{"id":"https://openalex.org/W3135203571","doi":"https://doi.org/10.1109/tcyb.2021.3051456","title":"Authentic Boundary Proximal Policy Optimization","display_name":"Authentic Boundary Proximal Policy Optimization","publication_year":2021,"publication_date":"2021-03-11","ids":{"openalex":"https://openalex.org/W3135203571","doi":"https://doi.org/10.1109/tcyb.2021.3051456","mag":"3135203571","pmid":"https://pubmed.ncbi.nlm.nih.gov/33705327"},"language":"en","primary_location":{"id":"doi:10.1109/tcyb.2021.3051456","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tcyb.2021.3051456","pdf_url":null,"source":{"id":"https://openalex.org/S4210191041","display_name":"IEEE Transactions on Cybernetics","issn_l":"2168-2267","issn":["2168-2267","2168-2275"],"is_oa":false,"is_in_doaj":false,"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":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Transactions on Cybernetics","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/A5091364297","display_name":"Yuhu Cheng","orcid":"https://orcid.org/0000-0003-2022-9999"},"institutions":[{"id":"https://openalex.org/I25757504","display_name":"China University of Mining and Technology","ror":"https://ror.org/01xt2dr21","country_code":"CN","type":"education","lineage":["https://openalex.org/I25757504"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Yuhu Cheng","raw_affiliation_strings":["Engineering Research Center of Intelligent Control for Underground Space, Ministry of Education, China University of Mining and Technology, Xuzhou, China","School of Information and Control Engineering, China University of Mining and Technology, Xuzhou, China"],"affiliations":[{"raw_affiliation_string":"Engineering Research Center of Intelligent Control for Underground Space, Ministry of Education, China University of Mining and Technology, Xuzhou, China","institution_ids":["https://openalex.org/I25757504"]},{"raw_affiliation_string":"School of Information and Control Engineering, China University of Mining and Technology, Xuzhou, China","institution_ids":["https://openalex.org/I25757504"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5085372626","display_name":"Longyang Huang","orcid":"https://orcid.org/0000-0001-5123-5043"},"institutions":[{"id":"https://openalex.org/I25757504","display_name":"China University of Mining and Technology","ror":"https://ror.org/01xt2dr21","country_code":"CN","type":"education","lineage":["https://openalex.org/I25757504"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Longyang Huang","raw_affiliation_strings":["Engineering Research Center of Intelligent Control for Underground Space, Ministry of Education, China University of Mining and Technology, Xuzhou, China","School of Information and Control Engineering, China University of Mining and Technology, Xuzhou, China"],"affiliations":[{"raw_affiliation_string":"Engineering Research Center of Intelligent Control for Underground Space, Ministry of Education, China University of Mining and Technology, Xuzhou, China","institution_ids":["https://openalex.org/I25757504"]},{"raw_affiliation_string":"School of Information and Control Engineering, China University of Mining and Technology, Xuzhou, China","institution_ids":["https://openalex.org/I25757504"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5108064895","display_name":"Xuesong Wang","orcid":"https://orcid.org/0000-0002-5327-1088"},"institutions":[{"id":"https://openalex.org/I25757504","display_name":"China University of Mining and Technology","ror":"https://ror.org/01xt2dr21","country_code":"CN","type":"education","lineage":["https://openalex.org/I25757504"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xuesong Wang","raw_affiliation_strings":["Engineering Research Center of Intelligent Control for Underground Space, Ministry of Education, China University of Mining and Technology, Xuzhou, China","School of Information and Control Engineering, China University of Mining and Technology, Xuzhou, China"],"affiliations":[{"raw_affiliation_string":"Engineering Research Center of Intelligent Control for Underground Space, Ministry of Education, China University of Mining and Technology, Xuzhou, China","institution_ids":["https://openalex.org/I25757504"]},{"raw_affiliation_string":"School of Information and Control Engineering, China University of Mining and