{"id":"https://openalex.org/W4401413768","doi":"https://doi.org/10.1109/icra57147.2024.10611197","title":"Boosting Offline Reinforcement Learning for Autonomous Driving with Hierarchical Latent Skills","display_name":"Boosting Offline Reinforcement Learning for Autonomous Driving with Hierarchical Latent Skills","publication_year":2024,"publication_date":"2024-05-13","ids":{"openalex":"https://openalex.org/W4401413768","doi":"https://doi.org/10.1109/icra57147.2024.10611197"},"language":"en","primary_location":{"id":"doi:10.1109/icra57147.2024.10611197","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icra57147.2024.10611197","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2024 IEEE 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/A5009560003","display_name":"Zenan Li","orcid":"https://orcid.org/0000-0003-2432-1776"},"institutions":[{"id":"https://openalex.org/I99065089","display_name":"Tsinghua University","ror":"https://ror.org/03cve4549","country_code":"CN","type":"education","lineage":["https://openalex.org/I99065089"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Zenan Li","raw_affiliation_strings":["Tsinghua University"],"affiliations":[{"raw_affiliation_string":"Tsinghua University","institution_ids":["https://openalex.org/I99065089"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5102560392","display_name":"Fan Nie","orcid":null},"institutions":[{"id":"https://openalex.org/I4210122302","display_name":"ShangHai JiAi Genetics & IVF Institute","ror":"https://ror.org/02rgbry52","country_code":"CN","type":"healthcare","lineage":["https://openalex.org/I4210122302"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Fan Nie","raw_affiliation_strings":["Shanghai Qi Zhi Institute"],"affiliations":[{"raw_affiliation_string":"Shanghai Qi Zhi Institute","institution_ids":["https://openalex.org/I4210122302"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100377836","display_name":"Qiao Sun","orcid":"https://orcid.org/0009-0003-1060-2371"},"institutions":[{"id":"https://openalex.org/I4210122302","display_name":"ShangHai JiAi Genetics & IVF Institute","ror":"https://ror.org/02rgbry52","country_code":"CN","type":"healthcare","lineage":["https://openalex.org/I4210122302"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Qiao Sun","raw_affiliation_strings":["Shanghai Qi Zhi Institute"],"affiliations":[{"raw_affiliation_string":"Shanghai Qi Zhi Institute","institution_ids":["https://openalex.org/I4210122302"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5004664254","display_name":"Fang Da","orcid":"https://orcid.org/0000-0002-0651-1608"},"institutions":[{"id":"https://openalex.org/I4210118951","display_name":"Craft Engineering Associates (United States)","ror":"https://ror.org/02b3gqy34","country_code":"US","type":"company","lineage":["https://openalex.org/I4210118951"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Fang Da","raw_affiliation_strings":["QCraft Inc"],"affiliations":[{"raw_affiliation_string":"QCraft Inc","institution_ids":["https://openalex.org/I4210118951"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5100418980","display_name":"Hang Zhao","orcid":"https://orcid.org/0000-0002-0482-1573"},"institutions":[{"id":"https://openalex.org/I99065089","display_name":"Tsinghua University","ror":"https://ror.org/03cve4549","country_code":"CN","type":"education","lineage":["https://openalex.org/I99065089"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Hang Zhao","raw_affiliation_strings":["Tsinghua University"],"affiliations":[{"raw_affiliation_string":"Tsinghua University","institution_ids":["https://openalex.org/I99065089"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":5,"corresponding_author_ids":["https://openalex.org/A5009560003"],"corresponding_institution_ids":["https://openalex.org/I99065089"],"apc_list":null,"apc_paid":null,"fwci":3.1896,"has_fulltext":false,"cited_by_count":9,"citation_normalized_percentile":{"value":0.92732463,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":94,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"18362","last_page":"18369"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10462","display_name":"Reinforcement Learning in Robotics","score":0.9995999932289124,"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":0.9995999932289124,"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":0.9922000169754028,"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/T12535","display_name":"Machine Learning and Data Classification","score":0.9793999791145325,"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/reinforcement-learning","display_name":"Reinforcement learning","score":0.8389641046524048},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6831935048103333},{"id":"https://openalex.org/keywords/boosting","display_name":"Boosting (machine learning)","score":0.6478824019432068},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.4406307339668274},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.436281681060791}],"concepts":[{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.8389641046524048},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6831935048103333},{"id":"https://openalex.org/C46686674","wikidata":"https://www.wikidata.org/wiki/Q466303","display_name":"Boosting (machine