{"id":"https://openalex.org/W4312597946","doi":"https://doi.org/10.1109/iros47612.2022.9981867","title":"Scalable Safety-Critical Policy Evaluation with Accelerated Rare Event Sampling","display_name":"Scalable Safety-Critical Policy Evaluation with Accelerated Rare Event Sampling","publication_year":2022,"publication_date":"2022-10-23","ids":{"openalex":"https://openalex.org/W4312597946","doi":"https://doi.org/10.1109/iros47612.2022.9981867"},"language":"en","primary_location":{"id":"doi:10.1109/iros47612.2022.9981867","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iros47612.2022.9981867","pdf_url":null,"source":{"id":"https://openalex.org/S4363607704","display_name":"2022 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":"2022 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/A5102020639","display_name":"Mengdi Xu","orcid":"https://orcid.org/0000-0001-6087-7558"},"institutions":[{"id":"https://openalex.org/I74973139","display_name":"Carnegie Mellon University","ror":"https://ror.org/05x2bcf33","country_code":"US","type":"education","lineage":["https://openalex.org/I74973139"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Mengdi Xu","raw_affiliation_strings":["Carnegie Mellon University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Carnegie Mellon University","institution_ids":["https://openalex.org/I74973139"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5010028058","display_name":"Peide Huang","orcid":"https://orcid.org/0000-0002-1048-8690"},"institutions":[{"id":"https://openalex.org/I74973139","display_name":"Carnegie Mellon University","ror":"https://ror.org/05x2bcf33","country_code":"US","type":"education","lineage":["https://openalex.org/I74973139"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Peide Huang","raw_affiliation_strings":["Carnegie Mellon University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Carnegie Mellon University","institution_ids":["https://openalex.org/I74973139"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5015581947","display_name":"Fengpei Li","orcid":"https://orcid.org/0000-0003-0904-4723"},"institutions":[{"id":"https://openalex.org/I2802755631","display_name":"Morgan Stanley (United States)","ror":"https://ror.org/00aphdz18","country_code":"US","type":"company","lineage":["https://openalex.org/I2802755631"]},{"id":"https://openalex.org/I78577930","display_name":"Columbia University","ror":"https://ror.org/00hj8s172","country_code":"US","type":"education","lineage":["https://openalex.org/I78577930"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Fengpei Li","raw_affiliation_strings":["Columbia University","Morgan Stanley Machine Learning Research"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Columbia University","institution_ids":["https://openalex.org/I78577930"]},{"raw_affiliation_string":"Morgan Stanley Machine Learning Research","institution_ids":["https://openalex.org/I2802755631"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5026307285","display_name":"Jiacheng Zhu","orcid":"https://orcid.org/0000-0001-9707-7503"},"institutions":[{"id":"https://openalex.org/I74973139","display_name":"Carnegie Mellon University","ror":"https://ror.org/05x2bcf33","country_code":"US","type":"education","lineage":["https://openalex.org/I74973139"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Jiacheng Zhu","raw_affiliation_strings":["Carnegie Mellon University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Carnegie Mellon University","institution_ids":["https://openalex.org/I74973139"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5049539929","display_name":"Xuewei Qi","orcid":"https://orcid.org/0000-0002-7695-2281"},"institutions":[{"id":"https://openalex.org/I1293612202","display_name":"Toyota Motor Corporation (Switzerland)","ror":"https://ror.org/05p0pbv75","country_code":"CH","type":"company","lineage":["https://openalex.org/I1293612202","https://openalex.org/I4210125472","https://openalex.org/I4210137853"]}],"countries":["CH"],"is_corresponding":false,"raw_author_name":"Xuewei Qi","raw_affiliation_strings":["Toyota Motor North America R&D"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Toyota Motor North America R&D","institution_ids":["https://openalex.org/I1293612202"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5025075066","display_name":"Kentaro Oguchi","orcid":"https://orcid.org/0000-0001-9724-6434"},"institutions":[{"id":"https://openalex.org/I1293612202","display_name":"Toyota Motor Corporation (Switzerland)","ror":"https://ror.org/05p0pbv75","country_code":"CH","type":"company","lineage":["https://openalex.org/I1293612202","https://openalex.org/I4210125472","https://openalex.org/I4210137853"]}],"countries":["CH"],"is_corresponding":false,"raw_author_name":"Kentaro