{"id":"https://openalex.org/W4392251671","doi":"https://doi.org/10.1109/lra.2024.3371260","title":"Data-Efficient Task Generalization via Probabilistic Model-Based Meta Reinforcement Learning","display_name":"Data-Efficient Task Generalization via Probabilistic Model-Based Meta Reinforcement Learning","publication_year":2024,"publication_date":"2024-02-28","ids":{"openalex":"https://openalex.org/W4392251671","doi":"https://doi.org/10.1109/lra.2024.3371260"},"language":"en","primary_location":{"id":"doi:10.1109/lra.2024.3371260","is_oa":false,"landing_page_url":"https://doi.org/10.1109/lra.2024.3371260","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/A5076560136","display_name":"Arjun Bhardwaj","orcid":"https://orcid.org/0009-0002-2469-2841"},"institutions":[{"id":"https://openalex.org/I35440088","display_name":"ETH Zurich","ror":"https://ror.org/05a28rw58","country_code":"CH","type":"education","lineage":["https://openalex.org/I2799323385","https://openalex.org/I35440088"]}],"countries":["CH"],"is_corresponding":true,"raw_author_name":"Arjun Bhardwaj","raw_affiliation_strings":["ETH Zurich, Zürich, Switzerland"],"affiliations":[{"raw_affiliation_string":"ETH Zurich, Zürich, Switzerland","institution_ids":["https://openalex.org/I35440088"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5088717202","display_name":"Jonas Rothfuss","orcid":"https://orcid.org/0000-0003-0129-0540"},"institutions":[{"id":"https://openalex.org/I35440088","display_name":"ETH Zurich","ror":"https://ror.org/05a28rw58","country_code":"CH","type":"education","lineage":["https://openalex.org/I2799323385","https://openalex.org/I35440088"]}],"countries":["CH"],"is_corresponding":false,"raw_author_name":"Jonas Rothfuss","raw_affiliation_strings":["ETH Zurich, Zürich, Switzerland"],"affiliations":[{"raw_affiliation_string":"ETH Zurich, Zürich, Switzerland","institution_ids":["https://openalex.org/I35440088"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5006117761","display_name":"Bhavya Sukhija","orcid":"https://orcid.org/0000-0001-6238-9734"},"institutions":[{"id":"https://openalex.org/I35440088","display_name":"ETH Zurich","ror":"https://ror.org/05a28rw58","country_code":"CH","type":"education","lineage":["https://openalex.org/I2799323385","https://openalex.org/I35440088"]}],"countries":["CH"],"is_corresponding":false,"raw_author_name":"Bhavya Sukhija","raw_affiliation_strings":["ETH Zurich, Zürich, Switzerland"],"affiliations":[{"raw_affiliation_string":"ETH Zurich, Zürich, Switzerland","institution_ids":["https://openalex.org/I35440088"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5056406128","display_name":"Yarden As","orcid":"https://orcid.org/0009-0005-1685-4099"},"institutions":[{"id":"https://openalex.org/I35440088","display_name":"ETH Zurich","ror":"https://ror.org/05a28rw58","country_code":"CH","type":"education","lineage":["https://openalex.org/I2799323385","https://openalex.org/I35440088"]}],"countries":["CH"],"is_corresponding":false,"raw_author_name":"Yarden As","raw_affiliation_strings":["ETH Zurich, Zürich, Switzerland"],"affiliations":[{"raw_affiliation_string":"ETH Zurich, Zürich, Switzerland","institution_ids":["https://openalex.org/I35440088"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5044258783","display_name":"Marco Hutter","orcid":"https://orcid.org/0000-0002-4285-4990"},"institutions":[{"id":"https://openalex.org/I35440088","display_name":"ETH Zurich","ror":"https://ror.org/05a28rw58","country_code":"CH","type":"education","lineage":["https://openalex.org/I2799323385","https://openalex.org/I35440088"]}],"countries":["CH"],"is_corresponding":false,"raw_author_name":"Marco Hutter","raw_affiliation_strings":["ETH Zurich, Zürich, Switzerland"],"affiliations":[{"raw_affiliation_string":"ETH Zurich, Zürich, Switzerland","institution_ids":["https://openalex.org/I35440088"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5055713873","display_name":"Stelian Coros","orcid":"https://orcid.org/0000-0001-6604-4784"},"institutions":[{"id":"https://openalex.org/I35440088","display_name":"ETH Zurich","ror":"https://ror.org/05a28rw58","country_code":"CH","type":"education","lineage":["https://openalex.org/I2799323385","https://openalex.org/I35440088"]}],"countries":["CH"],"is_corresponding":false,"raw_author_name":"Stelian Coros","raw_affiliation_strings":["ETH