{"id":"https://openalex.org/W2996868001","doi":"https://doi.org/10.1609/aaai.v34i04.6036","title":"Uncertainty-Aware Action Advising for Deep Reinforcement Learning Agents","display_name":"Uncertainty-Aware Action Advising for Deep Reinforcement Learning Agents","publication_year":2020,"publication_date":"2020-04-03","ids":{"openalex":"https://openalex.org/W2996868001","doi":"https://doi.org/10.1609/aaai.v34i04.6036","mag":"2996868001"},"language":"en","primary_location":{"id":"doi:10.1609/aaai.v34i04.6036","is_oa":true,"landing_page_url":"https://doi.org/10.1609/aaai.v34i04.6036","pdf_url":"https://ojs.aaai.org/index.php/AAAI/article/download/6036/5892","source":{"id":"https://openalex.org/S4210191458","display_name":"Proceedings of the AAAI Conference on Artificial Intelligence","issn_l":"2159-5399","issn":["2159-5399","2374-3468"],"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/P4310320058","host_organization_name":"Association for the Advancement of Artificial Intelligence","host_organization_lineage":["https://openalex.org/P4310320058"],"host_organization_lineage_names":["Association for the Advancement of Artificial Intelligence"],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the AAAI Conference on Artificial Intelligence","raw_type":"journal-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"diamond","oa_url":"https://ojs.aaai.org/index.php/AAAI/article/download/6036/5892","any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5053630715","display_name":"Felipe Leno da Silva","orcid":"https://orcid.org/0000-0003-4703-2061"},"institutions":[{"id":"https://openalex.org/I17974374","display_name":"Universidade de S\u00e3o Paulo","ror":"https://ror.org/036rp1748","country_code":"BR","type":"education","lineage":["https://openalex.org/I17974374"]}],"countries":["BR"],"is_corresponding":true,"raw_author_name":"Felipe Leno Da Silva","raw_affiliation_strings":["University of Sao Paulo"],"affiliations":[{"raw_affiliation_string":"University of Sao Paulo","institution_ids":["https://openalex.org/I17974374"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5005259414","display_name":"Pablo Hern\u00e1ndez-Leal","orcid":"https://orcid.org/0000-0002-8530-6775"},"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":"Pablo Hernandez-Leal","raw_affiliation_strings":["Borealis AI"],"affiliations":[{"raw_affiliation_string":"Borealis AI","institution_ids":["https://openalex.org/I4210162562"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5071731471","display_name":"Bilal Kartal","orcid":"https://orcid.org/0000-0001-9537-3835"},"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":"Bilal Kartal","raw_affiliation_strings":["Borealis AI"],"affiliations":[{"raw_affiliation_string":"Borealis AI","institution_ids":["https://openalex.org/I4210162562"]}]},{"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"],"affiliations":[{"raw_affiliation_string":"Borealis AI","institution_ids":["https://openalex.org/I4210162562"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5053630715"],"corresponding_institution_ids":["https://openalex.org/I17974374"],"apc_list":null,"apc_paid":null,"fwci":4.1919,"has_fulltext":true,"cited_by_count":69,"citation_normalized_percentile":{"value":0.94688869,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":90,"max":100},"biblio":{"volume":"34","issue":"04","first_page":"5792","last_page":"5799"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10462","display_name":"Reinforcement Learning in Robotics","score":0.9998000264167786,"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":0.9998000264167786,"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":0.9961000084877014,"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/T10603","display_name":"Smart Grid Energy Management","score":0.9886999726295471,"subfield":{"id":"https://openalex.org/subfields/2208","display_name":"Electrical and Electronic 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/reinforcement-learning","display_name":"Reinforcement learning","score":0.8955143690109253},{"id":"https://openalex.org/keywords/leverage","display_name":"Leverage (statistics)","score":0.8662793040275574},{"id":"https://openalex.org/keywords/advice","display_name":"Advice (programming)","score":0.7280673980712891},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6161658763885498},{"id":"https://openalex.org/keywords/action","display_name":"Action (physics)","score":0.5433207154273987},{"id":"https://openalex.org/keywords/sample","display_name":"Sample (material)","score":0.5311523675918579},{"id":"https://openalex.org/keywords/sample-complexity","display_name":"Sample complexity","score":0.5071580410003662},{"id":"https://openalex.org/keywords/function","display_name":"Function (biology)","score":0.47373974323272705},{"id":"https://openalex.org/keywords/reinforcement","display_name":"Reinforcement","score":0.44821658730506897},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4297448694705963},{"id":"https://openalex.org/keywords/risk-analysis","display_name":"Risk analysis (engineering)","score":0.3491000831127167},{"id":"https://openalex.org/keywords/operations-research","display_name":"Operations research","score":0.3329690396785736},{"id":"https://openalex.org/keywords/psychology","display_name":"Psychology","score":0.22816038131713867},{"id":"https://openalex.org/keywords/business","display_name":"Business","score":0.13186785578727722},{"id":"https://openalex.org/keywords/social-psychology","display_name":"Social psychology","score":0.13135048747062683},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.09122490882873535}],"concepts":[{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.8955143690109253},{"id":"https://openalex.org/C153083717","wikidata":"https://www.wikidata.org/wiki/Q6535263","display_name":"Leverage (statistics)","level":2,"score":0.8662793040275574},{"id":"https://openalex.org/C2779955035","wikidata":"https://www.wikidata.org/wiki/Q4686785","display_name":"Advice (programming)","level":2,"score":0.7280673980712891},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6161658763885498},{"id":"https://openalex.org/C2780791683","wikidata":"https://www.wikidata.org/wiki/Q846785","display_name":"Action (physics)","level":2,"score":0.5433207154273987},{"id":"https://openalex.org/C198531522","wikidata":"https://www.wikidata.org/wiki/Q485146","display_name":"Sample (material)","level":2,"score":0.5311523675918579},{"id":"https://openalex.org/C2778445095","wikidata":"https://www.wikidata.org/wiki/Q18354077","display_name":"Sample complexity","level":2,"score":0.5071580410003662},{"id":"https://openalex.org/C14036430","wikidata":"https://www.wikidata.org/wiki/Q3736076","display_name":"Function (biology)","level":2,"score":0.47373974323272705},{"id":"https://openalex.org/C67203356","wikidata":"https://www.wikidata.org/wiki/Q1321905","display_name":"Reinforcement","level":2,"score":0.44821658730506897},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4297448694705963},{"id":"https://openalex.org/C112930515","wikidata":"https://www.wikidata.org/wiki/Q4389547","display_name":"Risk analysis (engineering)","level":1,"score":0.3491000831127167},{"id":"https://openalex.org/C42475967","wikidata":"https://www.wikidata.org/wiki/Q194292","display_name":"Operations research","level":1,"score":0.3329690396785736},{"id":"https://openalex.org/C15744967","wikidata":"https://www.wikidata.org/wiki/Q9418","display_name":"Psychology","level":0,"score":0.22816038131713867},{"id":"https://openalex.org/C144133560","wikidata":"https://www.wikidata.org/wiki/Q4830453","display_name":"Business","level":0,"score":0.13186785578727722},{"id":"https://openalex.org/C77805123","wikidata":"https://www.wikidata.org/wiki/Q161272","display_name":"Social psychology","level":1,"score":0.13135048747062683},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.09122490882873535},{"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},{"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/C43617362","wikidata":"https://www.wikidata.org/wiki/Q170050","display_name":"Chromatography","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/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1609/aaai.v34i04.6036","is_oa":true,"landing_page_url":"https://doi.org/10.1609/aaai.v34i04.6036","pdf_url":"https://ojs.aaai.org/index.php/AAAI/article/download/6036/5892","source":{"id":"https://openalex.org/S4210191458","display_name":"Proceedings of the AAAI Conference on Artificial Intelligence","issn_l":"2159-5399","issn":["2159-5399","2374-3468"],"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/P4310320058","host_organization_name":"Association for the Advancement of Artificial Intelligence","host_organization_lineage":["https://openalex.org/P4310320058"],"host_organization_lineage_names":["Association for the Advancement of Artificial Intelligence"],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the AAAI Conference on Artificial Intelligence","raw_type":"journal-article"}],"best_oa_location":{"id":"doi:10.1609/aaai.v34i04.6036","is_oa":true,"landing_page_url":"https://doi.org/10.1609/aaai.v34i04.6036","pdf_url":"https://ojs.aaai.org/index.php/AAAI/article/download/6036/5892","source":{"id":"https://openalex.org/S4210191458","display_name":"Proceedings of the AAAI Conference on Artificial Intelligence","issn_l":"2159-5399","issn":["2159-5399","2374-3468"],"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/P4310320058","host_organization_name":"Association for the Advancement of Artificial Intelligence","host_organization_lineage":["https://openalex.org/P4310320058"],"host_organization_lineage_names":["Association for the Advancement of Artificial Intelligence"],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the