{"id":"https://openalex.org/W4312559878","doi":"https://doi.org/10.1109/iros47612.2022.9981621","title":"Improved Robustness and Safety for Pre-Adaptation of Meta Reinforcement Learning with Prior Regularization","display_name":"Improved Robustness and Safety for Pre-Adaptation of Meta Reinforcement Learning with Prior Regularization","publication_year":2022,"publication_date":"2022-10-23","ids":{"openalex":"https://openalex.org/W4312559878","doi":"https://doi.org/10.1109/iros47612.2022.9981621"},"language":"en","primary_location":{"id":"doi:10.1109/iros47612.2022.9981621","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iros47612.2022.9981621","pdf_url":null,"source":{"id":"https://openalex.org/S4363607704","display_name":"2022 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2022 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS)","raw_type":"proceedings-article"},"type":"article","indexed_in":["arxiv","crossref"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2108.08448","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5076564877","display_name":"Wenpeng L\u00fc","orcid":"https://orcid.org/0000-0002-1840-3540"},"institutions":[{"id":"https://openalex.org/I27837315","display_name":"University of Michigan\u2013Ann Arbor","ror":"https://ror.org/00jmfr291","country_code":"US","type":"education","lineage":["https://openalex.org/I27837315"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Lu Wen","raw_affiliation_strings":["Mechanical Engineering, University of Michigan"],"affiliations":[{"raw_affiliation_string":"Mechanical Engineering, University of Michigan","institution_ids":["https://openalex.org/I27837315"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5045427668","display_name":"Songan Zhang","orcid":"https://orcid.org/0000-0002-3238-5406"},"institutions":[{"id":"https://openalex.org/I4210166862","display_name":"Advanced Engineering (Czechia)","ror":"https://ror.org/05w67p097","country_code":"CZ","type":"company","lineage":["https://openalex.org/I4210166862"]}],"countries":["CZ"],"is_corresponding":false,"raw_author_name":"Songan Zhang","raw_affiliation_strings":["Ford Research and Advanced Engineering"],"affiliations":[{"raw_affiliation_string":"Ford Research and Advanced Engineering","institution_ids":["https://openalex.org/I4210166862"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5034788095","display_name":"H. Eric Tseng","orcid":"https://orcid.org/0000-0001-9544-4226"},"institutions":[{"id":"https://openalex.org/I4210166862","display_name":"Advanced Engineering (Czechia)","ror":"https://ror.org/05w67p097","country_code":"CZ","type":"company","lineage":["https://openalex.org/I4210166862"]}],"countries":["CZ"],"is_corresponding":false,"raw_author_name":"H. Eric Tseng","raw_affiliation_strings":["Ford Research and Advanced Engineering"],"affiliations":[{"raw_affiliation_string":"Ford Research and Advanced Engineering","institution_ids":["https://openalex.org/I4210166862"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5031454329","display_name":"Baljeet Singh","orcid":"https://orcid.org/0000-0001-8706-6309"},"institutions":[{"id":"https://openalex.org/I4210166862","display_name":"Advanced Engineering (Czechia)","ror":"https://ror.org/05w67p097","country_code":"CZ","type":"company","lineage":["https://openalex.org/I4210166862"]}],"countries":["CZ"],"is_corresponding":false,"raw_author_name":"Baljeet Singh","raw_affiliation_strings":["Ford Research and Advanced Engineering"],"affiliations":[{"raw_affiliation_string":"Ford Research and Advanced Engineering","institution_ids":["https://openalex.org/I4210166862"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5015550681","display_name":"Dimitar Filev","orcid":"https://orcid.org/0000-0001-7127-6782"},"institutions":[{"id":"https://openalex.org/I4210166862","display_name":"Advanced Engineering (Czechia)","ror":"https://ror.org/05w67p097","country_code":"CZ","type":"company","lineage":["https://openalex.org/I4210166862"]}],"countries":["CZ"],"is_corresponding":false,"raw_author_name":"Dimitar Filev","raw_affiliation_strings":["Ford Research and Advanced Engineering"],"affiliations":[{"raw_affiliation_string":"Ford Research and Advanced Engineering","institution_ids":["https://openalex.org/I4210166862"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5019025642","display_name":"Huei Peng","orcid":"https://orcid.org/0000-0002-1844-3163"},"institutions":[{"id":"https://openalex.org/I27837315","display_name":"University of Michigan\u2013Ann