Zurich, Zürich, Switzerland"],"affiliations":[{"raw_affiliation_string":"ETH Zurich, Zürich, Switzerland","institution_ids":["https://openalex.org/I35440088"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5003040843","display_name":"Andreas Krause","orcid":"https://orcid.org/0000-0001-7260-9673"},"institutions":[{"id":"https://openalex.org/I35440088","display_name":"ETH Zurich","ror":"https://ror.org/05a28rw58","country_code":"CH","type":"education","lineage":["https://openalex.org/I2799323385","https://openalex.org/I35440088"]}],"countries":["CH"],"is_corresponding":false,"raw_author_name":"Andreas Krause","raw_affiliation_strings":["ETH Zurich, Zürich, Switzerland"],"affiliations":[{"raw_affiliation_string":"ETH Zurich, Zürich, Switzerland","institution_ids":["https://openalex.org/I35440088"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":7,"corresponding_author_ids":["https://openalex.org/A5076560136"],"corresponding_institution_ids":["https://openalex.org/I35440088"],"apc_list":null,"apc_paid":null,"fwci":2.1431,"has_fulltext":false,"cited_by_count":6,"citation_normalized_percentile":{"value":0.88288497,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":100},"biblio":{"volume":"9","issue":"4","first_page":"3918","last_page":"3925"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10462","display_name":"Reinforcement Learning in Robotics","score":0.9991000294685364,"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":0.9991000294685364,"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/T12761","display_name":"Data Stream Mining Techniques","score":0.9811000227928162,"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":0.9771000146865845,"subfield":{"id":"https://openalex.org/subfields/1703","display_name":"Computational Theory and Mathematics"},"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/generalization","display_name":"Generalization","score":0.807965874671936},{"id":"https://openalex.org/keywords/reinforcement-learning","display_name":"Reinforcement learning","score":0.755412757396698},{"id":"https://openalex.org/keywords/probabilistic-logic","display_name":"Probabilistic logic","score":0.7135193347930908},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.7111395001411438},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6566638350486755},{"id":"https://openalex.org/keywords/reinforcement","display_name":"Reinforcement","score":0.5173375010490417},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.46631842851638794},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.4198293685913086},{"id":"https://openalex.org/keywords/psychology","display_name":"Psychology","score":0.1782856583595276},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.11427238583564758},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.07771891355514526},{"id":"https://openalex.org/keywords/social-psychology","display_name":"Social psychology","score":0.06877455115318298}],"concepts":[{"id":"https://openalex.org/C177148314","wikidata":"https://www.wikidata.org/wiki/Q170084","display_name":"Generalization","level":2,"score":0.807965874671936},{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.755412757396698},{"id":"https://openalex.org/C49937458","wikidata":"https://www.wikidata.org/wiki/Q2599292","display_name":"Probabilistic logic","level":2,"score":0.7135193347930908},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.7111395001411438},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6566638350486755},{"id":"https://openalex.org/C67203356","wikidata":"https://www.wikidata.org/wiki/Q1321905","display_name":"Reinforcement","level":2,"score":0.5173375010490417},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.46631842851638794},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.4198293685913086},{"id":"https://openalex.org/C15744967","wikidata":"https://www.wikidata.org/wiki/Q9418","display_name":"Psychology","level":0,"score":0.1782856583595276},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.11427238583564758},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.07771891355514526},{"id":"https://openalex.org/C77805123","wikidata":"https://www.wikidata.org/wiki/Q161272","display_name":"Social psychology","level":1,"score":0.06877455115318298},{"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/C134306372","wikidata":"https://www.wikidata.org/wiki/Q7754","display_name":"Mathematical