AAAI Conference on Artificial Intelligence","raw_type":"journal-article"},"sustainable_development_goals":[{"display_name":"Peace, Justice and strong institutions","id":"https://metadata.un.org/sdg/16","score":0.8199999928474426}],"awards":[],"funders":[],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W2996868001.pdf","grobid_xml":"https://content.openalex.org/works/W2996868001.grobid-xml"},"referenced_works_count":47,"referenced_works":["https://openalex.org/W1529399279","https://openalex.org/W1845972764","https://openalex.org/W1969685488","https://openalex.org/W1980969546","https://openalex.org/W1986014385","https://openalex.org/W2076063813","https://openalex.org/W2104171826","https://openalex.org/W2119567691","https://openalex.org/W2121863487","https://openalex.org/W2124175081","https://openalex.org/W2145339207","https://openalex.org/W2201581102","https://openalex.org/W2280163991","https://openalex.org/W2560321925","https://openalex.org/W2563829177","https://openalex.org/W2620645529","https://openalex.org/W2739473244","https://openalex.org/W2759104452","https://openalex.org/W2788862220","https://openalex.org/W2804726947","https://openalex.org/W2921955147","https://openalex.org/W2938421504","https://openalex.org/W2945466622","https://openalex.org/W2945850646","https://openalex.org/W2962787969","https://openalex.org/W2963238274","https://openalex.org/W2963376229","https://openalex.org/W2963390684","https://openalex.org/W2963423916","https://openalex.org/W2963477884","https://openalex.org/W2963938771","https://openalex.org/W2964043796","https://openalex.org/W2966816175","https://openalex.org/W2968491743","https://openalex.org/W2976108375","https://openalex.org/W2982705681","https://openalex.org/W4214717370","https://openalex.org/W4298876402","https://openalex.org/W6601295022","https://openalex.org/W6646884813","https://openalex.org/W6669567237","https://openalex.org/W6677916085","https://openalex.org/W6687681856","https://openalex.org/W6695011786","https://openalex.org/W6730844258","https://openalex.org/W6751661917","https://openalex.org/W7001894244"],"related_works":["https://openalex.org/W3038068131","https://openalex.org/W4226283576","https://openalex.org/W2996868001","https://openalex.org/W2909152095","https://openalex.org/W3042947755","https://openalex.org/W2953386523","https://openalex.org/W3174680430","https://openalex.org/W3208796191","https://openalex.org/W3135457936","https://openalex.org/W4287281679"],"abstract_inverted_index":{"Although":[0],"Reinforcement":[1],"Learning":[2],"(RL)":[3],"has":[4],"been":[5],"one":[6],"of":[7,21],"the":[8,19,51,77,82,101,121,136],"most":[9],"successful":[10],"approaches":[11],"for":[12,29,104,112],"learning":[13],"in":[14,143,168],"sequential":[15],"decision":[16],"making":[17],"problems,":[18],"sample-complexity":[20],"RL":[22,146],"techniques":[23],"still":[24],"represents":[25],"a":[26,37,42,46,113,132],"major":[27],"challenge":[28],"practical":[30],"applications.":[31],"To":[32],"combat":[33],"this":[34,57,88],"challenge,":[35],"whenever":[36],"competent":[38],"policy":[39,58],"(e.g.,":[40],"either":[41],"legacy":[43],"system":[44],"or":[45],"human":[47],"demonstrator)":[48],"is":[49,65,79,110,123],"available,":[50],"agent":[52,78,102,137],"could":[53],"leverage":[54],"samples":[55],"from":[56],"(advice)":[59],"to":[60,74,85,134],"improve":[61],"sample-efficiency.":[62],"However,":[63],"advice":[64,95,105,122],"normally":[66],"limited,":[67],"hence":[68],"it":[69,164],"should":[70],"ideally":[71],"be":[72,127],"directed":[73],"states":[75,167],"where":[76,100],"uncertain":[80],"on":[81],"best":[83],"action":[84],"execute.":[86],"In":[87],"work,":[89],"we":[90],"propose":[91],"Requesting":[92],"Confidence-Moderated":[93],"Policy":[94],"(RCMP),":[96],"an":[97],"action-advising":[98],"framework":[99],"asks":[103],"when":[106],"its":[107],"epistemic":[108],"uncertainty":[109,138],"high":[111],"certain":[114],"state.":[115],"RCMP":[116,153],"takes":[117],"into":[118],"account":[119],"that":[120,152],"limited":[124],"and":[125,162,170],"might":[126],"suboptimal.":[128],"We":[129],"also":[130],"describe":[131],"technique":[133],"estimate":[135],"by":[139],"performing":[140],"minor":[141],"modifications":[142],"standard":[144],"value-function-based":[145],"methods.":[147],"Our":[148],"empirical":[149],"evaluations":[150],"show":[151],"performs":[154],"better":[155],"than":[156],"Importance":[157],"Advising,":[158],"not":[159],"receiving":[160,163],"advice,":[161],"at":[165],"random":[166],"Gridworld":[169],"Atari":[171],"Pong":[172],"scenarios.":[173]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":11},{"year":2024,"cited_by_count":18},{"year":2023,"cited_by_count":11},{"year":2022,"cited_by_count":9},{"year":2021,"cited_by_count":14},{"year":2020,"cited_by_count":4},{"year":2019,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}