{"id":"https://openalex.org/W2945943081","doi":"https://doi.org/10.24963/ijcai.2019/581","title":"Metatrace Actor-Critic: Online Step-Size Tuning by Meta-gradient Descent for Reinforcement Learning Control","display_name":"Metatrace Actor-Critic: Online Step-Size Tuning by Meta-gradient Descent for Reinforcement Learning Control","publication_year":2019,"publication_date":"2019-07-28","ids":{"openalex":"https://openalex.org/W2945943081","doi":"https://doi.org/10.24963/ijcai.2019/581","mag":"2945943081"},"language":"en","primary_location":{"id":"doi:10.24963/ijcai.2019/581","is_oa":true,"landing_page_url":"https://doi.org/10.24963/ijcai.2019/581","pdf_url":"https://www.ijcai.org/proceedings/2019/0581.pdf","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the Twenty-Eighth International Joint Conference on Artificial Intelligence","raw_type":"proceedings-article"},"type":"preprint","indexed_in":["arxiv","crossref","datacite"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://www.ijcai.org/proceedings/2019/0581.pdf","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5007831673","display_name":"Kenny Young","orcid":null},"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":"Kenny Young","raw_affiliation_strings":["Borealis AI, Edmonton, Alberta, Canada","University of Alberta, Edmonton, Alberta, Canada"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Borealis AI, Edmonton, Alberta, Canada","institution_ids":[]},{"raw_affiliation_string":"University of Alberta, Edmonton, Alberta, Canada","institution_ids":["https://openalex.org/I154425047"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101781010","display_name":"Baoxiang Wang","orcid":"https://orcid.org/0000-0002-6569-9049"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Baoxiang Wang","raw_affiliation_strings":["Borealis AI, Edmonton, Alberta, Canada"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Borealis AI, Edmonton, Alberta, Canada","institution_ids":[]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5070914351","display_name":"Matthew E. Taylor","orcid":"https://orcid.org/0000-0001-8946-0211"},"institutions":[{"id":"https://openalex.org/I4210162562","display_name":"Borealis (Austria)","ror":"https://ror.org/05eat3g39","country_code":"AT","type":"company","lineage":["https://openalex.org/I4210162562"]}],"countries":["AT"],"is_corresponding":false,"raw_author_name":"Matthew E. Taylor","raw_affiliation_strings":["Borealis AI, Edmonton, Alberta, Canada","Borealis AI"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Borealis AI, Edmonton, Alberta, Canada","institution_ids":[]},{"raw_affiliation_string":"Borealis AI","institution_ids":["https://openalex.org/I4210162562"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":3,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.8676,"has_fulltext":false,"cited_by_count":7,"citation_normalized_percentile":{"value":0.80565106,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":97},"biblio":{"volume":null,"issue":null,"first_page":"4185","last_page":"4191"},"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/T12101","display_name":"Advanced Bandit Algorithms Research","score":0.9966999888420105,"subfield":{"id":"https://openalex.org/subfields/1803","display_name":"Management Science and Operations Research"},"field":{"id":"https://openalex.org/fields/18","display_name":"Decision Sciences"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}},{"id":"https://openalex.org/T12794","display_name":"Adaptive Dynamic Programming Control","score":0.9900000095367432,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/hyperparameter","display_name":"Hyperparameter","score":0.8153107762336731},{"id":"https://openalex.org/keywords/reinforcement-learning","display_name":"Reinforcement learning","score":0.8061611652374268},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.726191520690918},{"id":"https://openalex.org/keywords/robustness","display_name":"Robustness (evolution)","score":0.5876315832138062},{"id":"https://openalex.org/keywords/gradient-descent","display_name":"Gradient descent","score":0.5867610573768616},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.505230724811554},{"id":"https://openalex.org/keywords/nonlinear-system","display_name":"Nonlinear system","score":0.49560511112213135},{"id":"https://openalex.org/keywords/function-approximation","display_name":"Function approximation","score":0.48540768027305603},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.4709917902946472},{"id":"https://openalex.org/keywords/mathematical-optimization","display_name":"Mathematical optimization","score":0.36738157272338867},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.27931642532348633},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.18116414546966553}],"concepts":[{"id":"https://openalex.org/C8642999","wikidata":"https://www.wikidata.org/wiki/Q4171168","display_name":"Hyperparameter","level":2,"score":0.8153107762336731},{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.8061611652374268},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.726191520690918},{"id":"https://openalex.org/C63479239","wikidata":"https://www.wikidata.org/wiki/Q7353546","display_name":"Robustness (evolution)","level":3,"score":0.5876315832138062},{"id":"https://openalex.org/C153258448","wikidata":"https://www.wikidata.org/wiki/Q1199743","display_name":"Gradient descent","level":3,"score":0.5867610573768616},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.505230724811554},{"id":"https://openalex.org/C158622935","wikidata":"https://www.wikidata.org/wiki/Q660848","display_name":"Nonlinear system","level":2,"score":0.49560511112213135},{"id":"https://openalex.org/C91873725","wikidata":"https://www.wikidata.org/wiki/Q3445816","display_name":"Function