Technology, Xuzhou, China","institution_ids":["https://openalex.org/I25757504"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5091364297"],"corresponding_institution_ids":["https://openalex.org/I25757504"],"apc_list":null,"apc_paid":null,"fwci":4.7596,"has_fulltext":false,"cited_by_count":58,"citation_normalized_percentile":{"value":0.95654393,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":89,"max":100},"biblio":{"volume":"52","issue":"9","first_page":"9428","last_page":"9438"},"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/T12101","display_name":"Advanced Bandit Algorithms Research","score":0.994700014591217,"subfield":{"id":"https://openalex.org/subfields/1803","display_name":"Management Science and Operations Research"},"field":{"id":"https://openalex.org/fields/18","display_name":"Decision Sciences"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}},{"id":"https://openalex.org/T12288","display_name":"Optimization and Search Problems","score":0.9923999905586243,"subfield":{"id":"https://openalex.org/subfields/1705","display_name":"Computer Networks and Communications"},"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/boundary","display_name":"Boundary (topology)","score":0.4791833162307739},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.4225139617919922},{"id":"https://openalex.org/keywords/political-science","display_name":"Political science","score":0.3713959753513336},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.2566065192222595},{"id":"https://openalex.org/keywords/mathematical-analysis","display_name":"Mathematical analysis","score":0.1176745593547821}],"concepts":[{"id":"https://openalex.org/C62354387","wikidata":"https://www.wikidata.org/wiki/Q875399","display_name":"Boundary (topology)","level":2,"score":0.4791833162307739},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.4225139617919922},{"id":"https://openalex.org/C17744445","wikidata":"https://www.wikidata.org/wiki/Q36442","display_name":"Political science","level":0,"score":0.3713959753513336},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.2566065192222595},{"id":"https://openalex.org/C134306372","wikidata":"https://www.wikidata.org/wiki/Q7754","display_name":"Mathematical analysis","level":1,"score":0.1176745593547821}],"mesh":[{"descriptor_ui":"D000465","descriptor_name":"Algorithms","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D000465","descriptor_name":"Algorithms","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D000465","descriptor_name":"Algorithms","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D011243","descriptor_name":"Preferred Provider Organizations","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D011243","descriptor_name":"Preferred Provider Organizations","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D011243","descriptor_name":"Preferred Provider Organizations","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D057766","descriptor_name":"Policy","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D057766","descriptor_name":"Policy","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D057766","descriptor_name":"Policy","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false}],"locations_count":2,"locations":[{"id":"doi:10.1109/tcyb.2021.3051456","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tcyb.2021.3051456","pdf_url":null,"source":{"id":"https://openalex.org/S4210191041","display_name":"IEEE Transactions on Cybernetics","issn_l":"2168-2267","issn":["2168-2267","2168-2275"],"is_oa":false,"is_in_doaj":false,"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":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Transactions on Cybernetics","raw_type":"journal-article"},{"id":"pmid:33705327","is_oa":false,"landing_page_url":"https://pubmed.ncbi.nlm.nih.gov/33705327","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 