{"id":"https://openalex.org/W4281550413","doi":"https://doi.org/10.1109/lra.2022.3190100","title":"Hierarchical Planning Through Goal-Conditioned Offline Reinforcement Learning","display_name":"Hierarchical Planning Through Goal-Conditioned Offline Reinforcement Learning","publication_year":2022,"publication_date":"2022-07-12","ids":{"openalex":"https://openalex.org/W4281550413","doi":"https://doi.org/10.1109/lra.2022.3190100"},"language":"en","primary_location":{"id":"doi:10.1109/lra.2022.3190100","is_oa":false,"landing_page_url":"https://doi.org/10.1109/lra.2022.3190100","pdf_url":null,"source":{"id":"https://openalex.org/S4210169774","display_name":"IEEE Robotics and Automation Letters","issn_l":"2377-3766","issn":["2377-3766"],"is_oa":false,"is_in_doaj":false,"is_core":true,"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":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Robotics and Automation Letters","raw_type":"journal-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/A5065279959","display_name":"Jinning Li","orcid":"https://orcid.org/0000-0002-7335-5553"},"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":"Jinning Li","raw_affiliation_strings":["Department of Mechanical Engineering, University of California, Berkeley, CA, USA"],"raw_orcid":"https://orcid.org/0000-0002-7335-5553","affiliations":[{"raw_affiliation_string":"Department of Mechanical Engineering, University of California, Berkeley, CA, USA","institution_ids":["https://openalex.org/I95457486"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101867083","display_name":"Chen Tang","orcid":"https://orcid.org/0000-0002-7536-9983"},"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":"Chen Tang","raw_affiliation_strings":["Department of Mechanical Engineering, University of California, Berkeley, CA, USA"],"raw_orcid":"https://orcid.org/0000-0002-7536-9983","affiliations":[{"raw_affiliation_string":"Department of Mechanical Engineering, University of California, Berkeley, CA, USA","institution_ids":["https://openalex.org/I95457486"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5064077634","display_name":"Masayoshi Tomizuka","orcid":"https://orcid.org/0000-0003-0206-6639"},"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":"Masayoshi Tomizuka","raw_affiliation_strings":["Department of Mechanical Engineering, University of California, Berkeley, CA, USA"],"raw_orcid":"https://orcid.org/0000-0003-0206-6639","affiliations":[{"raw_affiliation_string":"Department of Mechanical Engineering, University of California, Berkeley, CA, USA","institution_ids":["https://openalex.org/I95457486"]}]},{"author_position":"last","author":{"id":null,"display_name":"Wei Zhan","orcid":"https://orcid.org/0000-0002-1474-1200"},"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":"Wei Zhan","raw_affiliation_strings":["Department of Mechanical Engineering, University of California, Berkeley, CA, USA"],"raw_orcid":"https://orcid.org/0000-0002-1474-1200","affiliations":[{"raw_affiliation_string":"Department of Mechanical Engineering, University of California, Berkeley, CA, USA","institution_ids":["https://openalex.org/I95457486"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5065279959"],"corresponding_institution_ids":["https://openalex.org/I95457486"],"apc_list":null,"apc_paid":null,"fwci":4.5781,"has_fulltext":false,"cited_by_count":37,"citation_normalized_percentile":{"value":0.95225547,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":90,"max":100},"biblio":{"volume":"7","issue":"4","first_page":"10216","last_page":"10223"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10462","display_name":"Reinforcement Learning in Robotics","score":0.9932000041007996,"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":0.9932000041007996,"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/T11714","display_name":"Multimodal Machine Learning Applications","score":0.9836999773979187,"subfield":{"id":"https://openalex.org/subfields/1707","display_name":"Computer Vision and Pattern Recognition"},"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/T10586","display_name":"Robotic Path