{"id":"https://openalex.org/W2995686239","doi":null,"title":"Improving Generalization in Meta Reinforcement Learning using Neural Objectives","display_name":"Improving Generalization in Meta Reinforcement Learning using Neural Objectives","publication_year":2020,"publication_date":"2020-04-30","ids":{"openalex":"https://openalex.org/W2995686239","mag":"2995686239"},"language":"en","primary_location":{"id":"mag:2995686239","doi":null,"is_oa":true,"landing_page_url":"https://arxiv.org/pdf/1910.04098","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":null,"is_accepted":false,"is_published":false,"raw_source_name":"arXiv (Cornell University)","raw_type":null},"volume":null,"type":"preprint","indexed_in":[],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/1910.04098","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5010855168","display_name":"Louis Kirsch","orcid":"https://orcid.org/0009-0001-5203-4144","observed_orcids":["https://orcid.org/0009-0001-5203-4144"]},"institutions":[{"id":"https://openalex.org/I2614128279","display_name":"Dalle Molle Institute for Artificial Intelligence Research","ror":"https://ror.org/013355g38","country_code":"CH","type":"facility","lineage":["https://openalex.org/I15196421","https://openalex.org/I2614128279","https://openalex.org/I57201433"]}],"countries":["CH"],"is_corresponding":false,"raw_author_name":"Louis Kirsch","raw_affiliation_strings":["Dalle Molle Institute for Artificial Intelligence Research, Lugano, Switzerland"],"raw_orcid":"https://orcid.org/0009-0001-5203-4144","affiliations":[{"raw_affiliation_string":"Dalle Molle Institute for Artificial Intelligence Research, Lugano, Switzerland","institution_ids":["https://openalex.org/I2614128279"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5000816835","display_name":"Sjoerd van Steenkiste","orcid":"https://orcid.org/0000-0003-4324-3021","observed_orcids":["https://orcid.org/0000-0003-4324-3021"]},"institutions":[{"id":"https://openalex.org/I2614128279","display_name":"Dalle Molle Institute for Artificial Intelligence Research","ror":"https://ror.org/013355g38","country_code":"CH","type":"facility","lineage":["https://openalex.org/I15196421","https://openalex.org/I2614128279","https://openalex.org/I57201433"]}],"countries":["CH"],"is_corresponding":false,"raw_author_name":"Sjoerd van Steenkiste","raw_affiliation_strings":["Dalle Molle Institute for Artificial Intelligence Research, Lugano, Switzerland"],"raw_orcid":"https://orcid.org/0000-0003-4324-3021","affiliations":[{"raw_affiliation_string":"Dalle Molle Institute for Artificial Intelligence Research, Lugano, Switzerland","institution_ids":["https://openalex.org/I2614128279"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5071172037","display_name":"J\u00fcrgen Schmidhuber","orcid":"https://orcid.org/0000-0002-1468-6758","observed_orcids":["https://orcid.org/0000-0002-1468-6758"]},"institutions":[{"id":"https://openalex.org/I2614128279","display_name":"Dalle Molle Institute for Artificial Intelligence Research","ror":"https://ror.org/013355g38","country_code":"CH","type":"facility","lineage":["https://openalex.org/I15196421","https://openalex.org/I2614128279","https://openalex.org/I57201433"]}],"countries":["CH"],"is_corresponding":false,"raw_author_name":"Juergen Schmidhuber","raw_affiliation_strings":["Dalle Molle Institute for Artificial Intelligence Research, Lugano, Switzerland"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Dalle Molle Institute for Artificial Intelligence Research, Lugano, Switzerland","institution_ids":["https://openalex.org/I2614128279"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I2614128279"],"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":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/T12072","display_name":"Machine Learning and Algorithms","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"}}],"keywords":[{"id":"https://openalex.org/keywords/meta-reinforcement-learning","display_name":"meta-reinforcement learning","score":0.906000018119812},{"id":"https://openalex.org/keywords/generalization","display_name":"generalization","score":0.5220000147819519},{"id":"https://openalex.org/keywords/second-order-gradient","display_name":"second-order gradient","score":0.8949999809265137},{"id":"https://openalex.org/keywords/sample-efficiency","display_name":"sample efficiency","score":0.9819999933242798},{"id":"https://openalex.org/keywords/meta-training","display_name":"meta-training","score":0.5630000233650208}],"concepts":[{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.8815381526947021},{"id":"https://openalex.org/C177148314","wikidata":"https://www.wikidata.org/wiki/Q170084","display_name":"Generalization","level":2,"score":0.7407141327857971},{"id":"https://openalex.org/C2781002164","wikidata":"https://www.wikidata.org/wiki/Q6822311","display_name":"Meta learning (computer science)","level":3,"score":0.7336044907569885},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7225323915481567},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6900083422660828},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.5862295627593994},{"id":"https://openalex.org/C2778445095","wikidata":"https://www.wikidata.org/wiki/Q18354077","display_name":"Sample