Oguchi","raw_affiliation_strings":["Toyota Motor North America R&D"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Toyota Motor North America R&D","institution_ids":["https://openalex.org/I1293612202"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101445344","display_name":"Zhiyuan Huang","orcid":"https://orcid.org/0000-0003-1284-2128"},"institutions":[{"id":"https://openalex.org/I116953780","display_name":"Tongji University","ror":"https://ror.org/03rc6as71","country_code":"CN","type":"education","lineage":["https://openalex.org/I116953780"]},{"id":"https://openalex.org/I74973139","display_name":"Carnegie Mellon University","ror":"https://ror.org/05x2bcf33","country_code":"US","type":"education","lineage":["https://openalex.org/I74973139"]}],"countries":["CN","US"],"is_corresponding":false,"raw_author_name":"Zhiyuan Huang","raw_affiliation_strings":["Carnegie Mellon University","Tongji University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Carnegie Mellon University","institution_ids":["https://openalex.org/I74973139"]},{"raw_affiliation_string":"Tongji University","institution_ids":["https://openalex.org/I116953780"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5086653913","display_name":"Henry Lam","orcid":null},"institutions":[{"id":"https://openalex.org/I78577930","display_name":"Columbia University","ror":"https://ror.org/00hj8s172","country_code":"US","type":"education","lineage":["https://openalex.org/I78577930"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Henry Lam","raw_affiliation_strings":["Columbia University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Columbia University","institution_ids":["https://openalex.org/I78577930"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5037644321","display_name":"Ding Zhao","orcid":"https://orcid.org/0000-0002-9400-8446"},"institutions":[{"id":"https://openalex.org/I74973139","display_name":"Carnegie Mellon University","ror":"https://ror.org/05x2bcf33","country_code":"US","type":"education","lineage":["https://openalex.org/I74973139"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Ding Zhao","raw_affiliation_strings":["Carnegie Mellon University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Carnegie Mellon University","institution_ids":["https://openalex.org/I74973139"]}]}],"institutions":[],"countries_distinct_count":3,"institutions_distinct_count":9,"corresponding_author_ids":["https://openalex.org/A5102020639"],"corresponding_institution_ids":["https://openalex.org/I74973139"],"apc_list":null,"apc_paid":null,"fwci":0.4172,"has_fulltext":false,"cited_by_count":4,"citation_normalized_percentile":{"value":0.59581346,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":97},"biblio":{"volume":null,"issue":null,"first_page":"12919","last_page":"12926"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11689","display_name":"Adversarial Robustness in Machine Learning","score":0.9973000288009644,"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":0.9973000288009644,"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/T12423","display_name":"Software Reliability and Analysis Research","score":0.9955000281333923,"subfield":{"id":"https://openalex.org/subfields/1712","display_name":"Software"},"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":0.9842000007629395,"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/scalability","display_name":"Scalability","score":0.7808490991592407},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7735347747802734},{"id":"https://openalex.org/keywords/event","display_name":"Event (particle physics)","score":0.6801985502243042},{"id":"https://openalex.org/keywords/reinforcement-learning","display_name":"Reinforcement learning","score":0.6582108736038208},{"id":"https://openalex.org/keywords/markov-decision-process","display_name":"Markov decision process","score":0.6253652572631836},{"id":"https://openalex.org/keywords/rare-events","display_name":"Rare events","score":0.6246027946472168},{"id":"https://openalex.org/keywords/variance","display_name":"Variance (accounting)","score":0.6149106025695801},{"id":"https://openalex.org/keywords/importance-sampling","display_name":"Importance sampling","score":0.6040436029434204},{"id":"https://openalex.org/keywords/convergence","display_name":"Convergence (economics)","score":0.5625656247138977},{"id":"https://openalex.org/keywords/software-deployment","display_name":"Software deployment","score":0.5201704502105713},{"id":"https://openalex.org/keywords/sampling","display_name":"Sampling (signal processing)","score":0.515656590461731},{"id":"https://openalex.org/keywords/markov-process","display_name":"Markov