{"id":"https://openalex.org/W4319323355","doi":"https://doi.org/10.48550/arxiv.2302.01470","title":"Learning to Optimize for Reinforcement Learning","display_name":"Learning to Optimize for Reinforcement Learning","publication_year":2023,"publication_date":"2023-02-03","ids":{"openalex":"https://openalex.org/W4319323355","doi":"https://doi.org/10.48550/arxiv.2302.01470"},"language":"en","primary_location":{"id":"pmh:oai:arXiv.org:2302.01470","doi":null,"is_oa":true,"landing_page_url":"http://arxiv.org/abs/2302.01470","pdf_url":"https://arxiv.org/pdf/2302.01470","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":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},"volume":null,"type":"preprint","is_traditional":true,"indexed_in":["arxiv","datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2302.01470","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5052537094","display_name":"Qingfeng Lan","orcid":"https://orcid.org/0000-0001-8568-7603","observed_orcids":["https://orcid.org/0000-0001-8568-7603"]},"institutions":[{"id":"https://openalex.org/I154425047","display_name":"University of Alberta","ror":"https://ror.org/0160cpw27","country_code":"CA","type":"education","lineage":["https://openalex.org/I154425047"]}],"countries":["CA"],"is_corresponding":false,"raw_author_name":"Lan, Qingfeng","raw_affiliation_strings":["Department of Computing Science University of Alberta Edmonton , Alberta , Canada"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Computing Science University of Alberta Edmonton , Alberta , Canada","institution_ids":["https://openalex.org/I154425047"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5102815213","display_name":"A. Rupam Mahmood","orcid":"https://orcid.org/0000-0002-2640-1844","observed_orcids":["https://orcid.org/0000-0002-2640-1844"]},"institutions":[{"id":"https://openalex.org/I109736498","display_name":"Canadian Institute for Advanced Research","ror":"https://ror.org/01sdtdd95","country_code":"CA","type":"facility","lineage":["https://openalex.org/I109736498"]},{"id":"https://openalex.org/I154425047","display_name":"University of Alberta","ror":"https://ror.org/0160cpw27","country_code":"CA","type":"education","lineage":["https://openalex.org/I154425047"]},{"id":"https://openalex.org/I4405260365","display_name":"Alberta Machine Intelligence Institute","ror":"https://ror.org/03msd8560","country_code":"CA","type":"facility","lineage":["https://openalex.org/I4405260365"]}],"countries":["CA"],"is_corresponding":false,"raw_author_name":"Mahmood, A. Rupam","raw_affiliation_strings":["Department of Computing Science University of Alberta CIFAR AI Chair , Amii"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Computing Science University of Alberta CIFAR AI Chair , Amii","institution_ids":["https://openalex.org/I109736498","https://openalex.org/I154425047","https://openalex.org/I4405260365"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100381753","display_name":"Shuicheng Yan","orcid":"https://orcid.org/0000-0001-8906-3777","observed_orcids":["https://orcid.org/0000-0001-8906-3777"]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Yan, Shuicheng","raw_affiliation_strings":["Sea AI Lab , Skywork AI"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Sea AI Lab , Skywork AI","institution_ids":[]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5062979221","display_name":"Zhongwen Xu","orcid":"https://orcid.org/0000-0002-9348-7262","observed_orcids":["https://orcid.org/0000-0002-9348-7262"]},"institutions":[{"id":"https://openalex.org/I2250653659","display_name":"Tencent (China)","ror":"https://ror.org/00hhjss72","country_code":"CN","type":"company","lineage":["https://openalex.org/I2250653659"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xu, Zhongwen","raw_affiliation_strings":["Sea AI Lab , Tencent AI Lab"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Sea AI Lab , Tencent AI Lab","institution_ids":["https://openalex.org/I2250653659"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":4,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":true,"cited_by_count":4,"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/T11612","display_name":"Stochastic Gradient Optimization Techniques","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"}},{"id":"https://openalex.org/T11307","display_name":"Domain Adaptation and Few-Shot Learning","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/learned-optimizers","display_name":"learned optimizers","score":0.9940000176429749},{"id":"https://openalex.org/keywords/reinforcement-learning","display_name":"reinforcement learning","score":0.6710000038146973},{"id":"https://openalex.org/keywords/meta-training","display_name":"meta-training","score":0.8730000257492065},{"id":"https://openalex.org/keywords/inductive-bias","display_name":"inductive bias","score":0.9259999990463257},{"id":"https://openalex.org/keywords/generalization-to-unseen-tasks","display_name":"generalization to unseen tasks","score":0.7599999904632568}],"concepts":[{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.8465970158576965},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8025752305984497},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6615917682647705},{"id":"https://openalex.org/C204323151","wikidata":"https://www.wikidata.org/wiki/Q905424","display_name":"Range (aeronautics)","level":2,"score":0.5747754573822021},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.5439249873161316},{"id":"https://openalex.org/C43521106","wikidata":"https://www.wikidata.org/wiki/Q2165493","display_name":"Pipeline (software)","level":2,"score":0.5327957272529602},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.487856388092041},{"id":"https://openalex.org/C196083921","wikidata":"https://www.wikidata.org/wiki/Q7915758","display_name":"Variance (accounting)","level":2,"score":0.4763655662536621},{"id":"https://openalex.org/C136389625","wikidata":"https://www.wikidata.org/wiki/Q334384","display_name":"Supervised learning","level":3,"score":0.4730859398841858},{"id":"https://openalex.org/C2781235140","wikidata":"https://www.wikidata.org/wiki/Q275131","display_name":"Scratch","level":2,"score":0.43495720624923706},{"id":"https://openalex.org/C2778355321","wikidata":"https://www.wikidata.org/wiki/Q17079427","display_name":"Identity (music)","level":2,"score":0.410104364156723},{"id":"https://openalex.org/C192562407","wikidata":"https://www.wikidata.org/wiki/Q228736","display_name":"Materials science","level":0,"score":0.0},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.0},{"id":"https://openalex.org/C121955636","wikidata":"https://www.wikidata.org/wiki/Q4116214","display_name":"Accounting","level":1,"score":0.0},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0},{"id":"https://openalex.org/C144133560","wikidata":"https://www.wikidata.org/wiki/Q4830453","display_name":"Business","level":0,"score":0.0},{"id":"https://openalex.org/C24890656","wikidata":"https://www.wikidata.org/wiki/Q82811","display_name":"Acoustics","level":1,"score":0.0},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.0},{"id":"https://openalex.org/C159985019","wikidata":"https://www.wikidata.org/wiki/Q181790","display_name":"Composite material","level":1,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"pmh:oai:arXiv.org:2302.01470","doi":null,"is_oa":true,"landing_page_url":"http://arxiv.org/abs/2302.01470","pdf_url":"https://arxiv.org/pdf/2302.01470","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":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},{"id":"doi:10.48550/arxiv.2302.01470","doi":"https://doi.org/10.48550/arxiv.2302.01470","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2302.01470","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":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":null,"is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Preprint"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2302.01470","doi":null,"is_oa":true,"landing_page_url":"http://arxiv.org/abs/2302.01470","pdf_url":"https://arxiv.org/pdf/2302.01470","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":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},"sustainable_development_goals":[],"study_designs":[],"awards":[],"funders":[],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4319323355.pdf","grobid_xml":"https://content.openalex.org/works/W4319323355.grobid-xml"},"referenced_works_count":0,"referenced_works":[],"related_works":["https://openalex.org/W4415798983","https://openalex.org/W4312233737","https://openalex.org/W7130379664","https://openalex.org/W3129941543","https://openalex.org/W2955597434","https://openalex.org/W2602585184","https://openalex.org/W3088321919","https://openalex.org/W4399115846","https://openalex.org/W7133235736","https://openalex.org/W7206193144"],"abstract_inverted_index":{"In":[0],"recent":[1],"years,":[2],"by":[3],"leveraging":[4],"more":[5],"data,":[6],"computation,":[7],"and":[8,33,52,62,81,97],"diverse":[9],"tasks,":[10,131],"learned":[11,37,133],"optimizers":[12,38],"have":[13,78],"achieved":[14],"remarkable":[15],"success":[16],"in":[17,34,44,129,141],"supervised":[18,31],"learning,":[19,32],"outperforming":[20],"classical":[21],"hand-designed":[22],"optimizers.":[23],"Reinforcement":[24],"learning":[25,88,120],"(RL)":[26],"is":[27,60],"essentially":[28],"different":[29],"from":[30,121],"practice,":[35],"these":[36,109],"do":[39],"not":[40],"work":[41],"well":[42],"even":[43],"simple":[45],"RL":[46],"tasks.":[47],"We":[48,93,123],"investigate":[49],"this":[50],"phenomenon":[51],"identify":[53],"two":[54],"issues.":[55],"First,":[56],"the":[57,76,85],"agent-gradient":[58],"distribution":[59],"non-independent":[61],"identically":[63],"distributed,":[64],"leading":[65],"to":[66,71,107,114,137],"inefficient":[67],"meta-training.":[68],"Moreover,":[69],"due":[70],"highly":[72],"stochastic":[73],"agent-environment":[74],"interactions,":[75],"agent-gradients":[77],"high":[79],"bias":[80,106],"variance,":[82],"which":[83],"increases":[84],"difficulty":[86],"of":[87],"an":[89,116],"optimizer":[90,100,117,134],"for":[91,118],"RL.":[92],"propose":[94],"pipeline":[95],"training":[96],"a":[98,103],"novel":[99],"structure":[101],"with":[102],"good":[104],"inductive":[105],"address":[108],"issues,":[110],"making":[111],"it":[112],"possible":[113],"learn":[115],"reinforcement":[119],"scratch.":[122],"show":[124],"that,":[125],"although":[126],"only":[127],"trained":[128],"toy":[130],"our":[132],"can":[135],"generalize":[136],"unseen":[138],"complex":[139],"tasks":[140],"Brax.":[142]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":2},{"year":2024,"cited_by_count":1}],"updated_date":"2026-11-04T10:54:05.112534","created_date":"2023-02-08T00:00:00"}
