{"id":"https://openalex.org/W4403977024","doi":"https://doi.org/10.1109/lra.2024.3490392","title":"Constrained Dirichlet Distribution Policy: Guarantee Zero Constraint Violation Reinforcement Learning for Continuous Robotic Control","display_name":"Constrained Dirichlet Distribution Policy: Guarantee Zero Constraint Violation Reinforcement Learning for Continuous Robotic Control","publication_year":2024,"publication_date":"2024-11-01","ids":{"openalex":"https://openalex.org/W4403977024","doi":"https://doi.org/10.1109/lra.2024.3490392"},"language":"en","primary_location":{"id":"doi:10.1109/lra.2024.3490392","is_oa":false,"landing_page_url":"https://doi.org/10.1109/lra.2024.3490392","pdf_url":null,"source":{"id":"https://openalex.org/S4210169774","display_name":"IEEE Robotics and Automation Letters","issn_l":"2377-3766","issn":["2377-3766","2377-3774"],"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 Robotics and Automation Letters","raw_type":"journal-article"},"type":"article","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/A5101087933","display_name":"Jianming Ma","orcid":"https://orcid.org/0000-0001-5769-2093"},"institutions":[{"id":"https://openalex.org/I183067930","display_name":"Shanghai Jiao Tong University","ror":"https://ror.org/0220qvk04","country_code":"CN","type":"education","lineage":["https://openalex.org/I183067930"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jianming Ma","raw_affiliation_strings":["Department of Automation, Shanghai Jiao Tong University, Shanghai, China"],"raw_orcid":"https://orcid.org/0000-0001-5769-2093","affiliations":[{"raw_affiliation_string":"Department of Automation, Shanghai Jiao Tong University, Shanghai, China","institution_ids":["https://openalex.org/I183067930"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5022312971","display_name":"Zhanxiang Cao","orcid":"https://orcid.org/0009-0001-2961-2997"},"institutions":[{"id":"https://openalex.org/I183067930","display_name":"Shanghai Jiao Tong University","ror":"https://ror.org/0220qvk04","country_code":"CN","type":"education","lineage":["https://openalex.org/I183067930"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zhanxiang Cao","raw_affiliation_strings":["Department of Computer Science and Technology, Shanghai Jiao Tong University, Shanghai, China"],"raw_orcid":"https://orcid.org/0009-0001-2961-2997","affiliations":[{"raw_affiliation_string":"Department of Computer Science and Technology, Shanghai Jiao Tong University, Shanghai, China","institution_ids":["https://openalex.org/I183067930"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5001956754","display_name":"Yue Gao","orcid":"https://orcid.org/0000-0002-8901-9335"},"institutions":[{"id":"https://openalex.org/I183067930","display_name":"Shanghai Jiao Tong University","ror":"https://ror.org/0220qvk04","country_code":"CN","type":"education","lineage":["https://openalex.org/I183067930"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yue Gao","raw_affiliation_strings":["MoE Key Lab of Artificial Intelligence and AI Institute, Shanghai Jiao Tong University, Shanghai, China"],"raw_orcid":"https://orcid.org/0000-0002-8901-9335","affiliations":[{"raw_affiliation_string":"MoE Key Lab of Artificial Intelligence and AI Institute, Shanghai Jiao Tong University, Shanghai, China","institution_ids":["https://openalex.org/I183067930"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I183067930"],"apc_list":null,"apc_paid":null,"fwci":0.2276,"has_fulltext":false,"cited_by_count":3,"citation_normalized_percentile":{"value":0.3900641,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":94,"max":97},"biblio":{"volume":"9","issue":"12","first_page":"11690","last_page":"11697"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T12617","display_name":"Energy, Environment, and Transportation Policies","score":0.8885999917984009,"subfield":{"id":"https://openalex.org/subfields/2105","display_name":"Renewable Energy, Sustainability and the Environment"},"field":{"id":"https://openalex.org/fields/21","display_name":"Energy"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},"topics":[{"id":"https://openalex.org/T12617","display_name":"Energy, Environment, and Transportation Policies","score":0.8885999917984009,"subfield":{"id":"https://openalex.org/subfields/2105","display_name":"Renewable Energy, Sustainability and the