process","score":0.45632389187812805},{"id":"https://openalex.org/keywords/markov-chain","display_name":"Markov chain","score":0.4168478846549988},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.3674997091293335},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.33527839183807373},{"id":"https://openalex.org/keywords/monte-carlo-method","display_name":"Monte Carlo method","score":0.2008347511291504},{"id":"https://openalex.org/keywords/statistics","display_name":"Statistics","score":0.1548614203929901},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.1421908140182495}],"concepts":[{"id":"https://openalex.org/C48044578","wikidata":"https://www.wikidata.org/wiki/Q727490","display_name":"Scalability","level":2,"score":0.7808490991592407},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7735347747802734},{"id":"https://openalex.org/C2779662365","wikidata":"https://www.wikidata.org/wiki/Q5416694","display_name":"Event (particle physics)","level":2,"score":0.6801985502243042},{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.6582108736038208},{"id":"https://openalex.org/C106189395","wikidata":"https://www.wikidata.org/wiki/Q176789","display_name":"Markov decision process","level":3,"score":0.6253652572631836},{"id":"https://openalex.org/C2777317252","wikidata":"https://www.wikidata.org/wiki/Q18393516","display_name":"Rare events","level":2,"score":0.6246027946472168},{"id":"https://openalex.org/C196083921","wikidata":"https://www.wikidata.org/wiki/Q7915758","display_name":"Variance (accounting)","level":2,"score":0.6149106025695801},{"id":"https://openalex.org/C52740198","wikidata":"https://www.wikidata.org/wiki/Q1539564","display_name":"Importance sampling","level":3,"score":0.6040436029434204},{"id":"https://openalex.org/C2777303404","wikidata":"https://www.wikidata.org/wiki/Q759757","display_name":"Convergence (economics)","level":2,"score":0.5625656247138977},{"id":"https://openalex.org/C105339364","wikidata":"https://www.wikidata.org/wiki/Q2297740","display_name":"Software deployment","level":2,"score":0.5201704502105713},{"id":"https://openalex.org/C140779682","wikidata":"https://www.wikidata.org/wiki/Q210868","display_name":"Sampling (signal processing)","level":3,"score":0.515656590461731},{"id":"https://openalex.org/C159886148","wikidata":"https://www.wikidata.org/wiki/Q176645","display_name":"Markov process","level":2,"score":0.45632389187812805},{"id":"https://openalex.org/C98763669","wikidata":"https://www.wikidata.org/wiki/Q176645","display_name":"Markov chain","level":2,"score":0.4168478846549988},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.3674997091293335},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.33527839183807373},{"id":"https://openalex.org/C19499675","wikidata":"https://www.wikidata.org/wiki/Q232207","display_name":"Monte Carlo method","level":2,"score":0.2008347511291504},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.1548614203929901},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.1421908140182495},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.0},{"id":"https://openalex.org/C77088390","wikidata":"https://www.wikidata.org/wiki/Q8513","display_name":"Database","level":1,"score":0.0},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0},{"id":"https://openalex.org/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","level":0,"score":0.0},{"id":"https://openalex.org/C50522688","wikidata":"https://www.wikidata.org/wiki/Q189833","display_name":"Economic growth","level":1,"score":0.0},{"id":"https://openalex.org/C62520636","wikidata":"https://www.wikidata.org/wiki/Q944","display_name":"Quantum mechanics","level":1,"score":0.0},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.0},{"id":"https://openalex.org/C121955636","wikidata":"https://www.wikidata.org/wiki/Q4116214","display_name":"Accounting","level":1,"score":0.0},{"id":"https://openalex.org/C144133560","wikidata":"https://www.wikidata.org/wiki/Q4830453","display_name":"Business","level":0,"score":0.0},{"id":"https://openalex.org/C106131492","wikidata":"https://www.wikidata.org/wiki/Q3072260","display_name":"Filter (signal processing)","level":2,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/iros47612.2022.9981867","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iros47612.2022.9981867","pdf_url":null,"source":{"id":"https://openalex.org/S4363607704","display_name":"2022 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":"2022 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/16","score":0.8100000023841858,"display_name":"Peace, Justice and strong institutions"}],"awards":[{"id":"https://openalex.org/G3796758555","display_name":null,"funder_award_id":"IIS-1849280,IIS-1849304","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"}],"funders":[{"id":"https://openalex.org/F4320306076","display_name":"National