{"id":"https://openalex.org/W4389665444","doi":"https://doi.org/10.1109/iros55552.2023.10341451","title":"Hierarchical Imitation Learning for Stochastic Environments","display_name":"Hierarchical Imitation Learning for Stochastic Environments","publication_year":2023,"publication_date":"2023-10-01","ids":{"openalex":"https://openalex.org/W4389665444","doi":"https://doi.org/10.1109/iros55552.2023.10341451"},"language":"en","primary_location":{"id":"doi:10.1109/iros55552.2023.10341451","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iros55552.2023.10341451","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2023 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/A5024136382","display_name":"Maximilian Igl","orcid":null},"institutions":[{"id":"https://openalex.org/I4210145145","display_name":"Nomor Research (Germany)","ror":"https://ror.org/04727qm97","country_code":"DE","type":"company","lineage":["https://openalex.org/I4210145145"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Maximilian Igl","raw_affiliation_strings":["Waymo Research"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Waymo Research","institution_ids":["https://openalex.org/I4210145145"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5043875101","display_name":"Punit Shah","orcid":"https://orcid.org/0000-0001-5497-4765"},"institutions":[{"id":"https://openalex.org/I4210145145","display_name":"Nomor Research (Germany)","ror":"https://ror.org/04727qm97","country_code":"DE","type":"company","lineage":["https://openalex.org/I4210145145"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Punit Shah","raw_affiliation_strings":["Waymo Research"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Waymo Research","institution_ids":["https://openalex.org/I4210145145"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5091007693","display_name":"Paul Mougin","orcid":null},"institutions":[{"id":"https://openalex.org/I4210145145","display_name":"Nomor Research (Germany)","ror":"https://ror.org/04727qm97","country_code":"DE","type":"company","lineage":["https://openalex.org/I4210145145"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Paul Mougin","raw_affiliation_strings":["Waymo Research"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Waymo Research","institution_ids":["https://openalex.org/I4210145145"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5029362547","display_name":"Sirish Srinivasan","orcid":"https://orcid.org/0000-0001-9460-9025"},"institutions":[{"id":"https://openalex.org/I4210145145","display_name":"Nomor Research (Germany)","ror":"https://ror.org/04727qm97","country_code":"DE","type":"company","lineage":["https://openalex.org/I4210145145"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Sirish Srinivasan","raw_affiliation_strings":["Waymo Research"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Waymo Research","institution_ids":["https://openalex.org/I4210145145"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101214183","display_name":"Tarun Gupta","orcid":null},"institutions":[{"id":"https://openalex.org/I40120149","display_name":"University of Oxford","ror":"https://ror.org/052gg0110","country_code":"GB","type":"education","lineage":["https://openalex.org/I40120149"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Tarun Gupta","raw_affiliation_strings":["U. of Oxford"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"U. of Oxford","institution_ids":["https://openalex.org/I40120149"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5111380600","display_name":"Brandyn White","orcid":null},"institutions":[{"id":"https://openalex.org/I4210145145","display_name":"Nomor Research (Germany)","ror":"https://ror.org/04727qm97","country_code":"DE","type":"company","lineage":["https://openalex.org/I4210145145"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Brandyn White","raw_affiliation_strings":["Waymo Research"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Waymo Research","institution_ids":["https://openalex.org/I4210145145"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5035251638","display_name":"Kyriacos Shiarlis","orcid":null},"institutions":[{"id":"https://openalex.org/I4210145145","display_name":"Nomor Research (Germany)","ror":"https://ror.org/04727qm97","country_code":"DE","type":"company","lineage":["https://openalex.org/I4210145145"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Kyriacos Shiarlis","raw_affiliation_strings":["Waymo Research"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Waymo Research","institution_ids":["https://openalex.org/I4210145145"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5056879203","display_name":"Shimon Whiteson","orcid":null},"institutions":[{"id":"https://openalex.org/I4210145145","display_name":"Nomor Research (Germany)","ror":"https://ror.org/04727qm97","country_code":"DE","type":"company","lineage":["https://openalex.org/I4210145145"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Shimon Whiteson","raw_affiliation_strings":["Waymo Research"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Waymo Research","institution_ids":["https://openalex.org/I4210145145"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":8,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.1632,"has_fulltext":false,"cited_by_count":1,"citation_normalized_percentile":{"value":0.58616212,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":91,"max":95},"biblio":{"volume":null,"issue":null,"first_page":"1697","last_page":"1704"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10462","display_name":"Reinforcement Learning in Robotics","score":0.9983999729156494,"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":0.9983999729156494,"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/T11099","display_name":"Autonomous Vehicle Technology and Safety","score":0.998199999332428,"subfield":{"id":"https://openalex.org/subfields/2203","display_name":"Automotive 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":0.9843000173568726,"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/computer-science","display_name":"Computer science","score":0.7395535707473755},{"id":"https://openalex.org/keywords/imitation","display_name":"Imitation","score":0.6227331757545471},{"id":"https://openalex.org/keywords/trajectory","display_name":"Trajectory","score":0.5817781686782837},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5485596656799316},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.5208814144134521},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.4829061031341553},{"id":"https://openalex.org/keywords/encoding","display_name":"Encoding (memory)","score":0.455992192029953},{"id":"https://openalex.org/keywords/control","display_name":"Control (management)","score":0.434345543384552},{"id":"https://openalex.org/keywords/adversarial-system","display_name":"Adversarial system","score":0.42786332964897156},{"id":"https://openalex.org/keywords/dependency","display_name":"Dependency (UML)","score":0.42763668298721313},{"id":"https://openalex.org/keywords/reinforcement-learning","display_name":"Reinforcement learning","score":0.4248386323451996},{"id":"https://openalex.org/keywords/scale","display_name":"Scale (ratio)","score":0.4237300157546997},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.10926049947738647}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7395535707473755},{"id":"https://openalex.org/C126388530","wikidata":"https://www.wikidata.org/wiki/Q1131737","display_name":"Imitation","level":2,"score":0.6227331757545471},{"id":"https://openalex.org/C13662910","wikidata":"https://www.wikidata.org/wiki/Q193139","display_name":"Trajectory","level":2,"score":0.5817781686782837},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5485596656799316},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.5208814144134521},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.4829061031341553},{"id":"https://openalex.org/C125411270","wikidata":"https://www.wikidata.org/wiki/Q18653","display_name":"Encoding (memory)","level":2,"score":0.455992192029953},{"id":"https://openalex.org/C2775924081","wikidata":"https://www.wikidata.org/wiki/Q55608371","display_name":"Control (management)","level":2,"score":0.434345543384552},{"id":"https://openalex.org/C37736160","wikidata":"https://www.wikidata.org/wiki/Q1801315","display_name":"Adversarial system","level":2,"score":0.42786332964897156},{"id":"https://openalex.org/C19768560","wikidata":"https://www.wikidata.org/wiki/Q320727","display_name":"Dependency (UML)","level":2,"score":0.42763668298721313},{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.4248386323451996},{"id":"https://openalex.org/C2778755073","wikidata":"https://www.wikidata.org/wiki/Q10858537","display_name":"Scale (ratio)","level":2,"score":0.4237300157546997},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.10926049947738647},{"id":"https://openalex.org/C15744967","wikidata":"https://www.wikidata.org/wiki/Q9418","display_name":"Psychology","level":0,"score":0.0},{"id":"https://openalex.org/C201995342","wikidata":"https://www.wikidata.org/wiki/Q682496","display_name":"Systems engineering","level":1,"score":0.0},{"id":"https://openalex.org/C1276947","wikidata":"https://www.wikidata.org/wiki/Q333","display_name":"Astronomy","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/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0},{"id":"https://openalex.org/C77805123","wikidata":"https://www.wikidata.org/wiki/Q161272","display_name":"Social psychology","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/iros55552.2023.10341451","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iros55552.2023.10341451","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2023 