{"id":"https://openalex.org/W3152923668","doi":"https://doi.org/10.1109/iros51168.2021.9635984","title":"Safe Continuous Control with Constrained Model-Based Policy Optimization","display_name":"Safe Continuous Control with Constrained Model-Based Policy Optimization","publication_year":2021,"publication_date":"2021-09-27","ids":{"openalex":"https://openalex.org/W3152923668","doi":"https://doi.org/10.1109/iros51168.2021.9635984","mag":"3152923668"},"language":"en","primary_location":{"id":"doi:10.1109/iros51168.2021.9635984","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iros51168.2021.9635984","pdf_url":null,"source":{"id":"https://openalex.org/S4363607734","display_name":"2021 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2021 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS)","raw_type":"proceedings-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/A5070632989","display_name":"Moritz A. Zanger","orcid":null},"institutions":[{"id":"https://openalex.org/I102335020","display_name":"Karlsruhe Institute of Technology","ror":"https://ror.org/04t3en479","country_code":"DE","type":"education","lineage":["https://openalex.org/I102335020","https://openalex.org/I1305996414"]}],"countries":["DE"],"is_corresponding":true,"raw_author_name":"Moritz A. Zanger","raw_affiliation_strings":["Karlsruhe Institute of Technology, Karlsruhe, Germany"],"affiliations":[{"raw_affiliation_string":"Karlsruhe Institute of Technology, Karlsruhe, Germany","institution_ids":["https://openalex.org/I102335020"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5004129561","display_name":"Karam Daaboul","orcid":null},"institutions":[{"id":"https://openalex.org/I102335020","display_name":"Karlsruhe Institute of Technology","ror":"https://ror.org/04t3en479","country_code":"DE","type":"education","lineage":["https://openalex.org/I102335020","https://openalex.org/I1305996414"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Karam Daaboul","raw_affiliation_strings":["Karlsruhe Institute of Technology, Karlsruhe, Germany"],"affiliations":[{"raw_affiliation_string":"Karlsruhe Institute of Technology, Karlsruhe, Germany","institution_ids":["https://openalex.org/I102335020"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5089087383","display_name":"J. Marius Z\u00f6llner","orcid":"https://orcid.org/0000-0002-3889-6629"},"institutions":[{"id":"https://openalex.org/I102335020","display_name":"Karlsruhe Institute of Technology","ror":"https://ror.org/04t3en479","country_code":"DE","type":"education","lineage":["https://openalex.org/I102335020","https://openalex.org/I1305996414"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"J. Marius Zollner","raw_affiliation_strings":["Karlsruhe Institute of Technology, Karlsruhe, Germany"],"affiliations":[{"raw_affiliation_string":"Karlsruhe Institute of Technology, Karlsruhe, Germany","institution_ids":["https://openalex.org/I102335020"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5070632989"],"corresponding_institution_ids":["https://openalex.org/I102335020"],"apc_list":null,"apc_paid":null,"fwci":0.8796,"has_fulltext":false,"cited_by_count":10,"citation_normalized_percentile":{"value":0.76332025,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":97},"biblio":{"volume":null,"issue":null,"first_page":"3512","last_page":"3519"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10462","display_name":"Reinforcement Learning in Robotics","score":0.9994000196456909,"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":0.9994000196456909,"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/T10848","display_name":"Advanced Multi-Objective Optimization Algorithms","score":0.9821000099182129,"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/T10653","display_name":"Robot Manipulation and Learning","score":0.9573000073432922,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6972633600234985},{"id":"https://openalex.org/keywords/reinforcement-learning","display_name":"Reinforcement learning","score":0.6500686407089233},{"id":"https://openalex.org/keywords/mathematical-optimization","display_name":"Mathematical