Environment"},"field":{"id":"https://openalex.org/fields/21","display_name":"Energy"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T11942","display_name":"Transportation and Mobility Innovations","score":0.866100013256073,"subfield":{"id":"https://openalex.org/subfields/2203","display_name":"Automotive 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/T10462","display_name":"Reinforcement Learning in Robotics","score":0.7950999736785889,"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/reinforcement-learning","display_name":"Reinforcement learning","score":0.8551245331764221},{"id":"https://openalex.org/keywords/constraint","display_name":"Constraint (computer-aided design)","score":0.6532580256462097},{"id":"https://openalex.org/keywords/zero","display_name":"Zero (linguistics)","score":0.6455156207084656},{"id":"https://openalex.org/keywords/control","display_name":"Control (management)","score":0.5898870825767517},{"id":"https://openalex.org/keywords/dirichlet-distribution","display_name":"Dirichlet distribution","score":0.5251186490058899},{"id":"https://openalex.org/keywords/mathematical-optimization","display_name":"Mathematical optimization","score":0.4833521544933319},{"id":"https://openalex.org/keywords/reinforcement","display_name":"Reinforcement","score":0.47208094596862793},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.42697083950042725},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.4267585277557373},{"id":"https://openalex.org/keywords/control-theory","display_name":"Control theory (sociology)","score":0.3937262296676636},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.27495288848876953},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.20998844504356384},{"id":"https://openalex.org/keywords/mathematical-analysis","display_name":"Mathematical analysis","score":0.1954280436038971},{"id":"https://openalex.org/keywords/geometry","display_name":"Geometry","score":0.08032166957855225},{"id":"https://openalex.org/keywords/structural-engineering","display_name":"Structural engineering","score":0.07103782892227173}],"concepts":[{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.8551245331764221},{"id":"https://openalex.org/C2776036281","wikidata":"https://www.wikidata.org/wiki/Q48769818","display_name":"Constraint (computer-aided design)","level":2,"score":0.6532580256462097},{"id":"https://openalex.org/C2780813799","wikidata":"https://www.wikidata.org/wiki/Q3274237","display_name":"Zero (linguistics)","level":2,"score":0.6455156207084656},{"id":"https://openalex.org/C2775924081","wikidata":"https://www.wikidata.org/wiki/Q55608371","display_name":"Control (management)","level":2,"score":0.5898870825767517},{"id":"https://openalex.org/C169214877","wikidata":"https://www.wikidata.org/wiki/Q981016","display_name":"Dirichlet distribution","level":3,"score":0.5251186490058899},{"id":"https://openalex.org/C126255220","wikidata":"https://www.wikidata.org/wiki/Q141495","display_name":"Mathematical optimization","level":1,"score":0.4833521544933319},{"id":"https://openalex.org/C67203356","wikidata":"https://www.wikidata.org/wiki/Q1321905","display_name":"Reinforcement","level":2,"score":0.47208094596862793},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.42697083950042725},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.4267585277557373},{"id":"https://openalex.org/C47446073","wikidata":"https://www.wikidata.org/wiki/Q5165890","display_name":"Control theory (sociology)","level":3,"score":0.3937262296676636},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.27495288848876953},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.20998844504356384},{"id":"https://openalex.org/C134306372","wikidata":"https://www.wikidata.org/wiki/Q7754","display_name":"Mathematical analysis","level":1,"score":0.1954280436038971},{"id":"https://openalex.org/C2524010","wikidata":"https://www.wikidata.org/wiki/Q8087","display_name":"Geometry","level":1,"score":0.08032166957855225},{"id":"https://openalex.org/C66938386","wikidata":"https://www.wikidata.org/wiki/Q633538","display_name":"Structural engineering","level":1,"score":0.07103782892227173},{"id":"https://openalex.org/C182310444","wikidata":"https://www.wikidata.org/wiki/Q1332643","display_name":"Boundary value