Planning Algorithms","score":0.9778000116348267,"subfield":{"id":"https://openalex.org/subfields/1707","display_name":"Computer Vision and Pattern Recognition"},"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":0.8553485870361328},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7136189341545105},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.6604712009429932},{"id":"https://openalex.org/keywords/planner","display_name":"Planner","score":0.6343557834625244},{"id":"https://openalex.org/keywords/autoencoder","display_name":"Autoencoder","score":0.5859239101409912},{"id":"https://openalex.org/keywords/offline-learning","display_name":"Offline learning","score":0.559645414352417},{"id":"https://openalex.org/keywords/hierarchy","display_name":"Hierarchy","score":0.5423513054847717},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.517143189907074},{"id":"https://openalex.org/keywords/robotics","display_name":"Robotics","score":0.44701117277145386},{"id":"https://openalex.org/keywords/function","display_name":"Function (biology)","score":0.4341171085834503},{"id":"https://openalex.org/keywords/robot","display_name":"Robot","score":0.419727623462677},{"id":"https://openalex.org/keywords/process","display_name":"Process (computing)","score":0.4132935404777527},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.2993841767311096},{"id":"https://openalex.org/keywords/online-learning","display_name":"Online learning","score":0.15994489192962646}],"concepts":[{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.8553485870361328},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7136189341545105},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6604712009429932},{"id":"https://openalex.org/C2776999362","wikidata":"https://www.wikidata.org/wiki/Q2349274","display_name":"Planner","level":2,"score":0.6343557834625244},{"id":"https://openalex.org/C101738243","wikidata":"https://www.wikidata.org/wiki/Q786435","display_name":"Autoencoder","level":3,"score":0.5859239101409912},{"id":"https://openalex.org/C2780490138","wikidata":"https://www.wikidata.org/wiki/Q7079636","display_name":"Offline learning","level":3,"score":0.559645414352417},{"id":"https://openalex.org/C31170391","wikidata":"https://www.wikidata.org/wiki/Q188619","display_name":"Hierarchy","level":2,"score":0.5423513054847717},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.517143189907074},{"id":"https://openalex.org/C34413123","wikidata":"https://www.wikidata.org/wiki/Q170978","display_name":"Robotics","level":3,"score":0.44701117277145386},{"id":"https://openalex.org/C14036430","wikidata":"https://www.wikidata.org/wiki/Q3736076","display_name":"Function (biology)","level":2,"score":0.4341171085834503},{"id":"https://openalex.org/C90509273","wikidata":"https://www.wikidata.org/wiki/Q11012","display_name":"Robot","level":2,"score":0.419727623462677},{"id":"https://openalex.org/C98045186","wikidata":"https://www.wikidata.org/wiki/Q205663","display_name":"Process (computing)","level":2,"score":0.4132935404777527},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.2993841767311096},{"id":"https://openalex.org/C2986087404","wikidata":"https://www.wikidata.org/wiki/Q15946010","display_name":"Online learning","level":2,"score":0.15994489192962646},{"id":"https://openalex.org/C78458016","wikidata":"https://www.wikidata.org/wiki/Q840400","display_name":"Evolutionary biology","level":1,"score":0.0},{"id":"https://openalex.org/C34447519","wikidata":"https://www.wikidata.org/wiki/Q179522","display_name":"Market economy","level":1,"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/C136764020","wikidata":"https://www.wikidata.org/wiki/Q466","display_name":"World Wide Web","level":1,"score":0.0},{"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/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/lra.2022.3190100","is_oa":false,"landing_page_url":"https://doi.org/10.1109/lra.2022.3190100","pdf_url":null,"source":{"id":"https://openalex.org/S4210169774","display_name":"IEEE Robotics and Automation