learning)","level":2,"score":0.6478824019432068},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.4406307339668274},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.436281681060791}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icra57147.2024.10611197","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icra57147.2024.10611197","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2024 IEEE International Conference on Robotics and Automation (ICRA)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Reduced inequalities","score":0.4300000071525574,"id":"https://metadata.un.org/sdg/10"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":63,"referenced_works":["https://openalex.org/W2096785587","https://openalex.org/W2109910161","https://openalex.org/W2148361676","https://openalex.org/W2187089797","https://openalex.org/W2547875792","https://openalex.org/W2784715585","https://openalex.org/W2796704765","https://openalex.org/W2892110489","https://openalex.org/W2905173465","https://openalex.org/W2924607344","https://openalex.org/W2962851448","https://openalex.org/W2964199361","https://openalex.org/W2986708244","https://openalex.org/W3022566517","https://openalex.org/W3025606523","https://openalex.org/W3033324992","https://openalex.org/W3034552332","https://openalex.org/W3041956526","https://openalex.org/W3048804154","https://openalex.org/W3090369311","https://openalex.org/W3104946437","https://openalex.org/W3156216502","https://openalex.org/W3172360140","https://openalex.org/W3193987867","https://openalex.org/W3205794883","https://openalex.org/W3207339639","https://openalex.org/W4225997321","https://openalex.org/W4281550413","https://openalex.org/W4287115177","https://openalex.org/W4298023569","https://openalex.org/W4300799055","https://openalex.org/W4306706296","https://openalex.org/W4311033210","https://openalex.org/W4312270460","https://openalex.org/W4312991107","https://openalex.org/W4313162271","https://openalex.org/W4389666640","https://openalex.org/W6640174482","https://openalex.org/W6729448088","https://openalex.org/W6730493023","https://openalex.org/W6740801417","https://openalex.org/W6744627333","https://openalex.org/W6745935785","https://openalex.org/W6755015941","https://openalex.org/W6757469721","https://openalex.org/W6760439459","https://openalex.org/W6776438516","https://openalex.org/W6777091672","https://openalex.org/W6779265984","https://openalex.org/W6780593937","https://openalex.org/W6784712800","https://openalex.org/W6785193213","https://openalex.org/W6795014841","https://openalex.org/W6796589144","https://openalex.org/W6797256610","https://openalex.org/W6797805403","https://openalex.org/W6802659552","https://openalex.org/W6802957429","https://openalex.org/W6804698612","https://openalex.org/W6810488170","https://openalex.org/W6811084544","https://openalex.org/W6842971753","https://openalex.org/W6845636941"],"related_works":["https://openalex.org/W2961085424","https://openalex.org/W4306674287","https://openalex.org/W3082059448","https://openalex.org/W4313640622","https://openalex.org/W3046775127","https://openalex.org/W3107602296","https://openalex.org/W4394896187","https://openalex.org/W3170094116","https://openalex.org/W4386462264","https://openalex.org/W4364306694"],"abstract_inverted_index":{"Learning-based":[0],"vehicle":[1,54],"planning":[2,55],"is":[3,23],"receiving":[4],"increasing":[5],"attention":[6],"with":[7],"the":[8,52,92,132,157],"emergence":[9],"of":[10,74,91,161],"diverse":[11],"driving":[12,16,94],"simulators":[13],"and":[14,88,104,149,154,159],"large-scale":[15],"datasets.":[17],"While":[18],"offline":[19,48,68,111],"reinforcement":[20],"learning":[21],"(RL)":[22],"well":[24],"suited":[25],"for":[26],"these":[27],"safety-critical":[28],"tasks,":[29],"it":[30],"still":[31],"struggles":[32],"to":[33,50,64,83,123],"plan":[34],"over":[35],"extended":[36,125],"periods.":[37],"In":[38],"this":[39],"work,":[40],"we":[41,58,77],"present":[42],"a":[43,60,79,116],"skill-based":[44],"framework":[45],"that":[46,139],"enhances":[47],"RL":[49,112],"overcome":[51],"long-horizon":[53],"challenge.":[56],"Specifically,":[57],"design":[59],"variational":[61],"autoencoder":[62],"(VAE)":[63],"learn":[65],"skills":[66,101],"from":[67,120],"demonstrations.":[69],"To":[70],"mitigate":[71],"posterior":[72],"collapse":[73],"common":[75],"VAEs,":[76],"introduce":[78],"two-branch":[80],"sequence":[81],"encoder":[82],"capture":[84],"both":[85,147],"discrete":[86],"options":[87],"continuous":[89],"variations":[90],"complex":[93],"skills.":[95,163],"The":[96],"final":[97],"policy":[98],"treats":[99],"learned":[100],"as":[102],"actions":[103,122],"can":[105],"be":[106],"trained":[107],"by":[108],"any":[109],"off-the-shelf":[110],"algorithms.":[113],"This":[114],"facilitates":[115],"shift":[117],"in":[118],"focus":[119],"per-step":[121],"temporally":[124],"skills,":[126],"thereby":[127],"enabling":[128],"long-term":[129],"reasoning":[130],"into":[131],"future.":[133],"Extensive":[134],"results":[135],"on":[136],"CARLA":[137],"prove":[138],"our":[140],"model":[141],"consistently":[142],"outperforms":[143],"strong":[144],"baselines":[145],"at":[146],"training":[148],"new":[150],"scenarios.":[151],"Additional":[152],"visualizations":[153],"experiments":[155],"demonstrate":[156],"interpretability":[158],"transferability":[160],"extracted":[162]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":6},{"year":2024,"cited_by_count":2}],"updated_date":"2026-03-20T23:20:44.827607","created_date":"2025-10-10T00:00:00"}