{"id":"https://openalex.org/W3201820699","doi":"https://doi.org/10.1109/tpami.2022.3215769","title":"Continuous-Time Fitted Value Iteration for Robust Policies","display_name":"Continuous-Time Fitted Value Iteration for Robust Policies","publication_year":2022,"publication_date":"2022-01-01","ids":{"openalex":"https://openalex.org/W3201820699","doi":"https://doi.org/10.1109/tpami.2022.3215769","mag":"3201820699"},"language":"en","primary_location":{"id":"doi:10.1109/tpami.2022.3215769","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tpami.2022.3215769","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"],"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/A5042151011","display_name":"Michael Lutter","orcid":"https://orcid.org/0000-0002-9019-6769"},"institutions":[{"id":"https://openalex.org/I31512782","display_name":"Technical University of Darmstadt","ror":"https://ror.org/05n911h24","country_code":"DE","type":"education","lineage":["https://openalex.org/I31512782"]}],"countries":["DE"],"is_corresponding":true,"raw_author_name":"Michael Lutter","raw_affiliation_strings":["Intelligent Autonomous Systems group with the Computer Science Department, Technical University of Darmstadt, Darmstadt, Germany"],"affiliations":[{"raw_affiliation_string":"Intelligent Autonomous Systems group with the Computer Science Department, Technical University of Darmstadt, Darmstadt, Germany","institution_ids":["https://openalex.org/I31512782"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5088706700","display_name":"Boris Belousov","orcid":"https://orcid.org/0000-0001-7172-9104"},"institutions":[{"id":"https://openalex.org/I31512782","display_name":"Technical University of Darmstadt","ror":"https://ror.org/05n911h24","country_code":"DE","type":"education","lineage":["https://openalex.org/I31512782"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Boris Belousov","raw_affiliation_strings":["Intelligent Autonomous Systems group with the Computer Science Department, Technical University of Darmstadt, Darmstadt, Germany"],"affiliations":[{"raw_affiliation_string":"Intelligent Autonomous Systems group with the Computer Science Department, Technical University of Darmstadt, Darmstadt, Germany","institution_ids":["https://openalex.org/I31512782"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5036260775","display_name":"Shie Mannor","orcid":"https://orcid.org/0000-0003-4439-7647"},"institutions":[{"id":"https://openalex.org/I174306211","display_name":"Technion \u2013 Israel Institute of Technology","ror":"https://ror.org/03qryx823","country_code":"IL","type":"education","lineage":["https://openalex.org/I174306211"]}],"countries":["IL"],"is_corresponding":false,"raw_author_name":"Shie Mannor","raw_affiliation_strings":["The Andrew and Erna Viterbi Faculty of Electrical &amp; Computer Engineering, Technion-Israel Institute of Technology and a Distinguished Scientist at NVIDIA, Tel Aviv, Israel"],"affiliations":[{"raw_affiliation_string":"The Andrew and Erna Viterbi Faculty of Electrical &amp; Computer Engineering, Technion-Israel Institute of Technology and a Distinguished Scientist at NVIDIA, Tel Aviv, Israel","institution_ids":["https://openalex.org/I174306211"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5108257764","display_name":"Dieter Fox","orcid":"https://orcid.org/0009-0009-4694-9127"},"institutions":[{"id":"https://openalex.org/I201448701","display_name":"University of Washington","ror":"https://ror.org/00cvxb145","country_code":"US","type":"education","lineage":["https://openalex.org/I201448701"]},{"id":"https://openalex.org/I4210116723","display_name":"Robotics Research (United States)","ror":"https://ror.org/020w2fr77","country_code":"US","type":"company","lineage":["https://openalex.org/I4210116723"]},{"id":"https://openalex.org/I4210127875","display_name":"Nvidia (United States)","ror":"https://ror.org/03jdj4y14","country_code":"US","type":"company","lineage":["https://openalex.org/I4210127875"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Dieter Fox","raw_affiliation_strings":["Allen School of Computer Science &amp; Engineering, University of Washington and Senior Director of Robotics Research at NVIDIA, Seattle, WA, USA"],"affiliations":[{"raw_affiliation_string":"Allen School of Computer Science &amp; Engineering, University of Washington and Senior Director of Robotics Research at NVIDIA, Seattle, WA, USA","institution_ids":["https://openalex.org/I4210127875","https://openalex.org/I4210116723","https://openalex.org/I201448701"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5061193324","display_name":"Animesh Garg","orcid":"https://orcid.org/0000-0003-0482-4296"},"institutions":[{"id":"https://openalex.org/I4210127509","display_name":"Vector