optimization","score":0.633624792098999},{"id":"https://openalex.org/keywords/probabilistic-logic","display_name":"Probabilistic logic","score":0.6206299066543579},{"id":"https://openalex.org/keywords/constraint","display_name":"Constraint (computer-aided design)","score":0.5421749949455261},{"id":"https://openalex.org/keywords/maximization","display_name":"Maximization","score":0.532965898513794},{"id":"https://openalex.org/keywords/divergence","display_name":"Divergence (linguistics)","score":0.49504151940345764},{"id":"https://openalex.org/keywords/resampling","display_name":"Resampling","score":0.4433210492134094},{"id":"https://openalex.org/keywords/reduction","display_name":"Reduction (mathematics)","score":0.4375861883163452},{"id":"https://openalex.org/keywords/constraint-satisfaction","display_name":"Constraint satisfaction","score":0.41923320293426514},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.2783554196357727},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.14982619881629944}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6972633600234985},{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.6500686407089233},{"id":"https://openalex.org/C126255220","wikidata":"https://www.wikidata.org/wiki/Q141495","display_name":"Mathematical optimization","level":1,"score":0.633624792098999},{"id":"https://openalex.org/C49937458","wikidata":"https://www.wikidata.org/wiki/Q2599292","display_name":"Probabilistic logic","level":2,"score":0.6206299066543579},{"id":"https://openalex.org/C2776036281","wikidata":"https://www.wikidata.org/wiki/Q48769818","display_name":"Constraint (computer-aided design)","level":2,"score":0.5421749949455261},{"id":"https://openalex.org/C2776330181","wikidata":"https://www.wikidata.org/wiki/Q18358244","display_name":"Maximization","level":2,"score":0.532965898513794},{"id":"https://openalex.org/C207390915","wikidata":"https://www.wikidata.org/wiki/Q1230525","display_name":"Divergence (linguistics)","level":2,"score":0.49504151940345764},{"id":"https://openalex.org/C150921843","wikidata":"https://www.wikidata.org/wiki/Q1170431","display_name":"Resampling","level":2,"score":0.4433210492134094},{"id":"https://openalex.org/C111335779","wikidata":"https://www.wikidata.org/wiki/Q3454686","display_name":"Reduction (mathematics)","level":2,"score":0.4375861883163452},{"id":"https://openalex.org/C44616089","wikidata":"https://www.wikidata.org/wiki/Q30158686","display_name":"Constraint satisfaction","level":3,"score":0.41923320293426514},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.2783554196357727},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.14982619881629944},{"id":"https://openalex.org/C2524010","wikidata":"https://www.wikidata.org/wiki/Q8087","display_name":"Geometry","level":1,"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/iros51168.2021.9635984","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iros51168.2021.9635984","pdf_url":null,"source":{"id":"https://openalex.org/S4363607734","display_name":"2021 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2021 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS)","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":0.6600000262260437}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":59,"referenced_works":["https://openalex.org/W1191599655","https://openalex.org/W1518931405","https://openalex.org/W1575592356","https://openalex.org/W1771410628","https://openalex.org/W1845972764","https://openalex.org/W2006859604","https://openalex.org/W2155511972","https://openalex.org/W2158782408","https://openalex.org/W2164479831","https://openalex.org/W2236244207","https://openalex.org/W2596214870","https://openalex.org/W2618318883","https://openalex.org/W2781726626","https://openalex.org/W2784465508","https://openalex.org/W2785389871","https://openalex.org/W2787938642","https://openalex.org/W2791704483","https://openalex.org/W2902098903","https://openalex.org/W2952720101","https://openalex.org/W2954115742","https://openalex.org/W2962803570","https://openalex.org/W2962902376","https://openalex.org/W2963082979","https://openalex.org/W2963238274","https://openalex.org/W2963923407","https://openalex.org/W2963960193","https