","https://openalex.org/W2982045184","https://openalex.org/W3029641972","https://openalex.org/W3038194455","https://openalex.org/W3091173443","https://openalex.org/W3091756548","https://openalex.org/W3105609823","https://openalex.org/W3127527157","https://openalex.org/W3206620955","https://openalex.org/W4221157877","https://openalex.org/W4287997343","https://openalex.org/W4298857966","https://openalex.org/W6631190155","https://openalex.org/W6637967152","https://openalex.org/W6680724558","https://openalex.org/W6684921986","https://openalex.org/W6736813088","https://openalex.org/W6741002519","https://openalex.org/W6747311492","https://openalex.org/W6768753331","https://openalex.org/W6769810359","https://openalex.org/W6778428183","https://openalex.org/W6780559895","https://openalex.org/W6809706482"],"related_works":["https://openalex.org/W4362501864","https://openalex.org/W4306904969","https://openalex.org/W3162204513","https://openalex.org/W4380318855","https://openalex.org/W2138720691","https://openalex.org/W2031695474","https://openalex.org/W2386410636","https://openalex.org/W3038962357","https://openalex.org/W2025663273","https://openalex.org/W3099153698"],"abstract_inverted_index":{"Controlling":[0],"a":[1,45,49,76,97,104,109],"non-statically":[2],"bipedal":[3],"robot":[4],"is":[5,51,161],"challenging":[6],"due":[7],"to":[8,43,58,89,107,118,130,163,165],"the":[9,20,35,67,86,132,146,154,173],"complex":[10,68],"dynamics":[11],"and":[12,29,54,139,160,175],"multi-criterion":[13],"optimization":[14],"involved.":[15],"Recent":[16],"works":[17],"have":[18],"demonstrated":[19],"effectiveness":[21,174],"of":[22,177],"deep":[23],"reinforcement":[24,79],"learning":[25,80],"(DRL)":[26],"for":[27,62,82,113],"simulation":[28],"physical":[30,166],"robots.":[31,167],"In":[32,71],"these":[33],"methods,":[34],"rewards":[36],"from":[37,66],"different":[38,135],"criteria":[39,95],"are":[40],"normally":[41],"summed":[42],"learn":[44,108,148],"scalar":[46,50],"function.":[47],"However,":[48],"less":[52],"informative":[53],"may":[55],"be":[56,90],"insufficient":[57],"derive":[59],"effective":[60],"information":[61],"each":[63,114,128],"reward":[64,115],"channel":[65],"hybrid":[69,119,138],"rewards.":[70],"this":[72],"work,":[73],"we":[74],"propose":[75,124],"novel":[77],"reward-adaptive":[78],"method":[81,102,156],"biped":[83],"locomotion,":[84],"allowing":[85,127],"control":[87],"policy":[88,120,133,141],"simultaneously":[91],"optimized":[92],"by":[93],"multiple":[94],"using":[96],"dynamic":[98,125,140],"mechanism.":[99],"The":[100,168],"proposed":[101,155],"applies":[103],"multi-head":[105],"critic":[106],"separate":[110],"value":[111],"function":[112],"component,":[116],"leading":[117],"gradients.":[121],"We":[122,151],"further":[123,171],"weight,":[126],"component":[129],"optimize":[131],"with":[134],"priorities.":[136],"This":[137],"gradient":[142],"(HDPG)":[143],"design":[144],"makes":[145],"agent":[147],"more":[149],"efficiently.":[150],"show":[152],"that":[153],"outperforms":[157],"summed-up-reward":[158],"approaches":[159],"able":[162],"transfer":[164],"MuJoCo":[169],"results":[170],"demonstrate":[172],"generalization":[176],"HDPG.":[178]},"counts_by_year":[{"year":2026,"cited_by_count":3},{"year":2025,"cited_by_count":18},{"year":2024,"cited_by_count":11},{"year":2023,"cited_by_count":6}],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2025-10-10T00:00:00"}