Arbor","ror":"https://ror.org/00jmfr291","country_code":"US","type":"education","lineage":["https://openalex.org/I27837315"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Huei Peng","raw_affiliation_strings":["Mechanical Engineering, University of Michigan"],"affiliations":[{"raw_affiliation_string":"Mechanical Engineering, University of Michigan","institution_ids":["https://openalex.org/I27837315"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":6,"corresponding_author_ids":["https://openalex.org/A5076564877"],"corresponding_institution_ids":["https://openalex.org/I27837315"],"apc_list":null,"apc_paid":null,"fwci":0.1047,"has_fulltext":false,"cited_by_count":1,"citation_normalized_percentile":{"value":0.32972916,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":94},"biblio":{"volume":"33","issue":null,"first_page":"8987","last_page":"8994"},"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/T12794","display_name":"Adaptive Dynamic Programming Control","score":0.9980000257492065,"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"}},{"id":"https://openalex.org/T12676","display_name":"Machine Learning and ELM","score":0.9797999858856201,"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":0.7842308282852173},{"id":"https://openalex.org/keywords/robustness","display_name":"Robustness (evolution)","score":0.7089618444442749},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.63039231300354},{"id":"https://openalex.org/keywords/regularization","display_name":"Regularization (linguistics)","score":0.545203685760498},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.49183082580566406},{"id":"https://openalex.org/keywords/meta-analysis","display_name":"Meta-analysis","score":0.4254401922225952},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.4144967794418335},{"id":"https://openalex.org/keywords/medicine","display_name":"Medicine","score":0.11270913481712341}],"concepts":[{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.7842308282852173},{"id":"https://openalex.org/C63479239","wikidata":"https://www.wikidata.org/wiki/Q7353546","display_name":"Robustness (evolution)","level":3,"score":0.7089618444442749},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.63039231300354},{"id":"https://openalex.org/C2776135515","wikidata":"https://www.wikidata.org/wiki/Q17143721","display_name":"Regularization (linguistics)","level":2,"score":0.545203685760498},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.49183082580566406},{"id":"https://openalex.org/C95190672","wikidata":"https://www.wikidata.org/wiki/Q815382","display_name":"Meta-analysis","level":2,"score":0.4254401922225952},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.4144967794418335},{"id":"https://openalex.org/C71924100","wikidata":"https://www.wikidata.org/wiki/Q11190","display_name":"Medicine","level":0,"score":0.11270913481712341},{"id":"https://openalex.org/C104317684","wikidata":"https://www.wikidata.org/wiki/Q7187","display_name":"Gene","level":2,"score":0.0},{"id":"https://openalex.org/C55493867","wikidata":"https://www.wikidata.org/wiki/Q7094","display_name":"Biochemistry","level":1,"score":0.0},{"id":"https://openalex.org/C126322002","wikidata":"https://www.wikidata.org/wiki/Q11180","display_name":"Internal medicine","level":1,"score":0.0},{"id":"https://openalex.org/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","level":0,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/iros47612.2022.9981621","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iros47612.2022.9981621","pdf_url":null,"source":{"id":"https://openalex.org/S4363607704","display_name":"2022 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2022 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS)","raw_type":"proceedings-article"},{"id":"pmh:oai:arXiv.org:2108.08448","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2108.08448","pdf_url":"https://arxiv.org/pdf/2108.08448","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"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":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2108.08448","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2108.08448","pdf_url":"https://arxiv.org/pdf/2108.08448","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"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":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":46,"referenced_works":["https://openalex.org/W1845972764","https://openalex.org/W1965455100","https://openalex.org/W2085842743","https://openalex.org/W2158782408","https://openalex.