://openalex.org/W2964340170","https://openalex.org/W2970277495","https://openalex.org/W2973525135","https://openalex.org/W2990747716","https://openalex.org/W2994712737","https://openalex.org/W2995520132","https://openalex.org/W3092461179","https://openalex.org/W3162902207","https://openalex.org/W4288319859","https://openalex.org/W4293545785","https://openalex.org/W4294555834","https://openalex.org/W4294562617","https://openalex.org/W4297780563","https://openalex.org/W4298206671","https://openalex.org/W6627932998","https://openalex.org/W6634413486","https://openalex.org/W6638018090","https://openalex.org/W6682367392","https://openalex.org/W6684037837","https://openalex.org/W6687063787","https://openalex.org/W6730042731","https://openalex.org/W6737893269","https://openalex.org/W6738483526","https://openalex.org/W6747473740","https://openalex.org/W6747790125","https://openalex.org/W6748519856","https://openalex.org/W6748839928","https://openalex.org/W6749363318","https://openalex.org/W6751494529","https://openalex.org/W6751535212","https://openalex.org/W6764053384","https://openalex.org/W6767919266","https://openalex.org/W6771280675"],"related_works":["https://openalex.org/W2052515325","https://openalex.org/W2050948537","https://openalex.org/W2767646790","https://openalex.org/W2352041579","https://openalex.org/W1488006380","https://openalex.org/W2138381686","https://openalex.org/W1998176685","https://openalex.org/W2141585124","https://openalex.org/W2032175896","https://openalex.org/W3123883311"],"abstract_inverted_index":{"The":[0,107],"applicability":[1],"of":[2,25,43,73,88,112,137,140,190,199],"reinforcement":[3],"learning":[4],"(RL)":[5],"algorithms":[6],"in":[7,50,118,149],"real-world":[8],"domains":[9],"often":[10,68],"requires":[11],"adherence":[12],"to":[13,19,33,65],"safety":[14,47],"constraints,":[15],"a":[16,56,97,113,186],"need":[17,108],"difficult":[18],"address":[20,66,124],"given":[21],"the":[22,26,34,41,67,86,131],"asymptotic":[23],"nature":[24],"classic":[27],"RL":[28,36],"optimization":[29,93],"objective.":[30],"In":[31],"contrast":[32],"traditional":[35],"objective,":[37],"safe":[38,58,75],"exploration":[39,59,76],"considers":[40],"maximization":[42],"expected":[44,51,132],"returns":[45],"under":[46],"constraints":[48],"expressed":[49],"cost":[52],"returns.":[53],"We":[54,123,159],"introduce":[55,96],"model-based":[57],"algorithm":[60,99,181],"for":[61,109],"constrained":[62,91,166],"high-dimensional":[63,171],"control":[64],"prohibitively":[69],"high":[70],"sample":[71],"complexity":[72],"model-free":[74,183,200],"algorithms.":[77],"Further,":[78],"we":[79],"provide":[80],"theoretical":[81],"and":[82,95,144,154,173],"empirical":[83,176],"analyses":[84],"regarding":[85],"implications":[87],"model-usage":[89],"on":[90,163],"policy":[92,102],"problems":[94],"practical":[98],"that":[100,179],"accelerates":[101],"search":[103],"with":[104,120,170,185],"model-generated":[105],"data.":[106],"accurate":[110],"estimates":[111],"policy\u2019s":[114],"constraint":[115,196],"satisfaction":[116,197],"is":[117],"conflict":[119],"accumulating":[121],"model-errors.":[122],"this":[125,146,161],"issue":[126],"by":[127],"quantifying":[128],"model-uncertainty":[129],"as":[130],"Kullback-Leibler":[133],"divergence":[134],"between":[135],"predictions":[136],"an":[138,150],"ensemble":[139],"probabilistic":[141],"dynamics":[142],"models":[143],"constrain":[145],"error-measure,":[147],"resulting":[148],"adaptive":[151],"resampling":[152],"scheme":[153],"dynamically":[155],"limited":[156],"rollout":[157],"horizons.":[158],"evaluate":[160],"approach":[162],"several":[164],"simulated":[165],"robot":[167],"locomotion":[168],"tasks":[169],"action-":[172],"state-spaces.":[174],"Our":[175],"studies":[177],"find":[178],"our":[180],"reaches":[182],"performances":[184],"10-20":[187],"fold":[188],"reduction":[189],"training":[191],"samples":[192],"while":[193],"maintaining":[194],"approximate":[195],"levels":[198],"methods.":[201]},"counts_by_year":[{"year":2025,"cited_by_count":3},{"year":2024,"cited_by_count":2},{"year":2023,"cited_by_count":4},{"year":2021,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}