approximation","level":3,"score":0.48540768027305603},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.4709917902946472},{"id":"https://openalex.org/C126255220","wikidata":"https://www.wikidata.org/wiki/Q141495","display_name":"Mathematical optimization","level":1,"score":0.36738157272338867},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.27931642532348633},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.18116414546966553},{"id":"https://openalex.org/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","level":0,"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/C62520636","wikidata":"https://www.wikidata.org/wiki/Q944","display_name":"Quantum mechanics","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/C55493867","wikidata":"https://www.wikidata.org/wiki/Q7094","display_name":"Biochemistry","level":1,"score":0.0}],"mesh":[],"locations_count":4,"locations":[{"id":"doi:10.24963/ijcai.2019/581","is_oa":true,"landing_page_url":"https://doi.org/10.24963/ijcai.2019/581","pdf_url":"https://www.ijcai.org/proceedings/2019/0581.pdf","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the Twenty-Eighth International Joint Conference on Artificial Intelligence","raw_type":"proceedings-article"},{"id":"pmh:oai:arXiv.org:1805.04514","is_oa":true,"landing_page_url":"http://arxiv.org/abs/1805.04514","pdf_url":"https://arxiv.org/pdf/1805.04514","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"},{"id":"mag:2945943081","is_oa":true,"landing_page_url":"http://export.arxiv.org/pdf/1805.04514","pdf_url":null,"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":"arXiv (Cornell University)","raw_type":null},{"id":"doi:10.48550/arxiv.1805.04514","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.1805.04514","pdf_url":null,"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":null,"is_accepted":false,"is_published":null,"raw_source_name":null,"raw_type":"article"}],"best_oa_location":{"id":"doi:10.24963/ijcai.2019/581","is_oa":true,"landing_page_url":"https://doi.org/10.24963/ijcai.2019/581","pdf_url":"https://www.ijcai.org/proceedings/2019/0581.pdf","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the Twenty-Eighth International Joint Conference on Artificial Intelligence","raw_type":"proceedings-article"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W2945943081.pdf","grobid_xml":"https://content.openalex.org/works/W2945943081.grobid-xml"},"referenced_works_count":14,"referenced_works":["https://openalex.org/W172031327","https://openalex.org/W1191599655","https://openalex.org/W1522301498","https://openalex.org/W1757796397","https://openalex.org/W2024390895","https://openalex.org/W2145339207","https://openalex.org/W2155027007","https://openalex.org/W2155968351","https://openalex.org/W2158596240","https://openalex.org/W2796618762","https://openalex.org/W2962834855","https://openalex.org/W2963403143","https://openalex.org/W2963433763","https://openalex.org/W2964043796"],"related_works":["https://openalex.org/W2965963242","https://openalex.org/W2800391888","https://openalex.org/W1500331901","https://openalex.org/W2471761533","https://openalex.org/W3125760305","https://openalex.org/W2967645217","https://openalex.org/W3009867653","https://openalex.org/W2146957157","https://openalex.org/W3007031922","https://openalex.org/W3005787005","https://openalex.org/W3057037158","https://openalex.org/W2808421695","https://openalex.org/W3103145727","https://openalex.org/W2950471160","https://openalex.org/W3123748881","https://openalex.org/W2783634529","https://openalex.org/W3126916000","https://openalex.org/W62417866","https://openalex.org/W2144655553","https://openalex.org/W2945529113"],"abstract_inverted_index":{"Reinforcement":[0],"learning":[1,33,57,92],"(RL)":[2],"has":[3],"had":[4],"many":[5],"successes,":[6],"but":[7],"significant":[8],"hyperparameter":[9],"tuning":[10,130],"is":[11,23,84],"commonly":[12],"required":[13],"to":[14,32,40,65,114],"achieve":[15],"good":[16],"performance.":[17],"Furthermore,":[18],"when":[19],"nonlinear":[20],"function":[21],"approximation":[22],"used,":[24],"non-stationarity":[25],"in":[26,162],"the":[27,49,60,66,73,79,116,121,148],"state":[28],"representation":[29],"can":[30,155],"lead":[31],"instability.":[34],"A":[35],"variety":[36],"of":[37,51,75,99,123],"techniques":[38,55],"exist":[39],"combat":[41],"this":[42],"---":[43],"most":[44],"notably":[45],"experience":[46],"replay":[47],"or":[48],"use":[50],"parallel":[52],"actors.":[53],"These":[54],"stabilize":[56],"by":[58],"making":[59],"RL":[61,80],"problem":[62,81],"more":[63],"similar":[64],"supervised":[67],"setting.":[68],"However,":[69],"they":[70],"come":[71],"at":[72],"cost":[74],"moving":[76],"away":[77],"from":[78],"as":[82],"it":[83],"typically":[85],"formulated,":[86],"that":[87],"is,":[88],"a":[89,96,109,131,135],"single":[90],"agent":[91],"online":[93],"without":[94],"maintaining":[95],"large":[97],"database":[98],"training":[100],"examples.":[101],"To":[102],"address":[103],"these":[104],"issues,":[105],"we":[106],"propose":[107],"Metatrace,":[108],"meta-gradient":[110],"descent":[111],"based":[112],"algorithm":[113],"tune":[115],"step-size":[117,133,137],"online.":[118],"Metatrace":[119,144,154],"leverages":[120],"structure":[122],"eligibility":[124],"traces,":[125],"and":[126,134,159],"works":[127],"for":[128,138,145],"both":[129],"scalar":[132],"respective":[136],"each":[139],"parameter.":[140],"We":[141],"empirically":[142],"evaluate":[143],"actor-critic":[146],"on":[147],"Arcade":[149],"Learning":[150],"Environment.":[151],"Results":[152],"show":[153],"speed":[156],"up":[157],"learning,":[158],"improve":[160],"performance":[161],"non-stationary":[163],"settings.":[164]},"counts_by_year":[{"year":2024,"cited_by_count":1},{"year":2021,"cited_by_count":1},{"year":2020,"cited_by_count":2},{"year":2019,"cited_by_count":3}],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2025-10-10T00:00:00"}