cybernetics","raw_type":null}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G6792490895","display_name":null,"funder_award_id":"61976215","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G7031480287","display_name":null,"funder_award_id":"61772532","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":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":38,"referenced_works":["https://openalex.org/W2107726111","https://openalex.org/W2139053308","https://openalex.org/W2145339207","https://openalex.org/W2492794003","https://openalex.org/W2523345745","https://openalex.org/W2736601468","https://openalex.org/W2746553466","https://openalex.org/W2761873684","https://openalex.org/W2768629321","https://openalex.org/W2773423866","https://openalex.org/W2781726626","https://openalex.org/W2785397462","https://openalex.org/W2791797404","https://openalex.org/W2798189842","https://openalex.org/W2811329274","https://openalex.org/W2888100907","https://openalex.org/W2888742002","https://openalex.org/W2901621510","https://openalex.org/W2907944110","https://openalex.org/W2908261578","https://openalex.org/W2914808443","https://openalex.org/W2921474818","https://openalex.org/W2954033048","https://openalex.org/W2966349401","https://openalex.org/W2970999977","https://openalex.org/W3005672216","https://openalex.org/W3032398409","https://openalex.org/W3092202606","https://openalex.org/W3092253573","https://openalex.org/W3094027362","https://openalex.org/W4288310790","https://openalex.org/W4289303873","https://openalex.org/W4289388948","https://openalex.org/W4300906944","https://openalex.org/W6634413486","https://openalex.org/W6638018090","https://openalex.org/W6683204974","https://openalex.org/W6685444567"],"related_works":["https://openalex.org/W4391375266","https://openalex.org/W2899084033","https://openalex.org/W2748952813","https://openalex.org/W2390279801","https://openalex.org/W4391913857","https://openalex.org/W2358668433","https://openalex.org/W4396701345","https://openalex.org/W2376932109","https://openalex.org/W2001405890","https://openalex.org/W4396696052"],"abstract_inverted_index":{"In":[0,51,84],"recent":[1],"years,":[2],"the":[3,33,47,58,67,90,97,107,132,139,142,151,156,183,196,214,219,224],"proximal":[4],"policy":[5,64,102,118,175,191],"optimization":[6,65],"(PPO)":[7],"algorithm":[8,120],"has":[9,79],"received":[10],"considerable":[11],"attention":[12],"because":[13],"of":[14,32,35,49,61,92,100,158,185],"its":[15],"excellent":[16],"performance":[17,48],"in":[18,202],"many":[19],"challenging":[20],"tasks.":[21],"However,":[22],"there":[23],"is":[24,41,55,126,129,147],"still":[25],"a":[26,42,115],"large":[27],"space":[28],"for":[29],"theoretical":[30,68,108],"explanation":[31],"mechanism":[34],"PPO's":[36,71,93],"horizontal":[37],"clipping":[38,72,94,152,187],"operation,":[39],"which":[40,128,179],"key":[43],"means":[44],"to":[45],"improve":[46,213],"PPO.":[50,226],"addition,":[52],"while":[53],"PPO":[54,111,124,165,209],"inspired":[56],"by":[57,154],"learning":[59,215,220],"theory":[60],"trust":[62,76],"region":[63,77],"(TRPO),":[66],"connection":[69],"between":[70,110,141],"operation":[73,95],"and":[74,104,112,144,172,188,217],"TRPO's":[75],"constraint":[78],"not":[80],"been":[81],"well":[82],"studied.":[83],"this":[85],"article,":[86],"we":[87,160],"first":[88],"analyze":[89],"effect":[91],"on":[96,131,182,195],"objective":[98],"function":[99],"conservative":[101],"iteration,":[103],"strictly":[105],"give":[106],"relationship":[109],"TRPO.":[113],"Then,":[114],"novel":[116,163],"first-order":[117],"gradient":[119],"called":[121,167],"authentic":[122,133],"boundary":[123,134],"(ABPPO)":[125],"proposed,":[127],"based":[130,181],"setting":[135],"rule.":[136],"To":[137],"ensure":[138],"difference":[140],"new":[143],"old":[145],"policies":[146],"better":[148],"kept":[149],"within":[150],"range,":[153],"borrowing":[155],"idea":[157],"ABPPO,":[159],"proposed":[161,207],"two":[162],"improved":[164,208],"algorithms":[166,210],"rollback":[168,186],"mechanism-based":[169],"ABPPO":[170,177],"(RMABPPO)":[171],"penalized":[173,189],"point":[174,190],"difference-based":[176],"(P3DABPPO),":[178],"are":[180],"ideas":[184],"difference,":[192],"respectively.":[193],"Experiments":[194],"continuous":[197],"robotic":[198],"control":[199],"tasks":[200],"implemented":[201],"MuJoCo":[203],"show":[204],"that":[205],"our":[206],"can":[211],"effectively":[212],"stability":[216],"accelerate":[218],"speed":[221],"compared":[222],"with":[223],"original":[225]},"counts_by_year":[{"year":2026,"cited_by_count":6},{"year":2025,"cited_by_count":18},{"year":2024,"cited_by_count":20},{"year":2023,"cited_by_count":8},{"year":2022,"cited_by_count":5},{"year":2021,"cited_by_count":1}],"updated_date":"2026-04-18T07:56:08.524223","created_date":"2025-10-10T00:00:00"}