Science Foundation","ror":"https://ror.org/021nxhr62"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":55,"referenced_works":["https://openalex.org/W1502922572","https://openalex.org/W2037393162","https://openalex.org/W2115264563","https://openalex.org/W2126025075","https://openalex.org/W2152790647","https://openalex.org/W2158126207","https://openalex.org/W2338318698","https://openalex.org/W2438413413","https://openalex.org/W2511072509","https://openalex.org/W2525936901","https://openalex.org/W2559655401","https://openalex.org/W2612690371","https://openalex.org/W2758442112","https://openalex.org/W2766678531","https://openalex.org/W2798302089","https://openalex.org/W2903075639","https://openalex.org/W2908515202","https://openalex.org/W2990138404","https://openalex.org/W3021538051","https://openalex.org/W3037100357","https://openalex.org/W3098217413","https://openalex.org/W3098237412","https://openalex.org/W3110161557","https://openalex.org/W3117478135","https://openalex.org/W3133465684","https://openalex.org/W3207250575","https://openalex.org/W4211042066","https://openalex.org/W4212774754","https://openalex.org/W4213251304","https://openalex.org/W4214717370","https://openalex.org/W4233696721","https://openalex.org/W4288419306","https://openalex.org/W4297744401","https://openalex.org/W4297797010","https://openalex.org/W4298857966","https://openalex.org/W6637967152","https://openalex.org/W6685474145","https://openalex.org/W6685480099","https://openalex.org/W6715102896","https://openalex.org/W6735677848","https://openalex.org/W6738536549","https://openalex.org/W6745256532","https://openalex.org/W6748638692","https://openalex.org/W6754098010","https://openalex.org/W6756633189","https://openalex.org/W6759312646","https://openalex.org/W6760560836","https://openalex.org/W6763800524","https://openalex.org/W6764793234","https://openalex.org/W6774966973","https://openalex.org/W6776847764","https://openalex.org/W6779679106","https://openalex.org/W6779832048","https://openalex.org/W6780559895","https://openalex.org/W6786026496"],"related_works":["https://openalex.org/W4400868993","https://openalex.org/W3096874164","https://openalex.org/W1985560493","https://openalex.org/W2937181779","https://openalex.org/W2386410636","https://openalex.org/W2357975469","https://openalex.org/W2145363145","https://openalex.org/W1626977535","https://openalex.org/W2341346307","https://openalex.org/W3168977894"],"abstract_inverted_index":{"Evaluating":[0],"rare":[1,69,74,141],"but":[2],"high-stakes":[3],"events":[4,70],"is":[5,109],"one":[6],"of":[7,32,126,152],"the":[8,36,60,73,85,99,104,123,129,140],"main":[9],"challenges":[10],"in":[11,18,45,77,128,158],"obtaining":[12],"reliable":[13],"reinforcement":[14],"learning":[15],"policies,":[16],"especially":[17],"large":[19,30,112],"or":[20,41,114],"infinite":[21],"state/action":[22],"spaces":[23,116],"where":[24],"limited":[25],"scalability":[26],"dictates":[27],"a":[28,39,46,145],"prohibitively":[29],"number":[31],"testing":[33],"iterations.":[34],"On":[35],"other":[37],"hand,":[38],"biased":[40],"inaccurate":[42],"policy":[43,105],"evaluation":[44],"safety-critical":[47],"system":[48],"could":[49],"potentially":[50],"cause":[51],"unexpected":[52],"catastrophic":[53],"failures":[54],"during":[55],"deployment.":[56],"This":[57],"paper":[58],"proposes":[59],"Accelerated":[61],"Policy":[62],"Evaluation":[63],"(APE)":[64],"method,":[65],"which":[66],"simultaneously":[67],"uncovers":[68],"and":[71,92,160],"estimates":[72],"event":[75,142],"probability":[76,143],"Markov":[78],"decision":[79],"processes.":[80],"The":[81],"APE":[82,108,127,137],"method":[83],"treats":[84],"environment":[86],"nature":[87],"as":[88],"an":[89],"adversarial":[90],"agent":[91],"learns":[93],"towards,":[94],"through":[95],"adaptive":[96],"importance":[97],"sampling,":[98],"zero-variance":[100],"sampling":[101],"distribution":[102],"for":[103],"evaluation.":[106],"Moreover,":[107],"scalable":[110],"to":[111],"discrete":[113],"continuous":[115],"by":[117],"incorporating":[118],"function":[119],"approximators.":[120],"We":[121],"investigate":[122],"convergence":[124],"property":[125],"tabular":[130],"setting.":[131],"Our":[132],"empirical":[133],"studies":[134],"show":[135],"that":[136],"can":[138],"estimate":[139],"with":[144],"smaller":[146],"bias":[147],"while":[148],"only":[149],"using":[150],"orders":[151],"magnitude":[153],"fewer":[154],"samples":[155],"than":[156],"baselines":[157],"multi-agent":[159],"single-agent":[161],"environments.":[162]},"counts_by_year":[{"year":2025,"cited_by_count":3},{"year":2023,"cited_by_count":1}],"updated_date":"2026-04-28T14:05:53.105641","created_date":"2025-10-10T00:00:00"}