org/W2578206533","https://openalex.org/W2604763608","https://openalex.org/W2767328598","https://openalex.org/W2781726626","https://openalex.org/W2788904251","https://openalex.org/W2914953695","https://openalex.org/W2935062270","https://openalex.org/W2952526277","https://openalex.org/W2979869797","https://openalex.org/W2996894943","https://openalex.org/W3008102108","https://openalex.org/W3020718655","https://openalex.org/W3035389468","https://openalex.org/W3036176146","https://openalex.org/W3115648115","https://openalex.org/W3127031155","https://openalex.org/W3134825596","https://openalex.org/W3206106208","https://openalex.org/W3209381383","https://openalex.org/W4293469690","https://openalex.org/W4294646197","https://openalex.org/W4300971732","https://openalex.org/W4302288054","https://openalex.org/W6639175102","https://openalex.org/W6729433768","https://openalex.org/W6729906282","https://openalex.org/W6731982132","https://openalex.org/W6736057607","https://openalex.org/W6745335788","https://openalex.org/W6747473740","https://openalex.org/W6748600884","https://openalex.org/W6750254146","https://openalex.org/W6759190994","https://openalex.org/W6760698134","https://openalex.org/W6761008914","https://openalex.org/W6768602481","https://openalex.org/W6768791272","https://openalex.org/W6771838272","https://openalex.org/W6779481570","https://openalex.org/W6779605632","https://openalex.org/W6791360822","https://openalex.org/W6792084852"],"related_works":["https://openalex.org/W4306904969","https://openalex.org/W2138720691","https://openalex.org/W4362501864","https://openalex.org/W4380318855","https://openalex.org/W2031695474","https://openalex.org/W2024136090","https://openalex.org/W4391331176","https://openalex.org/W2586732548","https://openalex.org/W3049728571","https://openalex.org/W2964765435"],"abstract_inverted_index":{"Meta":[0],"Reinforcement":[1],"Learning":[2],"(Meta-RL)":[3],"has":[4],"seen":[5],"substantial":[6],"advancements":[7],"recently.":[8],"In":[9,89],"particular,":[10],"off-policy":[11],"methods":[12],"were":[13],"developed":[14],"to":[15,66,150,154,165,188,215,220],"improve":[16,151],"the":[17,56,59,71,94,105,134,143,152,161,170,198,206],"data":[18],"efficiency":[19],"of":[20,42,58,119,160,175,205],"Meta-RL":[21,45],"techniques.":[22],"Probabilistic":[23],"embeddings":[24],"for":[25,35,70,77,107,141,169],"actor-critic":[26],"<tex":[27],"xmlns:mml=\"http://www.w3.org/1998/Math/MathML\"":[28,99,125,178],"xmlns:xlink=\"http://www.w3.org/1999/xlink\">$\\boldsymbol{RL}$</tex>":[29],"(PEARL)":[30],"is":[31,49,64,75,180,209],"a":[32,67,129,138,166],"leading":[33],"approach":[34],"multi-MDP":[36],"adaptation":[37],"problems.":[38,196],"A":[39],"major":[40],"drawback":[41],"many":[43,78],"existing":[44],"methods,":[46],"including":[47,82,192],"PEARL,":[48,120],"that":[50,203],"they":[51],"do":[52],"not":[53],"explicitly":[54],"consider":[55],"safety":[57,111,159,204],"prior":[60,109,130,147,207],"policy":[61,106,208],"when":[62],"it":[63],"exposed":[65,164],"new":[68,139,167],"task":[69,155,168,216],"first":[72,171],"time.":[73,172],"Safety":[74],"essential":[76],"real":[79],"world":[80],"applications,":[81],"field":[83],"robots":[84,189],"and":[85,112,137,158,190,212],"Autonomous":[86],"Vehicles":[87],"(AVs),":[88],"this":[90],"paper,":[91],"we":[92,201],"develop":[93],"PEARL":[95,123,176],"PLUS":[96],"(PEARL":[97],"<sup":[98,124,177],"xmlns:xlink=\"http://www.w3.org/1999/xlink\">+</sup>":[100,126,179],")":[101],"algorithm,":[102],"which":[103],"optimizes":[104],"both":[108],"(pre-adaptation)":[110],"posterior":[113],"(after-adaptation)":[114],"performance.":[115],"Building":[116],"on":[117],"top":[118],"our":[121],"proposed":[122],"algorithm":[127],"introduces":[128],"regularization":[131],"term":[132],"in":[133],"reward":[135],"function":[136],"Q-network":[140],"recovering":[142],"state-action":[144],"value":[145],"under":[146],"context":[148],"assumptions,":[149],"robustness":[153],"distribution":[156,217],"shift":[157,218],"trained":[162],"network":[163],"The":[173],"performance":[174],"validated":[181],"by":[182],"solving":[183],"three":[184],"safety-critical":[185],"problems":[186],"related":[187],"AVs,":[191],"two":[193],"MuJoCo":[194],"benchmark":[195],"From":[197],"simulation":[199],"experiments,":[200],"show":[202],"significantly":[210],"improved":[211],"more":[213],"robust":[214],"compared":[219],"PEARL.":[221]},"counts_by_year":[{"year":2024,"cited_by_count":1}],"updated_date":"2026-03-20T23:20:44.827607","created_date":"2023-01-05T00:00:00"}