{"id":"https://openalex.org/W4401110387","doi":"https://doi.org/10.1109/most60774.2024.00026","title":"L-MBOP-E: Latent-Model Based Offline Planning with Extrinsic Policy Guided Exploration","display_name":"L-MBOP-E: Latent-Model Based Offline Planning with Extrinsic Policy Guided Exploration","publication_year":2024,"publication_date":"2024-05-01","ids":{"openalex":"https://openalex.org/W4401110387","doi":"https://doi.org/10.1109/most60774.2024.00026"},"language":"en","primary_location":{"id":"doi:10.1109/most60774.2024.00026","doi":"https://doi.org/10.1109/most60774.2024.00026","is_oa":false,"landing_page_url":"http://dx.doi.org/10.1109/most60774.2024.00026","pdf_url":null,"source":{"id":"https://openalex.org/S7407088997","display_name":"IEEE International Conference on Mobility, Operations, Services and Technologies (MOST)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"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 Mobility, Operations, Services and Technologies (MOST)","raw_type":"proceedings-article"},"parent_works":[],"lineage":["https://openalex.org/W4401110387"],"child_works_count":0,"type":"conference-paper","is_traditional":true,"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/A5106011087","display_name":"Imran Adham","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I84218800","display_name":"University of California, Davis","ror":"https://ror.org/05rrcem69","country_code":"US","type":"education","lineage":["https://openalex.org/I84218800"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Imran Adham","raw_affiliation_strings":["University of California,Department of Computer Science,Davis,USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of California,Department of Computer Science,Davis,USA","institution_ids":["https://openalex.org/I84218800"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5115695424","display_name":"Hang Wang","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I84218800","display_name":"University of California, Davis","ror":"https://ror.org/05rrcem69","country_code":"US","type":"education","lineage":["https://openalex.org/I84218800"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Hang Wang","raw_affiliation_strings":["University of California,Department of Electrical and Computer Engineering,Davis,USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of California,Department of Electrical and Computer Engineering,Davis,USA","institution_ids":["https://openalex.org/I84218800"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5054861101","display_name":"Sen Lin","orcid":"https://orcid.org/0009-0005-4014-1646","observed_orcids":["https://orcid.org/0009-0005-4014-1646"]},"institutions":[{"id":"https://openalex.org/I44461941","display_name":"University of Houston","ror":"https://ror.org/048sx0r50","country_code":"US","type":"education","lineage":["https://openalex.org/I44461941"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Sen Lin","raw_affiliation_strings":["University of Houston,Department of Computer Science,USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Houston,Department of Computer Science,USA","institution_ids":["https://openalex.org/I44461941"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5027033026","display_name":"Junshan Zhang","orcid":"https://orcid.org/0000-0002-3840-1753","observed_orcids":["https://orcid.org/0000-0002-3840-1753"]},"institutions":[{"id":"https://openalex.org/I84218800","display_name":"University of California, Davis","ror":"https://ror.org/05rrcem69","country_code":"US","type":"education","lineage":["https://openalex.org/I84218800"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Junshan Zhang","raw_affiliation_strings":["University of California,Department of Electrical and Computer Engineering,Davis,USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of California,Department of Electrical and Computer Engineering,Davis,USA","institution_ids":["https://openalex.org/I84218800"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.0,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":"31","issue":null,"first_page":"178","last_page":"185"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10462","display_name":"Reinforcement Learning in Robotics","score":1.0,"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":1.0,"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/T10906","display_name":"AI-based Problem Solving and Planning","score":0.0,"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/T12794","display_name":"Adaptive Dynamic Programming Control","score":0.0,"subfield":{"id":"https://openalex.org/subfields/2207","display_name":"Control and Systems Engineering"},"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/latent-dynamics-models","display_name":"latent dynamics models","score":0.7570000290870667},{"id":"https://openalex.org/keywords/thompson-sampling","display_name":"Thompson sampling","score":0.6980000138282776},{"id":"https://openalex.org/keywords/exploration-strategy","display_name":"exploration strategy","score":0.7250000238418579},{"id":"https://openalex.org/keywords/zero-shot-transfer","display_name":"zero-shot transfer","score":0.8579999804496765},{"id":"https://openalex.org/keywords/model-uncertainty","display_name":"model