complexity","level":2,"score":0.579041063785553},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.5049708485603333},{"id":"https://openalex.org/C2986563244","wikidata":"https://www.wikidata.org/wiki/Q6822310","display_name":"Learning to learn","level":2,"score":0.4647146463394165},{"id":"https://openalex.org/C14036430","wikidata":"https://www.wikidata.org/wiki/Q3736076","display_name":"Function (biology)","level":2,"score":0.44491708278656006},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.15393343567848206},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.07940983772277832},{"id":"https://openalex.org/C145420912","wikidata":"https://www.wikidata.org/wiki/Q853077","display_name":"Mathematics education","level":1,"score":0.0},{"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/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.0},{"id":"https://openalex.org/C134306372","wikidata":"https://www.wikidata.org/wiki/Q7754","display_name":"Mathematical analysis","level":1,"score":0.0},{"id":"https://openalex.org/C78458016","wikidata":"https://www.wikidata.org/wiki/Q840400","display_name":"Evolutionary biology","level":1,"score":0.0},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"mag:2995686239","doi":null,"is_oa":true,"landing_page_url":"https://arxiv.org/pdf/1910.04098","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":null,"is_accepted":false,"is_published":false,"raw_source_name":"arXiv (Cornell University)","raw_type":null}],"best_oa_location":{"id":"mag:2995686239","doi":null,"is_oa":true,"landing_page_url":"https://arxiv.org/pdf/1910.04098","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":null,"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":41,"referenced_works":["https://openalex.org/W172298727","https://openalex.org/W1749958644","https://openalex.org/W1757796397","https://openalex.org/W1771410628","https://openalex.org/W1891300059","https://openalex.org/W1909320841","https://openalex.org/W1959608418","https://openalex.org/W2064675550","https://openalex.org/W2119717200","https://openalex.org/W2136848157","https://openalex.org/W2137825550","https://openalex.org/W2158782408","https://openalex.org/W2165150801","https://openalex.org/W2166082022","https://openalex.org/W2166160300","https://openalex.org/W2173248099","https://openalex.org/W2174786457","https://openalex.org/W2409744450","https://openalex.org/W2417786368","https://openalex.org/W2427497464","https://openalex.org/W2550182557","https://openalex.org/W2593649546","https://openalex.org/W2604763608","https://openalex.org/W2736601468","https://openalex.org/W2751973545","https://openalex.org/W2766363782","https://openalex.org/W2787387965","https://openalex.org/W2787501667","https://openalex.org/W2787938642","https://openalex.org/W2789008106","https://openalex.org/W2796429358","https://openalex.org/W2796979132","https://openalex.org/W2803767077","https://openalex.org/W2884901161","https://openalex.org/W2890208753","https://openalex.org/W2946004135","https://openalex.org/W2952193948","https://openalex.org/W2963094322","https://openalex.org/W2964121744","https://openalex.org/W2964121937","https://openalex.org/W2964295739"],"related_works":["https://openalex.org/W2979869797","https://openalex.org/W2976605067","https://openalex.org/W7207732984","https://openalex.org/W7133208860","https://openalex.org/W3109198942","https://openalex.org/W3035417664","https://openalex.org/W3206615896","https://openalex.org/W4308810206","https://openalex.org/W3098584432","https://openalex.org/W6969093990"],"abstract_inverted_index":{"Biological":[0],"evolution":[1],"has":[2],"distilled":[3],"the":[4,10,29],"experiences":[5,30],"of":[6,14,31],"many":[7,32],"learners":[8],"into":[9],"general":[11],"learning":[12,19],"algorithms":[13],"humans.":[15],"Our":[16],"novel":[17],"meta-reinforcement":[18],"algorithm":[20],"MetaGenRL":[21,27,53,77],"is":[22],"inspired":[23],"by":[24],"this":[25],"process.":[26],"distills":[28],"complex":[33],"agents":[34],"to":[35,56],"meta-learn":[36],"a":[37],"low-complexity":[38],"neural":[39],"objective":[40],"function":[41],"that":[42,59,84],"affects":[43],"how":[44],"future":[45],"individuals":[46],"will":[47],"learn.":[48],"Unlike":[49],"recent":[50],"meta-RL":[51],"algorithms,":[52],"can":[54],"generalize":[55],"new":[57],"environments":[58],"are":[60],"entirely":[61],"different":[62],"from":[63],"those":[64],"used":[65],"for":[66],"meta-training.":[67],"In":[68],"some":[69],"cases,":[70],"it":[71],"even":[72],"outperforms":[73],"human-engineered":[74],"RL":[75],"algorithms.":[76],"uses":[78],"off-policy":[79],"second-order":[80],"gradients":[81],"during":[82],"meta-training":[83],"greatly":[85],"increase":[86],"its":[87],"sample":[88],"efficiency.":[89]},"counts_by_year":[{"year":2021,"cited_by_count":6},{"year":2020,"cited_by_count":6},{"year":2019,"cited_by_count":1}],"updated_date":"2026-10-16T09:59:22.235173","created_date":"2019-12-26T00:00:00"}