problem","level":2,"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/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/lra.2024.3490392","is_oa":false,"landing_page_url":"https://doi.org/10.1109/lra.2024.3490392","pdf_url":null,"source":{"id":"https://openalex.org/S4210169774","display_name":"IEEE Robotics and Automation Letters","issn_l":"2377-3766","issn":["2377-3766","2377-3774"],"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 Robotics and Automation Letters","raw_type":"journal-article"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Reduced inequalities","id":"https://metadata.un.org/sdg/10","score":0.41999998688697815}],"awards":[{"id":"https://openalex.org/G6697330851","display_name":null,"funder_award_id":"62373242","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G8604742246","display_name":null,"funder_award_id":"92248303","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/F4320335787","display_name":"Fundamental Research Funds for the Central Universities","ror":null}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":44,"referenced_works":["https://openalex.org/W2158782408","https://openalex.org/W2492353954","https://openalex.org/W2736258566","https://openalex.org/W2736601468","https://openalex.org/W2784465508","https://openalex.org/W2913300629","https://openalex.org/W2963293747","https://openalex.org/W2968945909","https://openalex.org/W2996956772","https://openalex.org/W2998619042","https://openalex.org/W3035945418","https://openalex.org/W3103356223","https://openalex.org/W3122384525","https://openalex.org/W3127561923","https://openalex.org/W3135301907","https://openalex.org/W3162902207","https://openalex.org/W3195968524","https://openalex.org/W3207310431","https://openalex.org/W3213974477","https://openalex.org/W3216772467","https://openalex.org/W4206497039","https://openalex.org/W4206671011","https://openalex.org/W4213251304","https://openalex.org/W4226200846","https://openalex.org/W4379805190","https://openalex.org/W4383108274","https://openalex.org/W4392763392","https://openalex.org/W4394872716","https://openalex.org/W6631643967","https://openalex.org/W6687063787","https://openalex.org/W6737893269","https://openalex.org/W6741002519","https://openalex.org/W6747473740","https://openalex.org/W6747790125","https://openalex.org/W6758924645","https://openalex.org/W6766978945","https://openalex.org/W6780032648","https://openalex.org/W6780559895","https://openalex.org/W6790301552","https://openalex.org/W6800004206","https://openalex.org/W6800776581","https://openalex.org/W6804601995","https://openalex.org/W6847063038","https://openalex.org/W6858746968"],"related_works":["https://openalex.org/W4310083477","https://openalex.org/W2328553770","https://openalex.org/W2920061524","https://openalex.org/W1977959518","https://openalex.org/W2038908348","https://openalex.org/W2107890255","https://openalex.org/W2106552856","https://openalex.org/W2145821588","https://openalex.org/W2086122291","https://openalex.org/W1987513656"],"abstract_inverted_index":{"Learning-based":[0],"controllers":[1],"show":[2],"promising":[3],"performances":[4],"in":[5,20,65,69],"robotic":[6],"control":[7],"tasks.":[8],"However,":[9],"they":[10],"still":[11],"present":[12],"potential":[13,97],"safety":[14],"risks":[15],"due":[16],"to":[17,50],"the":[18,37,62,89,94],"difficulty":[19],"ensuring":[21],"satisfaction":[22,54],"of":[23,88,99],"complex":[24],"action":[25,39],"constraints.":[26],"We":[27,60],"propose":[28],"a":[29,70],"novel":[30],"action-constrained":[31],"reinforcement":[32],"learning":[33],"method,":[34],"which":[35],"transforms":[36],"constrained":[38],"space":[40,44],"into":[41],"its":[42],"dual":[43],"and":[45,68,83,96],"uses":[46],"Dirichlet":[47],"distribution":[48],"policy":[49],"guarantee":[51],"strict":[52],"constraint":[53],"as":[55,57],"well":[56],"randomized":[58],"exploration.":[59],"validate":[61],"proposed":[63],"method":[64,76],"benchmark":[66],"environments":[67],"real":[71,90],"quadruped":[72],"locomotion":[73],"task.":[74],"Our":[75],"outperforms":[77],"other":[78],"baselines":[79],"with":[80],"higher":[81],"reward":[82],"faster":[84],"inference":[85],"speed.":[86],"Results":[87],"robot":[91],"experiments":[92],"demonstrate":[93],"effectiveness":[95],"application":[98],"our":[100],"method.":[101]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":2}],"updated_date":"2026-07-25T15:57:00.446498","created_date":"2025-10-10T00:00:00"}