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS)","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":50,"referenced_works":["https://openalex.org/W2050032417","https://openalex.org/W2109910161","https://openalex.org/W2462906003","https://openalex.org/W2560678327","https://openalex.org/W2729615412","https://openalex.org/W2736601468","https://openalex.org/W2765811365","https://openalex.org/W2947630374","https://openalex.org/W2963411833","https://openalex.org/W2963713397","https://openalex.org/W2964227312","https://openalex.org/W2982316857","https://openalex.org/W3034055718","https://openalex.org/W3035069850","https://openalex.org/W3096831136","https://openalex.org/W3156216502","https://openalex.org/W3165436200","https://openalex.org/W3181350748","https://openalex.org/W4214700710","https://openalex.org/W4229450941","https://openalex.org/W4240805545","https://openalex.org/W4287685696","https://openalex.org/W4295837424","https://openalex.org/W4383108456","https://openalex.org/W6638018090","https://openalex.org/W6640174482","https://openalex.org/W6640963894","https://openalex.org/W6718092244","https://openalex.org/W6718836005","https://openalex.org/W6730700719","https://openalex.org/W6734215269","https://openalex.org/W6738261575","https://openalex.org/W6741002519","https://openalex.org/W6741010574","https://openalex.org/W6741115023","https://openalex.org/W6743368274","https://openalex.org/W6745405225","https://openalex.org/W6746090280","https://openalex.org/W6748198416","https://openalex.org/W6748603076","https://openalex.org/W6748972340","https://openalex.org/W6749986616","https://openalex.org/W6751912414","https://openalex.org/W6755459604","https://openalex.org/W6760439459","https://openalex.org/W6760847586","https://openalex.org/W6762863188","https://openalex.org/W6765008394","https://openalex.org/W6782088249","https://openalex.org/W6842337745"],"related_works":["https://openalex.org/W4387497383","https://openalex.org/W3183948672","https://openalex.org/W3173606202","https://openalex.org/W3110381201","https://openalex.org/W2948807893","https://openalex.org/W2935909890","https://openalex.org/W2778153218","https://openalex.org/W2758277628","https://openalex.org/W1531601525","https://openalex.org/W2502115930"],"abstract_inverted_index":{"Many":[0],"applications":[1],"of":[2,13,26,36,107,172],"imitation":[3],"learning":[4],"require":[5,103],"the":[6,10,17,24,56,81,95,105,113,125,131,147,158,169,200],"agent":[7,82,90,114,142,173],"to":[8,22,68,86,112,140,217],"generate":[9],"full":[11],"distribution":[12,166,171],"behaviour":[14,34,115],"observed":[15,96],"in":[16,29,130,168],"training":[18,190],"data.":[19],"For":[20],"example,":[21],"evaluate":[23],"safety":[25],"autonomous":[27],"vehicles":[28],"simulation,":[30],"accurate":[31],"and":[32,109,118,151],"diverse":[33],"models":[35],"other":[37],"road":[38],"users":[39],"are":[40,74,92,116,128],"paramount.":[41],"Existing":[42],"methods":[43,73],"that":[44,65,104],"improve":[45],"this":[46,163,186],"distributional":[47,208],"realism":[48,209],"typically":[49],"rely":[50],"on":[51,58,196],"hierarchical":[52],"policies.":[53],"These":[54],"condition":[55],"policy":[57],"types":[59,91,152,174],"such":[60,72],"as":[61,165],"goals":[62],"or":[63,212],"personas":[64],"give":[66],"rise":[67],"multi-modal":[69],"behaviour.":[70],"However,":[71],"often":[75],"inappropriate":[76,141],"for":[77],"stochastic":[78],"environments":[79,102],"where":[80],"must":[83,153],"also":[84],"react":[85],"external":[87,110,137],"factors:":[88],"because":[89],"inferred":[93],"from":[94,157],"future":[97,134,148],"trajectory":[98],"during":[99,144],"training,":[100],"these":[101],"contributions":[106],"internal":[108,120],"factors":[111,138],"disentangled":[117],"only":[119],"factors,":[121],"i.e.,":[122],"those":[123],"under":[124,175,191],"agent's":[126],"control,":[127],"encoded":[129],"type.":[132],"Encoding":[133],"information":[135],"about":[136],"leads":[139],"reactions":[143],"testing,":[145],"when":[146],"is":[149],"unknown":[150],"be":[154],"drawn":[155],"independently":[156],"actual":[159],"future.":[160],"We":[161,178],"formalize":[162],"challenge":[164],"shift":[167,187],"conditional":[170],"environmental":[176],"stochasticity.":[177],"propose":[179],"Robust":[180],"Type":[181],"Conditioning":[182],"(RTC),":[183],"which":[184],"eliminates":[185],"with":[188],"adversarial":[189],"randomly":[192],"sampled":[193],"types.":[194],"Experiments":[195],"two":[197],"domains,":[198],"including":[199],"large-scale":[201],"Waymo":[202],"Open":[203],"Motion":[204],"Dataset,":[205],"show":[206],"improved":[207],"while":[210],"maintaining":[211],"improving":[213],"task":[214],"performance":[215],"compared":[216],"state-of-the-art":[218],"baselines.":[219]},"counts_by_year":[{"year":2025,"cited_by_count":1}],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2025-10-10T00:00:00"}