{"id":"https://openalex.org/W3089710958","doi":"https://doi.org/10.1109/icra40945.2020.9197200","title":"Dynamic Actor-Advisor Programming for Scalable Safe Reinforcement Learning","display_name":"Dynamic Actor-Advisor Programming for Scalable Safe Reinforcement Learning","publication_year":2020,"publication_date":"2020-05-01","ids":{"openalex":"https://openalex.org/W3089710958","doi":"https://doi.org/10.1109/icra40945.2020.9197200","mag":"3089710958"},"language":"en","primary_location":{"id":"doi:10.1109/icra40945.2020.9197200","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icra40945.2020.9197200","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2020 IEEE International Conference on Robotics and Automation (ICRA)","raw_type":"proceedings-article"},"type":"conference-paper","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/A5012201453","display_name":"Lingwei Zhu","orcid":null},"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":false,"raw_author_name":"Lingwei Zhu","raw_affiliation_strings":["Graduate School of Science and Technology, Nara Institute of Science and Technology (NAIST), Nara, Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Graduate School of Science and Technology, Nara Institute of Science and Technology (NAIST), Nara, Japan","institution_ids":["https://openalex.org/I75917431"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5011048472","display_name":"Yunduan Cui","orcid":"https://orcid.org/0000-0001-5539-4260"},"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":false,"raw_author_name":"Yunduan Cui","raw_affiliation_strings":["Graduate School of Science and Technology, Nara Institute of Science and Technology (NAIST), Nara, Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Graduate School of Science and Technology, Nara Institute of Science and Technology (NAIST), Nara, Japan","institution_ids":["https://openalex.org/I75917431"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5042074952","display_name":"Takamitsu Matsubara","orcid":"https://orcid.org/0000-0003-3545-4814"},"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":false,"raw_author_name":"Takamitsu Matsubara","raw_affiliation_strings":["Graduate School of Science and Technology, Nara Institute of Science and Technology (NAIST), Nara, Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Graduate School of Science and Technology, Nara Institute of Science and Technology (NAIST), Nara, Japan","institution_ids":["https://openalex.org/I75917431"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I75917431"],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":6,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":"13","issue":null,"first_page":"10681","last_page":"10687"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10462","display_name":"Reinforcement Learning in Robotics","score":0.9997000098228455,"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":0.9997000098228455,"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/T10653","display_name":"Robot Manipulation and Learning","score":0.9922999739646912,"subfield":{"id":"https://openalex.org/subfields/2207","display_name":"Control and Systems 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/T11689","display_name":"Adversarial Robustness in Machine Learning","score":0.9596999883651733,"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":0.895295262336731},{"id":"https://openalex.org/keywords/scalability","display_name":"Scalability","score":0.7644041776657104},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7509872317314148},{"id":"https://openalex.org/keywords/dynamic-programming","display_name":"Dynamic programming","score":0.6959089040756226},{"id":"https://openalex.org/keywords/constraint","display_name":"Constraint (computer-aided design)","score":0.5941042900085449},{"id":"https://openalex.org/keywords/robot","display_name":"Robot","score":0.5817834734916687},{"id":"https://openalex.org/keywords/baseline","display_name":"Baseline (sea)","score":0.5781981945037842},{"id":"https://openalex.org/keywords/sample","display_name":"Sample (material)","score":0.567686915397644},{"id":"https://openalex.org/keywords/divergence","display_name":"Divergence (linguistics)","score":0.5321015119552612},{"id":"https://openalex.org/keywords/constraint-programming","display_name":"Constraint programming","score":0.4489808976650238},{"id":"https://openalex.org/keywords/control","display_name":"Control (management)","score":0.4383085370063782},{"id":"https://openalex.org/keywords/sample-complexity","display_name":"Sample complexity","score":0.42077693343162537},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4197380840778351},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.3842760920524597},{"id":"https://openalex.org/keywords/mathematical-optimization","display_name":"Mathematical optimization","score":0.34132498502731323},{"id":"https://openalex.org/keywords/distributed-computing","display_name":"Distributed computing","score":0.3240223228931427},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.1273289918899536},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.1113760769367218},{"id":"https://openalex.org/keywords/stochastic-programming","display_name":"Stochastic programming","score":0.08494269847869873},{"id":"https://openalex.org/keywords/operating-system","display_name":"Operating system","score":0.07319313287734985}],"concepts":[{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.895295262336731},{"id":"https://openalex.org/C48044578","wikidata":"https://www.wikidata.org/wiki/Q727490","display_name":"Scalability","level":2,"score":0.7644041776657104},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7509872317314148},{"id":"https://openalex.org/C37404715","wikidata":"https://www.wikidata.org/wiki/Q380679","display_name":"Dynamic programming","level":2,"score":0.6959089040756226},{"id":"https://openalex.org/C2776036281","wikidata":"https://www.wikidata.org/wiki/Q48769818","display_name":"Constraint (computer-aided design)","level":2,"score":0.5941042900085449},{"id":"https://openalex.org/C90509273","wikidata":"https://www.wikidata.org/wiki/Q11012","display_name":"Robot","level":2,"score":0.5817834734916687},{"id":"https://openalex.org/C12725497","wikidata":"https://www.wikidata.org/wiki/Q810247","display_name":"Baseline (sea)","level":2,"score":0.5781981945037842},{"id":"https://openalex.org/C198531522","wikidata":"https://www.wikidata.org/wiki/Q485146","display_name":"Sample (material)","level":2,"score":0.567686915397644},{"id":"https://openalex.org/C207390915","wikidata":"https://www.wikidata.org/wiki/Q1230525","display_name":"Divergence (linguistics)","level":2,"score":0.5321015119552612},{"id":"https://openalex.org/C173404611","wikidata":"https://www.wikidata.org/wiki/Q528588","display_name":"Constraint programming","level":3,"score":0.4489808976650238},{"id":"https://openalex.org/C2775924081","wikidata":"https://www.wikidata.org/wiki/Q55608371","display_name":"Control (management)","level":2,"score":0.4383085370063782},{"id":"https://openalex.org/C2778445095","wikidata":"https://www.wikidata.org/wiki/Q18354077","display_name":"Sample complexity","level":2,"score":0.42077693343162537},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4197380840778351},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.3842760920524597},{"id":"https://openalex.org/C126255220","wikidata":"https://www.wikidata.org/wiki/Q141495","display_name":"Mathematical optimization","level":1,"score":0.34132498502731323},{"id":"https://openalex.org/C120314980","wikidata":"https://www.wikidata.org/wiki/Q180634","display_name":"Distributed computing","level":1,"score":0.3240223228931427},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.1273289918899536},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.1113760769367218},{"id":"https://openalex.org/C137631369","wikidata":"https://www.wikidata.org/wiki/Q7617831","display_name":"Stochastic programming","level":2,"score":0.08494269847869873},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.07319313287734985},{"id":"https://openalex.org/C127313418","wikidata":"https://www.wikidata.org/wiki/Q1069","display_name":"Geology","level":0,"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/C111368507","wikidata":"https://www.wikidata.org/wiki/Q43518","display_name":"Oceanography","level":1,"score":0.0},{"id":"https://openalex.org/C78519656","wikidata":"https://www.wikidata.org/wiki/Q101333","display_name":"Mechanical