Letters","issn_l":"2377-3766","issn":["2377-3766"],"is_oa":false,"is_in_doaj":false,"is_core":true,"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":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Robotics and Automation Letters","raw_type":"journal-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":36,"referenced_works":["https://openalex.org/W1571530861","https://openalex.org/W1588241099","https://openalex.org/W2132083787","https://openalex.org/W2962894046","https://openalex.org/W2968202530","https://openalex.org/W2990123902","https://openalex.org/W3002044607","https://openalex.org/W3016525976","https://openalex.org/W3039055967","https://openalex.org/W3090369311","https://openalex.org/W3124514933","https://openalex.org/W3138939485","https://openalex.org/W3184258555","https://openalex.org/W3205367325","https://openalex.org/W4288319859","https://openalex.org/W4288331462","https://openalex.org/W6616173779","https://openalex.org/W6629152578","https://openalex.org/W6635701881","https://openalex.org/W6687045409","https://openalex.org/W6738483526","https://openalex.org/W6740801417","https://openalex.org/W6745935785","https://openalex.org/W6747473740","https://openalex.org/W6752089545","https://openalex.org/W6764053384","https://openalex.org/W6764173040","https://openalex.org/W6765008394","https://openalex.org/W6767649332","https://openalex.org/W6769035977","https://openalex.org/W6776601253","https://openalex.org/W6779265984","https://openalex.org/W6785193213","https://openalex.org/W6801009634","https://openalex.org/W6802363888","https://openalex.org/W6803084100"],"related_works":["https://openalex.org/W2159052453","https://openalex.org/W3013693939","https://openalex.org/W2566616303","https://openalex.org/W3131327266","https://openalex.org/W4225619808","https://openalex.org/W4388926065","https://openalex.org/W4376223516","https://openalex.org/W4226042081","https://openalex.org/W4283712691","https://openalex.org/W4308935744"],"abstract_inverted_index":{"Offline":[0],"Reinforcement":[1],"learning":[2],"(RL)":[3],"has":[4],"shown":[5],"potent":[6],"in":[7,11,26,141,165],"many":[8],"safe-critical":[9],"tasks":[10],"robotics":[12],"where":[13],"exploration":[14],"is":[15,65],"risky":[16],"and":[17,57,127,144,159],"expensive.":[18],"However,":[19],"it":[20],"still":[21],"struggles":[22],"to":[23,75,121,128],"acquire":[24],"skills":[25],"temporally":[27,41],"extended":[28,42],"tasks.":[29,43,147,168],"In":[30],"this":[31],"paper,":[32],"we":[33],"study":[34],"the":[35,72,107,112,130],"problem":[36],"of":[37,51,95,111],"offline":[38,68,73],"RL":[39,55],"for":[40],"We":[44,70,115,136],"propose":[45],"a":[46,52,58,81,117],"hierarchical":[47,157],"planning":[48,97],"framework,":[49],"consisting":[50],"low-level":[53,63,113],"goal-conditioned":[54],"policy":[56,64],"high-level":[59,87,131],"goal":[60,83],"planner.":[61],"The":[62,86],"trained":[66],"via":[67],"RL.":[69],"improve":[71],"training":[74],"deal":[76],"with":[77,155],"out-of-distribution":[78],"goals":[79],"by":[80,92],"perturbed":[82],"sampling":[84],"process.":[85],"planner":[88],"selects":[89],"intermediate":[90],"sub-goals":[91],"taking":[93],"advantages":[94],"model-based":[96],"methods.":[98],"It":[99],"plans":[100],"over":[101],"future":[102],"sub-goal":[103,125],"sequences":[104],"based":[105],"on":[106],"learned":[108],"value":[109],"function":[110],"policy.":[114],"adopt":[116],"Conditional":[118],"Variational":[119],"Autoencoder":[120],"sample":[122],"meaningful":[123],"high-dimensional":[124],"candidates":[126],"solve":[129],"long-term":[132],"strategy":[133],"optimization":[134],"problem.":[135],"evaluate":[137],"our":[138,151],"proposed":[139],"method":[140,152],"long-horizon":[142],"driving":[143],"robot":[145],"navigation":[146],"Experiments":[148],"show":[149],"that":[150],"outperforms":[153],"baselines":[154],"different":[156],"designs":[158],"other":[160],"regular":[161],"planners":[162],"without":[163],"hierarchy":[164],"these":[166],"complex":[167]},"counts_by_year":[{"year":2026,"cited_by_count":4},{"year":2025,"cited_by_count":10},{"year":2024,"cited_by_count":19},{"year":2023,"cited_by_count":3},{"year":2022,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}