Institute","ror":"https://ror.org/03kqdja62","country_code":"CA","type":"facility","lineage":["https://openalex.org/I4210127509"]},{"id":"https://openalex.org/I185261750","display_name":"University of Toronto","ror":"https://ror.org/03dbr7087","country_code":"CA","type":"education","lineage":["https://openalex.org/I185261750"]}],"countries":["CA"],"is_corresponding":false,"raw_author_name":"Animesh Garg","raw_affiliation_strings":["Computer Science Department, University of Toronto, Member of the Vector Institute and Senior Scientist at NVIDIA, Toronto, Canada"],"affiliations":[{"raw_affiliation_string":"Computer Science Department, University of Toronto, Member of the Vector Institute and Senior Scientist at NVIDIA, Toronto, Canada","institution_ids":["https://openalex.org/I4210127509","https://openalex.org/I185261750"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5071367253","display_name":"Jan Peters","orcid":"https://orcid.org/0000-0002-5266-8091"},"institutions":[{"id":"https://openalex.org/I31512782","display_name":"Technical University of Darmstadt","ror":"https://ror.org/05n911h24","country_code":"DE","type":"education","lineage":["https://openalex.org/I31512782"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Jan Peters","raw_affiliation_strings":["Intelligent Autonomous Systems group with the Computer Science Department, Technical University of Darmstadt, Darmstadt, Germany"],"affiliations":[{"raw_affiliation_string":"Intelligent Autonomous Systems group with the Computer Science Department, Technical University of Darmstadt, Darmstadt, Germany","institution_ids":["https://openalex.org/I31512782"]}]}],"institutions":[],"countries_distinct_count":4,"institutions_distinct_count":6,"corresponding_author_ids":["https://openalex.org/A5042151011"],"corresponding_institution_ids":["https://openalex.org/I31512782"],"apc_list":null,"apc_paid":null,"fwci":0.6631,"has_fulltext":false,"cited_by_count":5,"citation_normalized_percentile":{"value":0.72592766,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":96},"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"15"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10462","display_name":"Reinforcement Learning in Robotics","score":0.9993000030517578,"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":0.9993000030517578,"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/T11689","display_name":"Adversarial Robustness in Machine Learning","score":0.9975000023841858,"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/T12794","display_name":"Adaptive Dynamic Programming Control","score":0.9818999767303467,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/bellman-equation","display_name":"Bellman equation","score":0.6441562175750732},{"id":"https://openalex.org/keywords/discretization","display_name":"Discretization","score":0.5739342570304871},{"id":"https://openalex.org/keywords/reinforcement-learning","display_name":"Reinforcement learning","score":0.5300170183181763},{"id":"https://openalex.org/keywords/leverage","display_name":"Leverage (statistics)","score":0.5226159691810608},{"id":"https://openalex.org/keywords/optimal-control","display_name":"Optimal control","score":0.5057017803192139},{"id":"https://openalex.org/keywords/mathematical-optimization","display_name":"Mathematical optimization","score":0.5037140250205994},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.4744371473789215},{"id":"https://openalex.org/keywords/robustness","display_name":"Robustness (evolution)","score":0.45008012652397156},{"id":"https://openalex.org/keywords/dynamic-programming","display_name":"Dynamic programming","score":0.43872013688087463},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.4121451675891876},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.28074002265930176}],"concepts":[{"id":"https://openalex.org/C14646407","wikidata":"https://www.wikidata.org/wiki/Q1430750","display_name":"Bellman equation","level":2,"score":0.6441562175750732},{"id":"https://openalex.org/C73000952","wikidata":"https://www.wikidata.org/wiki/Q17007827","display_name":"Discretization","level":2,"score":0.5739342570304871},{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.5300170183181763},{"id":"https://openalex.org/C153083717","wikidata":"https://www.wikidata.org/wiki/Q6535263","display_name":"Leverage (statistics)","level":2,"score":0.5226159691810608},{"id":"https://openalex.org/C91575142","wikidata":"https://www.wikidata.org/wiki/Q1971426","display_name":"Optimal control","level":2,"score":0.5057017803192139},{"id":"https://openalex.org/C126255220","wikidata":"https://www.wikidata.org/wiki/Q141495","display_name":"Mathematical optimization","level":1,"score":0.5037140250205994},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.4744371473789215},{"id":"https://openalex.org/C63479239","wikidata":"https://www.wikidata.org/wiki/Q7353546","display_name":"Robustness (evolution)","level":3,"score":0.45008012652397156},{"id":"https://openalex.org/C37404715","wikidata":"https://www.wikidata.org/wiki/Q380679","display_name":"Dynamic programming","level":2,"score":0.43872013688087463},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.4121451675891876},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.28074002265930176},{"id":"https://openalex.org/C104317684","wikidata":"https://www.wikidata.org/wiki/Q7187","display_name":"Gene","level":2,"score":0.0},{"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/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","level":0,"score":0.0},{"id":"https://openalex.org/C55493867","wikidata":"https://www.wikidata.org/wiki/Q7094","display_name":"Biochemistry","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/tpami.2022.3215769","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tpami.2022.3215769","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"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":156,"referenced_works":["https://openalex.org/W134786152","https://openalex.org/W166862392","https://openalex.org/W287592399","https://openalex.org/W565431999","https://openalex.org/W580164506","https://openalex.org/W1191599655","https://openalex.org/W1424654272","https://openalex.org/W1515851193","https://openalex.org/W1542941925","https://openalex.org/W1558902221","https://openalex.org/W1574514837","https://openalex.org/W1578936488","https://openalex.org/W1581842928","https://openalex.org/W1589216054","https://openalex.org/W1646707810","https://openalex.org/W1714604093","https://openalex.org/W1892947258","https://openalex.org/W1965878388","https://openalex.org/W1977237536","https://openalex.org/W1980801308","https://openalex.org/W1989855774","https://openalex.org/W1990437501","https://openalex.org/W2009533501","https://openalex.org/W2042882799","https://openalex.org/W2043962331","https://openalex.org/W2103626435","https://openalex.org/W2105078254","https://openalex.org/W2108984317","https://openalex.org/W2113501460","https://openalex.org/W2117355432","https://openalex.org/W2119567691","https://openalex.org/W2120346334","https://openalex.org/W2125074935","https://openalex.org/W2132397872","https://openalex.org/W2145060720","https://openalex.org/W2145339207","https://openalex.org/W2160284799","https://openalex.org/W2167940675","https://openalex.org/W2169982856","https://openalex.org/W2173248099","https://openalex.org/W2197493596","https://openalex.org/W2239929133","https://openalex.org/W2290354866","https://openalex.org/W2296319761","https://openalex.org/W2334782222","https://openalex.org/W2341171179","https://openalex.org/W2343609400","https://openalex.org/W2602963933","https://openalex.org/W2618318883","https://openalex.org/W2736601468","https://openalex.org/W2773525213","https://openalex.org/W2773691349","https://openalex.org/W2781726626","https://openalex.org/W2789824229","https://openalex.org/W2810754397","https://openalex.org/W2810785043","https://openalex.org/W2898758998","https://openalex.org/W2913577890","https://openalex.org/W2914994663","https://openalex.org/W2945924974","https://openalex.org/W2948680363","https://openalex.org/W2950471160","https://openalex.org/W2952337742","https://openalex.org/W2952981100","https://openalex.org/W2962730452","https://openalex.org/W2962896691","https://openalex.org/W2962902376","https://openalex.org/W2963525569","https://openalex.org/W2963684914","https://openalex.org/W2963864421","https://openalex.org/W2963906246","https://openalex.org/W2964040381","https://openalex.org/W2964686099","https://openalex.org/W2968116426","https://openalex.org/W2970362693","https://openalex.org/W2970795963","https://openalex.org/W2970971581","https://openalex.org/W2972586385","https://openalex.org/W2973229164","https://openalex.org/W2975293371","https://openalex.org/W2990747716","https://openalex.org/W2995968686","https://openalex.org/W2996343955","https://openalex.org/W2998544442","https://openalex.org/W2999054007","https://openalex.org/W3004137006","https://openalex.org/W3021796787","https://openalex.org/W3031711947","https://openalex.org/W3035965352","https://openalex.org/W3037024314","https://openalex.org/W3082784051","https://openalex.org/W3096740192","https://openalex.org/W3096954237","https://openalex.org/W3098237412","https://openalex.org/W3099878876","https://openalex.org/W3109395707","https://openalex.org/W3118300017","https://openalex.org/W3123320253","https://openalex.org/W3126300335","https://openalex.org/W3130843035","https://openalex.org/W3131920644","https://openalex.org/W3135581169","https://openalex.org/W3135791089","https://openalex.org/W3160754213","https://openalex.org/W3164428799","https://openalex.org/W3167204845","https://openalex.org/W3173331501","https://openalex.org/W3174652807","https://openalex.org/W3204973825","https://openalex.org/W4210791600","https://openalex.org/W4213251304","https://openalex.org/W4214717370","https://openalex.org/W4240362674","https://openalex.org/W4250589301","https://openalex.org/W4287674453","https://openalex.org/W4289709949","https://openalex.org/W4294555834","https://openalex.org/W4295312788","https://openalex.org/W4300446173","https://openalex.org/W6617021176","https://openalex.org/W6627932998","https://openalex.org/W6637618445","https://openalex.org/W6677549092","https://openalex.org/W6677737365","https://openalex.org/W6678545291","https://openalex.org/W6679802252","https://openalex.org/W6687820959","https://openalex.org/W6696324988","https://openalex.org/W6735677848","https://openalex.org/W6738483526","https://openalex.org/W6741002519","https://openalex.org/W6747027214","https://openalex.org/W6747473740","https://openalex.org/W6748817170","https://openalex.org/W6753243525","https://openalex.org/W6753264383","https://openalex.org/W6753691991","https://openalex.org/W6755890616","https://openalex.org/W6758539823","https://openalex.org/W6758907457","https://openalex.org/W6759312646","https://openalex.org/W6762427411","https://openalex.org/W6763340073","https://openalex.org/W6766978945","https://openalex.org/W6767081328","https://openalex.org/W6767277667","https://openalex.org/W6767539605","https://openalex.org/W6768242542","https://openalex.org/W6771707735","https://openalex.org/W6779733183","https://openalex.org/W6782560877","https://openalex.org/W6784643869","https://openalex.org/W6784829994","https://openalex.org/W6794802532","https://openalex.org/W6929201857","https://openalex.org/W7011603464"],"related_works":["https://openalex.org/W4255265352","https://openalex.org/W4239477580","https://openalex.org/W2386410636","https://openalex.org/W2952594763","https://openalex.org/W3038962357","https://openalex.org/W2025663273","https://openalex.org/W2090698372","https://openalex.org/W4383890581","https://openalex.org/W4285537323","https://openalex.org/W1932159282"],"abstract_inverted_index":{"Solving":[0],"the":[1,25,33,38,46,49,57,61,63,72,93,110,123,132,147,151,164,168,179,187,192,196,199,203,206,224,228,232],"Hamilton-Jacobi-Bellman":[2],"equation":[3,21],"is":[4,28,66,214],"important":[5,29],"in":[6,116,198],"many":[7,104],"domains":[8],"including":[9],"control,":[10,17],"robotics":[11],"and":[12,22,59,84,97,100,113,126,142,171,223],"economics.":[13],"Especially":[14],"for":[15,131,139],"continuous":[16,79,105,140],"solving":[18],"this":[19,75],"differential":[20,124],"its":[23],"extension":[24],"Hamilton-Jacobi-Isaacs":[26,50],"equation,":[27,51],"as":[30,144,146],"it":[31],"yields":[32],"optimal":[34,111,114,133,180],"policy":[35,65,112],"that":[36,175,191,210],"achieves":[37],"maximum":[39],"reward":[40,102],"on":[41,186],"a":[42],"give":[43],"task.":[44],"In":[45,74],"case":[47],"of":[48,71,103,158,205,227,231],"which":[52],"includes":[53],"an":[54],"adversary":[55,115],"controlling":[56],"environment":[58],"minimizing":[60],"reward,":[62],"obtained":[64],"also":[67],"robust":[68,85,211,216],"to":[69,108,129,167,218],"perturbations":[70],"dynamics.":[73],"paper":[76],"we":[77,208],"propose":[78],"fitted":[80,86],"value":[81,87,134,137,212],"iteration":[82,88,138,213],"(cFVI)":[83],"(rFVI).":[89],"These":[90],"algorithms":[91,153,166,177],"leverage":[92],"non-linear":[94],"control-affine":[95],"dynamics":[96],"separable":[98],"state":[99],"action":[101],"control":[106],"problems":[107],"derive":[109],"closed":[117],"form.":[118],"This":[119],"analytic":[120],"expression":[121],"simplifies":[122],"equations":[125],"enables":[127],"us":[128],"solve":[130],"function":[135],"using":[136],"actions":[141],"states":[143,159],"well":[145],"adversarial":[148],"case.":[149],"Notably,":[150],"resulting":[152,165],"do":[154],"not":[155],"require":[156],"discretization":[157],"or":[160],"actions.":[161],"We":[162,173],"apply":[163],"Furuta":[169],"pendulum":[170],"cartpole.":[172],"show":[174,190],"both":[176],"obtain":[178],"policy.":[181],"The":[182],"robustness":[183],"Sim2Real":[184],"experiments":[185,233],"physical":[188],"systems":[189],"policies":[193],"successfully":[194],"achieve":[195],"task":[197],"real-world.":[200],"When":[201],"changing":[202],"masses":[204],"pendulum,":[207],"observe":[209],"more":[215],"compared":[217],"deep":[219],"reinforcement":[220],"learning":[221],"algorithm":[222],"non-robust":[225],"version":[226],"algorithm.":[229],"Videos":[230],"are":[234],"shown":[235],"at":[236],"<uri":[237],"xmlns:mml=\"http://www.w3.org/1998/Math/MathML\"":[238],"xmlns:xlink=\"http://www.w3.org/1999/xlink\">https://sites.google.com/view/rfvi</uri>":[239]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2024,"cited_by_count":2},{"year":2023,"cited_by_count":1},{"year":2022,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2021-10-11T00:00:00"}