engineering","level":1,"score":0.0},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.0},{"id":"https://openalex.org/C43617362","wikidata":"https://www.wikidata.org/wiki/Q170050","display_name":"Chromatography","level":1,"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/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icra40945.2020.9197200","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icra40945.2020.9197200","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2020 IEEE International Conference on Robotics and Automation (ICRA)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.7099999785423279,"display_name":"Peace, Justice and strong institutions","id":"https://metadata.un.org/sdg/16"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":39,"referenced_works":["https://openalex.org/W1518931405","https://openalex.org/W1575592356","https://openalex.org/W1840625103","https://openalex.org/W1845972764","https://openalex.org/W2101075098","https://openalex.org/W2118556122","https://openalex.org/W2121863487","https://openalex.org/W2145339207","https://openalex.org/W2151237105","https://openalex.org/W2164479831","https://openalex.org/W2555811267","https://openalex.org/W2586680856","https://openalex.org/W2618318883","https://openalex.org/W2730929966","https://openalex.org/W2766447205","https://openalex.org/W2808709600","https://openalex.org/W2900582619","https://openalex.org/W2911305319","https://openalex.org/W2921639061","https://openalex.org/W2962736495","https://openalex.org/W2962901215","https://openalex.org/W2963780574","https://openalex.org/W2964340170","https://openalex.org/W3104013016","https://openalex.org/W3106238320","https://openalex.org/W4214717370","https://openalex.org/W4285719527","https://openalex.org/W4294555834","https://openalex.org/W4294562617","https://openalex.org/W4297780563","https://openalex.org/W6634413486","https://openalex.org/W6682330108","https://openalex.org/W6682367392","https://openalex.org/W6684037837","https://openalex.org/W6738483526","https://openalex.org/W6746595151","https://openalex.org/W6751535212","https://openalex.org/W6758165564","https://openalex.org/W6760729737"],"related_works":["https://openalex.org/W2383111961","https://openalex.org/W2365952365","https://openalex.org/W2352448290","https://openalex.org/W2380820513","https://openalex.org/W2913146933","https://openalex.org/W2372385138","https://openalex.org/W4296359239","https://openalex.org/W2101155126","https://openalex.org/W2043093291","https://openalex.org/W2363545964"],"abstract_inverted_index":{"Real-world":[0],"robots":[1],"have":[2],"complex":[3],"strict":[4],"constraints.":[5],"Therefore,":[6],"safe":[7,59],"reinforcement":[8,60],"learning":[9],"algorithms":[10,29],"that":[11,31],"can":[12,32],"simultaneously":[13],"minimize":[14,74],"the":[15,19,38,91,94,98,108],"total":[16,75],"cost":[17,76],"and":[18,57,68,77,83,110],"risk":[20,78],"of":[21,40,79,101,113],"constraint":[22,80],"violation":[23,81],"are":[24,71],"crucial.":[25],"However,":[26],"almost":[27],"no":[28],"exist":[30],"scale":[33],"to":[34,37,73,127],"high-dimensional":[35],"systems":[36],"best":[39],"our":[41],"knowledge.":[42],"In":[43],"this":[44],"paper,":[45],"we":[46],"propose":[47],"Dynamic":[48,102],"Actor-Advisor":[49],"Programming":[50,104],"(DAAP),":[51],"as":[52,93],"an":[53],"algorithm":[54],"for":[55],"sample-efficient":[56],"scalable":[58],"learning.":[61],"DAAP":[62,114],"employs":[63],"two":[64],"control":[65,122],"policies,":[66],"actor":[67],"advisor.":[69],"They":[70],"updated":[72],"intertwiningly":[82],"smoothly":[84],"towards":[85],"each":[86],"other's":[87],"direction":[88],"by":[89],"using":[90],"other":[92],"baseline":[95],"policy":[96],"in":[97],"Kullback-Leibler":[99],"divergence":[100],"Policy":[103],"framework.":[105],"We":[106],"demonstrate":[107],"scalability":[109],"sample":[111],"efficiency":[112],"through":[115],"its":[116],"application":[117],"on":[118],"simulated":[119],"robot":[120],"arm":[121],"tasks":[123],"with":[124],"performance":[125],"comparisons":[126],"baselines.":[128]},"counts_by_year":[{"year":2024,"cited_by_count":1},{"year":2023,"cited_by_count":2},{"year":2022,"cited_by_count":2},{"year":2021,"cited_by_count":1}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}