analysis","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/lra.2024.3371260","is_oa":false,"landing_page_url":"https://doi.org/10.1109/lra.2024.3371260","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":46,"referenced_works":["https://openalex.org/W99485931","https://openalex.org/W186151502","https://openalex.org/W1845972764","https://openalex.org/W2145339207","https://openalex.org/W2225156818","https://openalex.org/W2578206533","https://openalex.org/W2740020751","https://openalex.org/W2903630557","https://openalex.org/W2962872206","https://openalex.org/W2963411833","https://openalex.org/W2996795455","https://openalex.org/W3047366950","https://openalex.org/W4283790903","https://openalex.org/W4383108577","https://openalex.org/W6639949747","https://openalex.org/W6677888739","https://openalex.org/W6680139899","https://openalex.org/W6680657880","https://openalex.org/W6684809622","https://openalex.org/W6716474083","https://openalex.org/W6725708968","https://openalex.org/W6729433768","https://openalex.org/W6731982132","https://openalex.org/W6736057607","https://openalex.org/W6747473740","https://openalex.org/W6748911209","https://openalex.org/W6749700008","https://openalex.org/W6751494529","https://openalex.org/W6752342722","https://openalex.org/W6754471908","https://openalex.org/W6755476724","https://openalex.org/W6758359583","https://openalex.org/W6760698134","https://openalex.org/W6764053384","https://openalex.org/W6773539357","https://openalex.org/W6777635358","https://openalex.org/W6778000925","https://openalex.org/W6779325250","https://openalex.org/W6779911313","https://openalex.org/W6780559895","https://openalex.org/W6782399914","https://openalex.org/W6809864479","https://openalex.org/W6845261369","https://openalex.org/W6846236938","https://openalex.org/W6850204301","https://openalex.org/W6853962198"],"related_works":["https://openalex.org/W2920061524","https://openalex.org/W4310083477","https://openalex.org/W2328553770","https://openalex.org/W1977959518","https://openalex.org/W2038908348","https://openalex.org/W2107890255","https://openalex.org/W2106552856","https://openalex.org/W2145821588","https://openalex.org/W2086122291","https://openalex.org/W2501594388"],"abstract_inverted_index":{"We":[0],"introduce":[1],"PACOH-RL,":[2],"a":[3,131],"novel":[4],"model-based":[5,117,120],"Meta-Reinforcement":[6],"Learning":[7],"(Meta-RL)":[8],"algorithm":[9],"designed":[10],"to":[11,16,29,55,84,99,125],"efficiently":[12],"adapt":[13],"control":[14],"policies":[15],"changing":[17],"dynamics.":[18],"PACOH-RL":[19,60,115],"meta-learns":[20],"priors":[21],"for":[22,139],"the":[23,69,137],"dynamics":[24,31],"model,":[25],"allowing":[26],"swift":[27],"adaptation":[28,73,143],"new":[30,77,126],"with":[32],"minimal":[33],"interaction":[34],"data.":[35],"Existing":[36],"Meta-RL":[37,121],"methods":[38],"require":[39],"abundant":[40],"meta-learning":[41,70],"data,":[42],"limiting":[43],"their":[44],"applicability":[45],"in":[46,67,123,144],"settings":[47,106],"such":[48],"as":[49],"robotics,":[50],"where":[51],"data":[52,89,100],"is":[53,107],"costly":[54],"obtain.":[56],"To":[57],"address":[58],"this,":[59],"incorporates":[61],"regularization":[62],"and":[63,71,88,119],"epistemic":[64],"uncertainty":[65,82],"quantification":[66],"both":[68],"task":[72],"stages.":[74],"When":[75],"facing":[76],"dynamics,":[78],"we":[79,135],"use":[80],"these":[81],"estimates":[83],"effectively":[85],"guide":[86],"exploration":[87],"collection.":[90],"Overall,":[91],"this":[92],"enables":[93],"positive":[94],"transfer,":[95],"even":[96],"when":[97],"access":[98],"from":[101],"prior":[102],"tasks":[103],"or":[104],"dynamic":[105,127],"severely":[108],"limited.":[109],"Our":[110],"experiment":[111],"results":[112],"demonstrate":[113],"that":[114],"outperforms":[116],"RL":[118,141],"baselines":[122],"adapting":[124],"conditions.":[128,147],"Finally,":[129],"on":[130],"real":[132],"robotic":[133],"car,":[134],"showcase":[136],"potential":[138],"efficient":[140],"policy":[142],"diverse,":[145],"data-scarce":[146]},"counts_by_year":[{"year":2026,"cited_by_count":3},{"year":2025,"cited_by_count":2},{"year":2024,"cited_by_count":1}],"updated_date":"2026-03-18T14:38:29.013473","created_date":"2025-10-10T00:00:00"}