{"id":"https://openalex.org/W2968547875","doi":"https://doi.org/10.1109/icra.2019.8794107","title":"Bridging Hamilton-Jacobi Safety Analysis and Reinforcement Learning","display_name":"Bridging Hamilton-Jacobi Safety Analysis and Reinforcement Learning","publication_year":2019,"publication_date":"2019-05-01","ids":{"openalex":"https://openalex.org/W2968547875","doi":"https://doi.org/10.1109/icra.2019.8794107","mag":"2968547875"},"language":"en","primary_location":{"id":"doi:10.1109/icra.2019.8794107","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icra.2019.8794107","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2019 International Conference on Robotics and Automation (ICRA)","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/A5050710435","display_name":"Jaime F. Fisac","orcid":"https://orcid.org/0000-0002-2676-5090"},"institutions":[{"id":"https://openalex.org/I95457486","display_name":"University of California, Berkeley","ror":"https://ror.org/01an7q238","country_code":"US","type":"education","lineage":["https://openalex.org/I95457486"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Jaime F. Fisac","raw_affiliation_strings":["Department of Electrical Engineering and Computer Sciences, University of California, Berkeley"],"affiliations":[{"raw_affiliation_string":"Department of Electrical Engineering and Computer Sciences, University of California, Berkeley","institution_ids":["https://openalex.org/I95457486"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5012329527","display_name":"Neil F. Lugovoy","orcid":null},"institutions":[{"id":"https://openalex.org/I95457486","display_name":"University of California, Berkeley","ror":"https://ror.org/01an7q238","country_code":"US","type":"education","lineage":["https://openalex.org/I95457486"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Neil F. Lugovoy","raw_affiliation_strings":["Department of Electrical Engineering and Computer Sciences, University of California, Berkeley"],"affiliations":[{"raw_affiliation_string":"Department of Electrical Engineering and Computer Sciences, University of California, Berkeley","institution_ids":["https://openalex.org/I95457486"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5009308827","display_name":"Vicen\u00e7 Rubies-Royo","orcid":"https://orcid.org/0000-0002-8814-0248"},"institutions":[{"id":"https://openalex.org/I95457486","display_name":"University of California, Berkeley","ror":"https://ror.org/01an7q238","country_code":"US","type":"education","lineage":["https://openalex.org/I95457486"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Vicenc Rubies-Royo","raw_affiliation_strings":["Department of Electrical Engineering and Computer Sciences, University of California, Berkeley"],"affiliations":[{"raw_affiliation_string":"Department of Electrical Engineering and Computer Sciences, University of California, Berkeley","institution_ids":["https://openalex.org/I95457486"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101510201","display_name":"Shromona Ghosh","orcid":null},"institutions":[{"id":"https://openalex.org/I95457486","display_name":"University of California, Berkeley","ror":"https://ror.org/01an7q238","country_code":"US","type":"education","lineage":["https://openalex.org/I95457486"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Shromona Ghosh","raw_affiliation_strings":["Department of Electrical Engineering and Computer Sciences, University of California, Berkeley"],"affiliations":[{"raw_affiliation_string":"Department of Electrical Engineering and Computer Sciences, University of California, Berkeley","institution_ids":["https://openalex.org/I95457486"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5045155646","display_name":"Claire J. Tomlin","orcid":"https://orcid.org/0000-0003-3192-3185"},"institutions":[{"id":"https://openalex.org/I95457486","display_name":"University of California, Berkeley","ror":"https://ror.org/01an7q238","country_code":"US","type":"education","lineage":["https://openalex.org/I95457486"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Claire J. Tomlin","raw_affiliation_strings":["Department of Electrical Engineering and Computer Sciences, University of California, Berkeley"],"affiliations":[{"raw_affiliation_string":"Department of Electrical Engineering and Computer Sciences, University of California, Berkeley","institution_ids":["https://openalex.org/I95457486"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":5,"corresponding_author_ids":["https://openalex.org/A5050710435"],"corresponding_institution_ids":["https://openalex.org/I95457486"],"apc_list":null,"apc_paid":null,"fwci":4.6205,"has_fulltext":false,"cited_by_count":85,"citation_normalized_percentile":{"value":0.95844671,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":96,"max":100},"biblio":{"volume":null,"issue":null,"first_page":"8550","last_page":"8556"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11689","display_name":"Adversarial