{"id":"https://openalex.org/W3193667944","doi":null,"title":"Prior Is All You Need to Improve the Robustness and Safety for the First Time Deployment of Meta RL.","display_name":"Prior Is All You Need to Improve the Robustness and Safety for the First Time Deployment of Meta RL.","publication_year":2021,"publication_date":"2021-08-19","ids":{"openalex":"https://openalex.org/W3193667944","mag":"3193667944"},"language":"en","primary_location":{"id":"mag:3193667944","doi":null,"is_oa":true,"landing_page_url":"https://arxiv.org/pdf/2108.08448","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":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"arXiv (Cornell University)","raw_type":null},"volume":null,"type":"preprint","is_traditional":true,"indexed_in":[],"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/A5109870380","display_name":"Lu Wen","orcid":"https://orcid.org/0009-0006-5558-2820","observed_orcids":["https://orcid.org/0009-0006-5558-2820"]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Lu Wen","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5045427668","display_name":"Songan Zhang","orcid":"https://orcid.org/0000-0002-3238-5406","observed_orcids":["https://orcid.org/0000-0002-3238-5406"]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Songan Zhang","raw_affiliation_strings":[],"raw_orcid":"https://orcid.org/0000-0002-3238-5406","affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5034788095","display_name":"H. Eric Tseng","orcid":"https://orcid.org/0000-0001-9544-4226","observed_orcids":["https://orcid.org/0000-0001-9544-4226"]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"H. Eric Tseng","raw_affiliation_strings":[],"raw_orcid":"https://orcid.org/0000-0001-9544-4226","affiliations":[]},{"author_position":"middle","author":{"id":null,"display_name":"Baljeet Singh","orcid":"https://orcid.org/0000-0001-8706-6309","observed_orcids":["https://orcid.org/0000-0001-8706-6309"]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Baljeet Singh","raw_affiliation_strings":[],"raw_orcid":"https://orcid.org/0000-0001-8706-6309","affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5015550681","display_name":"Dimitar Filev","orcid":"https://orcid.org/0000-0001-7127-6782","observed_orcids":["https://orcid.org/0000-0001-7127-6782"]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Dimitar Filev","raw_affiliation_strings":[],"raw_orcid":"https://orcid.org/0000-0001-7127-6782","affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5019025642","display_name":"Huei Peng","orcid":"https://orcid.org/0000-0002-1844-3163","observed_orcids":["https://orcid.org/0000-0002-1844-3163"]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Huei Peng","raw_affiliation_strings":[],"raw_orcid":"https://orcid.org/0000-0002-1844-3163","affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":0,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":1,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":null,"last_page":null},"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/T11307","display_name":"Domain Adaptation and Few-Shot Learning","score":9.999999747378752e-05,"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/meta-reinforcement-learning","display_name":"meta-reinforcement learning","score":0.9769999980926514},{"id":"https://openalex.org/keywords/pearl","display_name":"pearls","score":0.9309999942779541},{"id":"https://openalex.org/keywords/q-network","display_name":"Q-network","score":0.5509999990463257},{"id":"https://openalex.org/keywords/autonomous-vehicles","display_name":"autonomous vehicles","score":0.777999997138977},{"id":"https://openalex.org/keywords/robot-control","display_name":"robot control","score":0.5559999942779541},{"id":"https://openalex.org/keywords/safety-critical-decision-making","display_name":"safety-critical decision-making","score":0.9020000100135803}],"concepts":[{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.8228272199630737},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.782850444316864},{"id":"https://openalex.org/C2779251273","wikidata":"https://www.wikidata.org/wiki/Q43436","display_name":"Pearl","level":2,"score":0.7451450824737549},{"id":"https://openalex.org/C63479239","wikidata":"https://www.wikidata.org/wiki/Q7353546","display_name":"Robustness (evolution)","level":3,"score":0.686343789100647},{"id":"https://openalex.org/C49937458","wikidata":"https://www.wikidata.org/wiki/Q2599292","display_name":"Probabilistic logic","level":2,"score":0.5984320640563965},{"id":"https://openalex.org/C105339364","wikidata":"https://www.wikidata.org/wiki/Q2297740","display_name":"Software deployment","level":2,"score":0.5503291487693787},{"id":"https://openalex.org/C90509273","wikidata":"https://www.wikidata.org/wiki/Q11012","display_name":"Robot","level":2,"score":0.491039514541626},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.47289884090423584},{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.4718962609767914},{"id":"https://openalex.org/C2776135515","wikidata":"https://www.wikidata.org/wiki/Q17143721","display_name":"Regularization (linguistics)","level":2,"score":0.4273892641067505},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.41111159324645996},{"id":"https://openalex.org/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","level":0,"score":0.0},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0},{"id":"https://openalex.org/C205649164","wikidata":"https://www.wikidata.org/wiki/Q1071","display_name":"Geography","level":0,"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/C13280743","wikidata":"https://www.wikidata.org/wiki/Q131089","display_name":"Geodesy","level":1,"score":0.0},{"id":"https://openalex.org/C27206212","wikidata":"https://www.wikidata.org/wiki/Q34178","display_name":"Theology","level":1,"score":0.0},{"id":"https://openalex.org/C104317684","wikidata":"https://www.wikidata.org/wiki/Q7187","display_name":"Gene","level":2,"score":0.0},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"mag:3193667944","doi":null,"is_oa":true,"landing_page_url":"https://arxiv.org/pdf/2108.08448","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":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"arXiv (Cornell University)","raw_type":null}],"best_oa_location":{"id":"mag:3193667944","doi":null,"is_oa":true,"landing_page_url":"https://arxiv.org/pdf/2108.08448","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":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"arXiv (Cornell University)","raw_type":null},"sustainable_development_goals":[],"study_designs":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":25,"referenced_works":["https://openalex.org/W1845972764","https://openalex.org/W1965455100","https://openalex.org/W2085842743","https://openalex.org/W2158782408","https://openalex.org/W2550182557","https://openalex.org/W2557579533","https://openalex.org/W2578206533","https://openalex.org/W2604763608","https://openalex.org/W2767328598","https://openalex.org/W2794363191","https://openalex.org/W2795900505","https://openalex.org/W2895899670","https://openalex.org/W2923504512","https://openalex.org/W2963176272","https://openalex.org/W2971014752","https://openalex.org/W2979869797","https://openalex.org/W2982536628","https://openalex.org/W2996894943","https://openalex.org/W3020718655","https://openalex.org/W3104364497","https://openalex.org/W3115648115","https://openalex.org/W3131969754","https://openalex.org/W3206106208","https://openalex.org/W3209381383","https://openalex.org/W4302288054"],"related_works":["https://openalex.org/W4312559878","https://openalex.org/W7213300035","https://openalex.org/W4411399924","https://openalex.org/W7196934227","https://openalex.org/W7197479741","https://openalex.org/W7133193675","https://openalex.org/W7116956745","https://openalex.org/W4226220005","https://openalex.org/W4415799127","https://openalex.org/W7124262094"],"abstract_inverted_index":{"The":[0,165],"field":[1,88],"of":[2,23,35,46,62,118,152,167,198,208],"Meta":[3],"Reinforcement":[4],"Learning":[5],"(Meta-RL)":[6],"has":[7],"seen":[8],"substantial":[9],"advancements":[10],"recently.":[11],"In":[12,94],"particular,":[13],"off-policy":[14],"methods":[15],"were":[16],"developed":[17],"to":[18,70,146,157,180,206],"improve":[19,147],"the":[20,36,60,63,75,99,106,130,139,148,153,162,168,190,196,199,209],"data":[21],"efficiency":[22],"Meta-RL":[24,49],"techniques.":[25],"\\textit{Probabilistic":[26],"embeddings":[27],"for":[28,39,74,83,108,137,161],"actor-critic":[29],"RL}":[30],"(PEARL)":[31],"is":[32,53,68,80,171,202],"currently":[33],"one":[34],"leading":[37],"approaches":[38],"multi-MDP":[40],"adaptation":[41],"problems.":[42,188],"A":[43],"major":[44],"drawback":[45],"many":[47],"existing":[48],"methods,":[50],"including":[51,87,184],"PEARL,":[52,119],"that":[54,195,207],"they":[55],"do":[56],"not":[57],"explicitly":[58],"consider":[59],"safety":[61,111,151,197],"prior":[64,110,126,143,200],"policy":[65,107,201],"when":[66],"it":[67],"exposed":[69],"a":[71,125,134,158],"new":[72,135,159],"task":[73,160],"very":[76,81],"first":[77,163],"time.":[78,164],"This":[79],"important":[82],"some":[84],"real-world":[85],"applications,":[86],"robots":[89,181],"and":[90,112,133,150,182],"Autonomous":[91],"Vehicles":[92],"(AVs).":[93],"this":[95],"paper,":[96],"we":[97,193],"develop":[98],"PEARL":[100,211],"PLUS":[101],"(PEARL$^+$)":[102],"algorithm,":[103],"which":[104],"optimizes":[105],"both":[109],"posterior":[113],"adaptation.":[114],"Building":[115],"on":[116],"top":[117],"our":[120],"proposed":[121],"PEARL$^+$":[122,169],"algorithm":[123],"introduces":[124],"regularization":[127],"term":[128],"in":[129],"reward":[131],"function":[132],"Q-network":[136],"recovering":[138],"state-action":[140],"value":[141],"with":[142],"context":[144],"assumption,":[145],"robustness":[149],"trained":[154],"network":[155],"exposing":[156],"performance":[166],"method":[170],"demonstrated":[172],"by":[173],"solving":[174],"three":[175],"safety-critical":[176],"decision-making":[177],"problems":[178],"related":[179],"AVs,":[183],"two":[185],"MuJoCo":[186],"benchmark":[187],"From":[189],"simulation":[191],"experiments,":[192],"show":[194],"significantly":[203],"improved":[204],"compared":[205],"original":[210],"method.":[212]},"counts_by_year":[{"year":2024,"cited_by_count":1}],"updated_date":"2026-11-04T10:54:05.112534","created_date":"2021-08-30T00:00:00"}