{"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","doi":"https://doi.org/10.1109/icra57147.2024.10611197","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icra57147.2024.10611197","pdf_url":null,"source":{"id":"https://openalex.org/S4210217939","display_name":"Proceedings - IEEE International Conference on Robotics and Automation/Proceedings","issn_l":"1050-4729","issn":["1050-4729","2577-087X"],"is_oa":false,"is_in_doaj":false,"is_core":true,"listed_in":["cwts-core","norway-1"],"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"conference"},"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"},"volume":null,"type":"conference-paper","indexed_in":["arxiv","crossref","datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2309.13614","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5009560003","display_name":"Zenan Li","orcid":"https://orcid.org/0000-0003-2432-1776","observed_orcids":["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":false,"raw_author_name":"Zenan Li","raw_affiliation_strings":["Tsinghua University"],"raw_orcid":null,"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":"https://orcid.org/0009-0009-1983-6952","observed_orcids":["https://orcid.org/0009-0009-1983-6952"]},"institutions":[{"id":"https://openalex.org/I4405259049","display_name":"Shanghai Qi Zhi Institute","ror":"https://ror.org/01n14yn69","country_code":"CN","type":"facility","lineage":["https://openalex.org/I4405259049"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Fan Nie","raw_affiliation_strings":["Shanghai Qi Zhi Institute"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Shanghai Qi Zhi Institute","institution_ids":["https://openalex.org/I4405259049"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100377836","display_name":"Qiao Sun","orcid":"https://orcid.org/0009-0003-1060-2371","observed_orcids":["https://orcid.org/0009-0003-1060-2371"]},"institutions":[{"id":"https://openalex.org/I4405259049","display_name":"Shanghai Qi Zhi Institute","ror":"https://ror.org/01n14yn69","country_code":"CN","type":"facility","lineage":["https://openalex.org/I4405259049"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Qiao Sun","raw_affiliation_strings":["Shanghai Qi Zhi Institute"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Shanghai Qi Zhi Institute","institution_ids":["https://openalex.org/I4405259049"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5004664254","display_name":"Fang Da","orcid":"https://orcid.org/0000-0002-0651-1608","observed_orcids":["https://orcid.org/0000-0002-0651-1608","https://orcid.org/0000-0001-9449-0992"]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Fang Da","raw_affiliation_strings":["QCraft Inc"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"QCraft Inc","institution_ids":[]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5101826600","display_name":"Hang Zhao","orcid":"https://orcid.org/0000-0003-1928-7841","observed_orcids":["https://orcid.org/0000-0003-1928-7841","https://orcid.org/0000-0001-7903-581X"]},"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"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Tsinghua University","institution_ids":["https://openalex.org/I99065089"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":2.6436,"has_fulltext":true,"cited_by_count":9,"citation_normalized_percentile":{"value":0.91412376,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":93,"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":0.9937000274658203,"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":0.9937000274658203,"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":0.005799999926239252,"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/T10370","display_name":"Traffic and Road Safety","score":0.0,"subfield":{"id":"https://openalex.org/subfields/2213","display_name":"Safety, Risk, Reliability and Quality"},"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/offline-reinforcement-learning","display_name":"offline reinforcement learning","score":0.996999979019165},{"id":"https://openalex.org/keywords/autonomous-driving","display_name":"autonomous driving","score":0.9679999947547913},{"id":"https://openalex.org/keywords/long-horizon-planning","display_name":"long-horizon planning","score":0.8539999723434448},{"id":"https://openalex.org/keywords/variational-autoencoder","display_name":"variational autoencoder","score":0.9620000123977661},{"id":"https://openalex.org/keywords/posterior-collapse","display_name":"posterior collapse","score":0.9449999928474426},{"id":"https://openalex.org/keywords/carla","display_name":"CARLA","score":0.7179999947547913},{"id":"https://openalex.org/keywords/driving-simulator","display_name":"driving simulator","score":0.4429999887943268},{"id":"https://openalex.org/keywords/skill-transferability","display_name":"skill transferability","score":0.46299999952316284}],"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":3,"locations":[{"id":"doi:10.1109/icra57147.2024.10611197","doi":"https://doi.org/10.1109/icra57147.2024.10611197","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icra57147.2024.10611197","pdf_url":null,"source":{"id":"https://openalex.org/S4210217939","display_name":"Proceedings - IEEE International Conference on Robotics and Automation/Proceedings","issn_l":"1050-4729","issn":["1050-4729","2577-087X"],"is_oa":false,"is_in_doaj":false,"is_core":true,"listed_in":["cwts-core","norway-1"],"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"conference"},"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"},{"id":"pmh:oai:arXiv.org:2309.13614","doi":null,"is_oa":true,"landing_page_url":"http://arxiv.org/abs/2309.13614","pdf_url":"https://arxiv.org/pdf/2309.13614","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},{"id":"doi:10.48550/arxiv.2309.13614","doi":"https://doi.org/10.48550/arxiv.2309.13614","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2309.13614","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":null,"is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Preprint"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2309.13614","doi":null,"is_oa":true,"landing_page_url":"http://arxiv.org/abs/2309.13614","pdf_url":"https://arxiv.org/pdf/2309.13614","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},"sustainable_development_goals":[],"study_designs":[],"awards":[],"funders":[],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4401413768.pdf","grobid_xml":"https://content.openalex.org/works/W4401413768.grobid-xml"},"referenced_works_count":48,"referenced_works":["https://openalex.org/W1931877416","https://openalex.org/W2096785587","https://openalex.org/W2109910161","https://openalex.org/W2148361676","https://openalex.org/W2187089797","https://openalex.org/W2547875792","https://openalex.org/W2561050497","https://openalex.org/W2733961795","https://openalex.org/W2753738274","https://openalex.org/W2767621168","https://openalex.org/W2784715585","https://openalex.org/W2807692250","https://openalex.org/W2892110489","https://openalex.org/W2904453761","https://openalex.org/W2905173465","https://openalex.org/W2919872398","https://openalex.org/W2924607344","https://openalex.org/W2962851448","https://openalex.org/W2964199361","https://openalex.org/W2986616324","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/W3094484961","https://openalex.org/W3096964654","https://openalex.org/W3156216502","https://openalex.org/W3170059879","https://openalex.org/W3172360140","https://openalex.org/W3173049816","https://openalex.org/W3176012696","https://openalex.org/W3193987867","https://openalex.org/W3205794883","https://openalex.org/W3207339639","https://openalex.org/W3216078707","https://openalex.org/W4224944611","https://openalex.org/W4225997321","https://openalex.org/W4281550413","https://openalex.org/W4296566564","https://openalex.org/W4298023569","https://openalex.org/W4306706296","https://openalex.org/W4312270460","https://openalex.org/W4312991107","https://openalex.org/W4313162271","https://openalex.org/W4389666640"],"related_works":["https://openalex.org/W4281550413","https://openalex.org/W4416407779","https://openalex.org/W4400647782","https://openalex.org/W4386903194","https://openalex.org/W4296566564","https://openalex.org/W4382173260","https://openalex.org/W4403667614","https://openalex.org/W4410500809","https://openalex.org/W7213412980","https://openalex.org/W4315778373"],"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":"2026-10-31T12:09:11.096373","created_date":"2024-08-09T00:00:00"}