Robustness in Machine Learning","score":0.9980999827384949,"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/T11689","display_name":"Adversarial Robustness in Machine Learning","score":0.9980999827384949,"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/T10462","display_name":"Reinforcement Learning in Robotics","score":0.9904999732971191,"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/T10409","display_name":"Fuel Cells and Related Materials","score":0.9599999785423279,"subfield":{"id":"https://openalex.org/subfields/2208","display_name":"Electrical and Electronic 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/reinforcement-learning","display_name":"Reinforcement learning","score":0.8554048538208008},{"id":"https://openalex.org/keywords/correctness","display_name":"Correctness","score":0.6415829062461853},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.640198826789856},{"id":"https://openalex.org/keywords/reachability","display_name":"Reachability","score":0.601359486579895},{"id":"https://openalex.org/keywords/stochastic-game","display_name":"Stochastic game","score":0.5356167554855347},{"id":"https://openalex.org/keywords/scalability","display_name":"Scalability","score":0.48696884512901306},{"id":"https://openalex.org/keywords/dynamic-programming","display_name":"Dynamic programming","score":0.4388042092323303},{"id":"https://openalex.org/keywords/bellman-equation","display_name":"Bellman equation","score":0.42996945977211},{"id":"https://openalex.org/keywords/mathematical-optimization","display_name":"Mathematical optimization","score":0.41066810488700867},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.38997435569763184},{"id":"https://openalex.org/keywords/theoretical-computer-science","display_name":"Theoretical computer science","score":0.31191256642341614},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.2002621293067932},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.14902332425117493}],"concepts":[{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.8554048538208008},{"id":"https://openalex.org/C55439883","wikidata":"https://www.wikidata.org/wiki/Q360812","display_name":"Correctness","level":2,"score":0.6415829062461853},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.640198826789856},{"id":"https://openalex.org/C136643341","wikidata":"https://www.wikidata.org/wiki/Q1361526","display_name":"Reachability","level":2,"score":0.601359486579895},{"id":"https://openalex.org/C22171661","wikidata":"https://www.wikidata.org/wiki/Q1074380","display_name":"Stochastic game","level":2,"score":0.5356167554855347},{"id":"https://openalex.org/C48044578","wikidata":"https://www.wikidata.org/wiki/Q727490","display_name":"Scalability","level":2,"score":0.48696884512901306},{"id":"https://openalex.org/C37404715","wikidata":"https://www.wikidata.org/wiki/Q380679","display_name":"Dynamic programming","level":2,"score":0.4388042092323303},{"id":"https://openalex.org/C14646407","wikidata":"https://www.wikidata.org/wiki/Q1430750","display_name":"Bellman equation","level":2,"score":0.42996945977211},{"id":"https://openalex.org/C126255220","wikidata":"https://www.wikidata.org/wiki/Q141495","display_name":"Mathematical optimization","level":1,"score":0.41066810488700867},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.38997435569763184},{"id":"https://openalex.org/C80444323","wikidata":"https://www.wikidata.org/wiki/Q2878974","display_name":"Theoretical computer science","level":1,"score":0.31191256642341614},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.2002621293067932},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.14902332425117493},{"id":"https://openalex.org/C77088390","wikidata":"https://www.wikidata.org/wiki/Q8513","display_name":"Database","level":1,"score":0.0},{"id":"https://openalex.org/C144237770","wikidata":"https://www.wikidata.org/wiki/Q747534","display_name":"Mathematical economics","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icra.2019.8794107","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icra.2019.8794107","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2019 International Conference on Robotics and Automation (ICRA)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":53,"referenced_works":["https://openalex.org/W32403112","https://openalex.org/W1582899597","https://openalex.org/W1771410628","https://openalex.org/W1796544916","https://openalex.org/W1963790880","https://openalex.org/W1975236902","https://openalex.org/W2053572490","https://openalex.org/W2059435624","https://openalex.org/W2067265108","https://openalex.org/W2080813827","https://openalex.org/W2090501324","https://openalex.org/W2100677568","https://openalex.org/W2116364955","https://openalex.org/W2119717200","https://openalex.org/W2121863487","https://openalex.org/W2145339207","https://openalex.org/W2147750403","https://openalex.org/W2151237105","https://openalex.org/W2155007355","https://openalex.org/W2158782408","https://openalex.org/W2298163601","https://openalex.org/W2298907094","https://openalex.org/W2594877703","https://openalex.org/W2726187156","https://openalex.org/W2781726626","https://openalex.org/W2800797998","https://openalex.org/W2891413349","https://openalex.org/W2962803570","https://openalex.org/W2963395620","https://openalex.org/W2963525569","https://openalex.org/W2964161785","https://openalex.org/W2968646325","https://openalex.org/W3037207827","https://openalex.org/W3041202696","https://openalex.org/W3098713169","https://openalex.org/W3104543508","https://openalex.org/W3105818906","https://openalex.org/W4214717370","https://openalex.org/W4233696721","https://openalex.org/W4293545785","https://openalex.org/W4297780563","https://openalex.org/W4387904839","https://openalex.org/W6638018090","https://openalex.org/W6644075784","https://openalex.org/W6681861716","https://openalex.org/W6682367392","https://openalex.org/W6682849425","https://openalex.org/W6737214707","https://openalex.org/W6737893269","https://openalex.org/W6740222838","https://openalex.org/W6747473740","https://openalex.org/W6755257367","https://openalex.org/W6780559895"],"related_works":["https://openalex.org/W4255265352","https://openalex.org/W4239477580","https://openalex.org/W2386410636","https://openalex.org/W2952594763","https://openalex.org/W4285537323","https://openalex.org/W3038962357","https://openalex.org/W2025663273","https://openalex.org/W1932159282","https://openalex.org/W2090698372","https://openalex.org/W4383890581"],"abstract_inverted_index":{"Safety":[0],"analysis":[1,153,175],"is":[2],"a":[3,27,108,126,133,140,167],"necessary":[4],"component":[5],"in":[6,77,86],"the":[7,37,112,116,158,177,183],"design":[8],"and":[9,79,161,176,197,200,208,223],"deployment":[10],"of":[11,30,40,111,114,170,185,214],"autonomous":[12],"robotic":[13],"systems.":[14],"Techniques":[15],"from":[16],"robust":[17],"optimal":[18,74,162],"control":[19,75,209],"theory,":[20],"such":[21],"as":[22,32,154],"Hamilton-Jacobi":[23],"reachability":[24],"analysis,":[25,124],"allow":[26],"rigorous":[28],"formalization":[29],"safety":[31,123,152,163,174,190],"guaranteed":[33],"constraint":[34],"satisfaction.":[35],"Unfortunately,":[36],"computational":[38],"complexity":[39],"these":[41],"tools":[42,54,155],"for":[43,99,211],"general":[44],"dynamical":[45],"systems":[46,213],"scales":[47],"poorly":[48],"with":[49,92],"state":[50,218],"dimension,":[51],"making":[52],"existing":[53],"impractical":[55],"beyond":[56],"small":[57],"problems.":[58],"Modern":[59],"reinforcement":[60,146,178],"learning":[61,147,179,205,222],"methods":[62],"have":[63],"shown":[64],"promising":[65],"ability":[66],"to":[67,73,90,122,150,156,195,216],"find":[68],"approximate":[69,157],"yet":[70],"proficient":[71],"solutions":[72],"problems":[76,91],"complex":[78],"high-dimensional":[80],"systems,":[81],"however":[82],"their":[83],"application":[84],"has":[85],"practice":[87],"been":[88],"restricted":[89],"an":[93],"additive":[94],"payoff":[95,118],"over":[96,119],"time,":[97,120],"unsuitable":[98],"reasoning":[100],"about":[101],"safety.":[102],"In":[103],"recent":[104],"work,":[105],"we":[106,137],"introduced":[107],"time-discounted":[109],"modification":[110],"problem":[113],"maximizing":[115],"minimum":[117],"central":[121],"through":[125,193],"modified":[127],"dynamic":[128],"programming":[129],"equation":[130],"that":[131],"induces":[132],"contraction":[134,142],"mapping.":[135],"Here,":[136],"show":[138],"how":[139],"similar":[141],"mapping":[143],"can":[144],"render":[145],"techniques":[148],"amenable":[149],"quantitative":[151],"safe":[159,206],"set":[160],"policy.":[164],"This":[165],"opens":[166],"new":[168],"avenue":[169],"research":[171],"connecting":[172],"control-theoretic":[173],"domain.":[180],"We":[181],"validate":[182],"correctness":[184],"our":[186],"formulation":[187],"by":[188,204],"comparing":[189],"results":[191],"computed":[192],"Q-learning":[194],"analytic":[196],"numerical":[198],"solutions,":[199],"demonstrate":[201],"its":[202],"scalability":[203],"sets":[207],"policies":[210],"simulated":[212],"up":[215],"18":[217],"dimensions":[219],"using":[220],"value":[221],"policy":[224],"gradient":[225],"techniques.":[226]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":16},{"year":2024,"cited_by_count":16},{"year":2023,"cited_by_count":19},{"year":2022,"cited_by_count":7},{"year":2021,"cited_by_count":16},{"year":2020,"cited_by_count":7},{"year":2019,"cited_by_count":3}],"updated_date":"2026-01-14T23:40:02.550235","created_date":"2025-10-10T00:00:00"}