{"id":"https://openalex.org/W3005787005","doi":null,"title":"Provably Convergent Policy Gradient Methods for Model-Agnostic Meta-Reinforcement Learning","display_name":"Provably Convergent Policy Gradient Methods for Model-Agnostic Meta-Reinforcement Learning","publication_year":2020,"publication_date":"2020-02-12","ids":{"openalex":"https://openalex.org/W3005787005","mag":"3005787005"},"language":"en","primary_location":{"id":"mag:3005787005","doi":null,"is_oa":true,"landing_page_url":"https://arxiv.org/pdf/2002.05135","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/2002.05135","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5016741616","display_name":"Alireza Fallah","orcid":"https://orcid.org/0000-0002-9295-704X","observed_orcids":["https://orcid.org/0000-0002-9295-704X"]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Alireza Fallah","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5008417632","display_name":"Aryan Mokhtari","orcid":"https://orcid.org/0000-0001-6603-0091","observed_orcids":["https://orcid.org/0000-0001-6603-0091"]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Aryan Mokhtari","raw_affiliation_strings":[],"raw_orcid":"https://orcid.org/0000-0001-6603-0091","affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5067307504","display_name":"Asuman Ozdaglar","orcid":"https://orcid.org/0000-0002-1827-1285","observed_orcids":["https://orcid.org/0000-0002-1827-1285"]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Asuman Ozdaglar","raw_affiliation_strings":[],"raw_orcid":"https://orcid.org/0000-0002-1827-1285","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":13,"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":0.9976000189781189,"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":0.9976000189781189,"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":0.0020000000949949026,"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/T11612","display_name":"Stochastic Gradient Optimization Techniques","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"}}],"keywords":[{"id":"https://openalex.org/keywords/model-agnostic-meta-learning","display_name":"model-agnostic meta-learning","score":0.953000009059906},{"id":"https://openalex.org/keywords/meta-reinforcement-learning","display_name":"meta-reinforcement learning","score":0.9929999709129333},{"id":"https://openalex.org/keywords/convergence-guarantees","display_name":"convergence guarantees","score":0.8669999837875366},{"id":"https://openalex.org/keywords/iteration-complexity","display_name":"iteration complexity","score":0.8109999895095825},{"id":"https://openalex.org/keywords/sample-complexity","display_name":"sample complexity","score":0.9990000128746033},{"id":"https://openalex.org/keywords/first-order-stationary-points","display_name":"first-order stationary points","score":0.7509999871253967}],"concepts":[{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.9143815040588379},{"id":"https://openalex.org/C106189395","wikidata":"https://www.wikidata.org/wiki/Q176789","display_name":"Markov decision process","level":3,"score":0.7357082366943359},{"id":"https://openalex.org/C2777303404","wikidata":"https://www.wikidata.org/wiki/Q759757","display_name":"Convergence (economics)","level":2,"score":0.7180693745613098},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7173606157302856},{"id":"https://openalex.org/C2781002164","wikidata":"https://www.wikidata.org/wiki/Q6822311","display_name":"Meta learning (computer science)","level":3,"score":0.520841658115387},{"id":"https://openalex.org/C45374587","wikidata":"https://www.wikidata.org/wiki/Q12525525","display_name":"Computation","level":2,"score":0.5102331638336182},{"id":"https://openalex.org/C126255220","wikidata":"https://www.wikidata.org/wiki/Q141495","display_name":"Mathematical optimization","level":1,"score":0.4815516769886017},{"id":"https://openalex.org/C98763669","wikidata":"https://www.wikidata.org/wiki/Q176645","display_name":"Markov chain","level":2,"score":0.46595484018325806},{"id":"https://openalex.org/C55479107","wikidata":"https://www.wikidata.org/wiki/Q97663916","display_name":"Stochastic approximation","level":3,"score":0.4534071981906891},{"id":"https://openalex.org/C198531522","wikidata":"https://www.wikidata.org/wiki/Q485146","display_name":"Sample (material)","level":2,"score":0.45114561915397644},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4139159619808197},{"id":"https://openalex.org/C159886148","wikidata":"https://www.wikidata.org/wiki/Q176645","display_name":"Markov