uncertainty","score":0.6909999847412109},{"id":"https://openalex.org/keywords/d4rl","display_name":"D4RL","score":0.5210000276565552},{"id":"https://openalex.org/keywords/locomotor-control","display_name":"locomotion control","score":0.5460000038146973}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6638311147689819}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/most60774.2024.00026","doi":"https://doi.org/10.1109/most60774.2024.00026","is_oa":false,"landing_page_url":"http://dx.doi.org/10.1109/most60774.2024.00026","pdf_url":null,"source":{"id":"https://openalex.org/S7407088997","display_name":"IEEE International Conference on Mobility, Operations, Services and Technologies (MOST)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"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 Mobility, Operations, Services and Technologies (MOST)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"study_designs":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":40,"referenced_works":["https://openalex.org/W146900863","https://openalex.org/W834081922","https://openalex.org/W1492106702","https://openalex.org/W1987034518","https://openalex.org/W2100495367","https://openalex.org/W2584986912","https://openalex.org/W2604763608","https://openalex.org/W2781585732","https://openalex.org/W2781726626","https://openalex.org/W2804020409","https://openalex.org/W2805762288","https://openalex.org/W2898917980","https://openalex.org/W2900152462","https://openalex.org/W2904453761","https://openalex.org/W2914921993","https://openalex.org/W2922723479","https://openalex.org/W2950564923","https://openalex.org/W2975909688","https://openalex.org/W3015437096","https://openalex.org/W3016525976","https://openalex.org/W3028766998","https://openalex.org/W3033324992","https://openalex.org/W3048825312","https://openalex.org/W3102317072","https://openalex.org/W3103605161","https://openalex.org/W3106426955","https://openalex.org/W3132674603","https://openalex.org/W3213247705","https://openalex.org/W3214251933","https://openalex.org/W3216078707","https://openalex.org/W4212774754","https://openalex.org/W4221155015","https://openalex.org/W4221158443","https://openalex.org/W4221164079","https://openalex.org/W4285604474","https://openalex.org/W4320342971","https://openalex.org/W4409147637","https://openalex.org/W6750253780","https://openalex.org/W6776601253","https://openalex.org/W7133216847"],"related_works":["https://openalex.org/W3048825312","https://openalex.org/W4285604474","https://openalex.org/W4393159768","https://openalex.org/W4403573525","https://openalex.org/W4403487451","https://openalex.org/W7196931009","https://openalex.org/W4417097827","https://openalex.org/W2950564923","https://openalex.org/W3028766998","https://openalex.org/W3106426955"],"abstract_inverted_index":{"Offline":[0,64],"planning":[1,21,43,113,158],"has":[2],"recently":[3],"emerged":[4],"as":[5],"a":[6,92,101,134,138,193],"promising":[7],"reinforcement":[8],"learning":[9,82,91],"(RL)":[10],"paradigm":[11],"for":[12,35],"locomotion":[13],"and":[14,31,49,99,118,164,180,196],"control":[15],"tasks.":[16],"In":[17],"particular,":[18],"model-based":[19,41,156],"offline":[20,29,42,97,157,200],"learns":[22],"an":[23,108],"approximate":[24],"dynamics":[25,93],"model":[26,81,94,178],"from":[27,51,141],"the":[28,85,115,121,129,154,161],"dataset,":[30],"then":[32],"uses":[33],"it":[34],"rollout-aided":[36],"decision-time":[37],"planning.":[38,201],"Nevertheless,":[39],"existing":[40],"algorithms":[44,159],"could":[45],"be":[46,133],"overly":[47],"conservative":[48],"suffer":[50],"compounding":[52,88],"modeling":[53],"errors.":[54],"To":[55],"tackle":[56],"these":[57,125],"challenges,":[58],"we":[59],"propose":[60],"L-MBOP-E":[61,151,191],"(Latent-Model":[62],"Based":[63],"Planning":[65],"with":[66,95,107,186],"Extrinsic":[67],"policy":[68,110,117,131,136,139],"guided":[69],"exploration)":[70],"that":[71,150,190],"is":[72],"built":[73],"on":[74,160,183],"two":[75,126],"key":[76],"ideas:":[77],"1)":[78],"low-dimensional":[79],"latent":[80],"to":[83,111,199],"reduce":[84],"effects":[86],"of":[87,124],"errors":[89],"when":[90],"limited":[96],"data,":[98],"2)":[100],"Thompson":[102],"Sampling":[103],"based":[104],"exploration":[105],"strategy":[106],"extrinsic":[109,130],"guide":[112],"beyond":[114],"behavior":[116],"hence":[119],"get":[120],"best":[122],"out":[123],"policies,":[127],"where":[128],"can":[132],"meta-learned":[135],"or":[137],"learned":[140],"another":[142],"similar":[143],"RL":[144],"task.":[145],"Extensive":[146],"experimental":[147],"results":[148],"demonstrate":[149],"significantly":[152],"outperforms":[153],"state-of-the-art":[155],"MuJoCo":[162],"D4RL":[163],"Deepmind":[165],"Control":[166],"tasks,":[167],"yielding":[168],"more":[169,194],"than":[170],"200%":[171],"gains":[172],"in":[173],"some":[174],"cases.":[175],"Furthermore,":[176],"reduced":[177],"uncertainty":[179],"superior":[181],"performance":[182],"new":[184],"tasks":[185],"zero-shot":[187],"adaptation":[188],"indicates":[189],"provides":[192],"flexible":[195],"lightweight":[197],"solution":[198]},"counts_by_year":[],"updated_date":"2026-11-14T11:04:58.165337","created_date":"2024-07-31T00:00:00"}