process","level":2,"score":0.3779865503311157},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.26999765634536743},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.2624357342720032},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.2092823088169098},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.08126312494277954},{"id":"https://openalex.org/C38652104","wikidata":"https://www.wikidata.org/wiki/Q3510521","display_name":"Computer security","level":1,"score":0.0},{"id":"https://openalex.org/C50522688","wikidata":"https://www.wikidata.org/wiki/Q189833","display_name":"Economic growth","level":1,"score":0.0},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","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},{"id":"https://openalex.org/C187736073","wikidata":"https://www.wikidata.org/wiki/Q2920921","display_name":"Management","level":1,"score":0.0},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"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/C43617362","wikidata":"https://www.wikidata.org/wiki/Q170050","display_name":"Chromatography","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"mag:3005787005","doi":null,"is_oa":true,"landing_page_url":"https://arxiv.org/pdf/2002.05135","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:3005787005","doi":null,"is_oa":true,"landing_page_url":"https://arxiv.org/pdf/2002.05135","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":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":16,"referenced_works":["https://openalex.org/W2119717200","https://openalex.org/W2125612430","https://openalex.org/W2144446635","https://openalex.org/W2156737235","https://openalex.org/W2550182557","https://openalex.org/W2604763608","https://openalex.org/W2787501667","https://openalex.org/W2903630557","https://openalex.org/W2945007422","https://openalex.org/W2949369413","https://openalex.org/W2949555518","https://openalex.org/W2952689429","https://openalex.org/W2963176272","https://openalex.org/W2970697704","https://openalex.org/W2971014752","https://openalex.org/W2981344907"],"related_works":["https://openalex.org/W3212442854","https://openalex.org/W3008360155","https://openalex.org/W3042103612","https://openalex.org/W3037724881","https://openalex.org/W3130974966","https://openalex.org/W4297899395","https://openalex.org/W2804329956","https://openalex.org/W7084406210","https://openalex.org/W3035175316","https://openalex.org/W4391019807"],"abstract_inverted_index":{"We":[0,95,127],"consider":[1],"Model-Agnostic":[2],"Meta-Learning":[3],"(MAML)":[4],"methods":[5],"for":[6,41,56,122],"Reinforcement":[7],"Learning":[8,88],"(RL)":[9],"problems":[10,58],"where":[11,137],"the":[12,42,81,97,112,118,135,150,153],"goal":[13],"is":[14,54,147],"to":[15,66,104,111,134],"find":[16,105],"a":[17,67,78],"policy":[18,39,144],"(using":[19],"data":[20],"from":[21],"several":[22],"tasks":[23],"represented":[24],"by":[25,34],"Markov":[26],"Decision":[27],"Processes":[28],"(MDPs))":[29],"that":[30],"can":[31],"be":[32],"updated":[33],"one":[35,140],"step":[36,53,141],"of":[37,61,70,80,102,114,142],"stochastic":[38,48,143],"gradient":[40,145],"realized":[43],"MDP.":[44],"In":[45],"particular,":[46],"using":[47],"gradients":[49,63],"in":[50,149],"MAML":[51,82],"update":[52,151],"crucial":[55],"RL":[57],"since":[59],"computation":[60],"exact":[62],"requires":[64],"access":[65],"large":[68],"number":[69],"possible":[71],"trajectories.":[72],"For":[73],"this":[74],"formulation,":[75],"we":[76],"propose":[77],"variant":[79],"method,":[83],"named":[84],"Stochastic":[85],"Gradient":[86],"Meta-Reinforcement":[87],"(SG-MRL),":[89],"and":[90,99],"study":[91],"its":[92],"convergence":[93,120],"properties.":[94],"derive":[96],"iteration":[98],"sample":[100],"complexity":[101],"SG-MRL":[103],"an":[106],"$\\epsilon$-first-order":[107],"stationary":[108],"point,":[109],"which,":[110],"best":[113],"our":[115,131],"knowledge,":[116],"provides":[117],"first":[119],"guarantee":[121],"model-agnostic":[123],"meta-reinforcement":[124],"learning":[125],"algorithms.":[126],"further":[128],"show":[129],"how":[130],"results":[132],"extend":[133],"case":[136],"more":[138],"than":[139],"method":[146],"used":[148],"during":[152],"test":[154],"time.":[155]},"counts_by_year":[{"year":2024,"cited_by_count":1},{"year":2021,"cited_by_count":9},{"year":2020,"cited_by_count":3}],"updated_date":"2026-11-04T10:54:05.112534","created_date":"2020-02-24T00:00:00"}