{"id":"https://openalex.org/W3038068131","doi":"https://doi.org/10.1609/aaai.v34i10.7229","title":"Providing Uncertainty-Based Advice for Deep Reinforcement Learning Agents (Student Abstract)","display_name":"Providing Uncertainty-Based Advice for Deep Reinforcement Learning Agents (Student Abstract)","publication_year":2020,"publication_date":"2020-04-03","ids":{"openalex":"https://openalex.org/W3038068131","doi":"https://doi.org/10.1609/aaai.v34i10.7229","mag":"3038068131"},"language":"en","primary_location":{"id":"doi:10.1609/aaai.v34i10.7229","is_oa":true,"landing_page_url":"https://doi.org/10.1609/aaai.v34i10.7229","pdf_url":"https://ojs.aaai.org/index.php/AAAI/article/download/7229/7083","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/7229/7083","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":[],"countries":[],"is_corresponding":true,"raw_author_name":"Felipe Leno Da Silva","raw_affiliation_strings":["University of S\u00e3o Paulo"],"affiliations":[{"raw_affiliation_string":"University of S\u00e3o Paulo","institution_ids":[]}]},{"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":1,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5053630715"],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":true,"cited_by_count":0,"citation_normalized_percentile":{"value":0.07870289,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":"34","issue":"10","first_page":"13913","last_page":"13914"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10462","display_name":"Reinforcement Learning in Robotics","score":0.9775999784469604,"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":0.9775999784469604,"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/reinforcement-learning","display_name":"Reinforcement learning","score":0.8912965059280396},{"id":"https://openalex.org/keywords/advice","display_name":"Advice (programming)","score":0.8849737048149109},{"id":"https://openalex.org/keywords/leverage","display_name":"Leverage (statistics)","score":0.8599419593811035},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6633450984954834},{"id":"https://openalex.org/keywords/reinforcement","display_name":"Reinforcement","score":0.5616233944892883},{"id":"https://openalex.org/keywords/domain","display_name":"Domain (mathematical analysis)","score":0.4623492956161499},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.45632505416870117},{"id":"https://openalex.org/keywords/action","display_name":"Action (physics)","score":0.4333825707435608},{"id":"https://openalex.org/keywords/psychology","display_name":"Psychology","score":0.1726306676864624},{"id":"https://openalex.org/keywords/social-psychology","display_name":"Social psychology","score":0.08298763632774353},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.08173328638076782}],"concepts":[{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.8912965059280396},{"id":"https://openalex.org/C2779955035","wikidata":"https://www.wikidata.org/wiki/Q4686785","display_name":"Advice (programming)","level":2,"score":0.8849737048149109},{"id":"https://openalex.org/C153083717","wikidata":"https://www.wikidata.org/wiki/Q6535263","display_name":"Leverage (statistics)","level":2,"score":0.8599419593811035},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6633450984954834},{"id":"https://openalex.org/C67203356","wikidata":"https://www.wikidata.org/wiki/Q1321905","display_name":"Reinforcement","level":2,"score":0.5616233944892883},{"id":"https://openalex.org/C36503486","wikidata":"https://www.wikidata.org/wiki/Q11235244","display_name":"Domain (mathematical analysis)","level":2,"score":0.4623492956161499},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.45632505416870117},{"id":"https://openalex.org/C2780791683","wikidata":"https://www.wikidata.org/wiki/Q846785","display_name":"Action (physics)","level":2,"score":0.4333825707435608},{"id":"https://openalex.org/C15744967","wikidata":"https://www.wikidata.org/wiki/Q9418","display_name":"Psychology","level":0,"score":0.1726306676864624},{"id":"https://openalex.org/C77805123","wikidata":"https://www.wikidata.org/wiki/Q161272","display_name":"Social psychology","level":1,"score":0.08298763632774353},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.08173328638076782},{"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/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","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/C134306372","wikidata":"https://www.wikidata.org/wiki/Q7754","display_name":"Mathematical analysis","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1609/aaai.v34i10.7229","is_oa":true,"landing_page_url":"https://doi.org/10.1609/aaai.v34i10.7229","pdf_url":"https://ojs.aaai.org/index.php/AAAI/article/download/7229/7083","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.v34i10.7229","is_oa":true,"landing_page_url":"https://doi.org/10.1609/aaai.v34i10.7229","pdf_url":"https://ojs.aaai.org/index.php/AAAI/article/download/7229/7083","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":[{"score":0.4099999964237213,"id":"https://metadata.un.org/sdg/16","display_name":"Peace, Justice and strong institutions"}],"awards":[],"funders":[],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W3038068131.pdf","grobid_xml":"https://content.openalex.org/works/W3038068131.grobid-xml"},"referenced_works_count":5,"referenced_works":["https://openalex.org/W1529399279","https://openalex.org/W2145339207","https://openalex.org/W2280163991","https://openalex.org/W2563829177","https://openalex.org/W2921955147"],"related_works":["https://openalex.org/W3090906284","https://openalex.org/W253876680","https://openalex.org/W1987931999","https://openalex.org/W2920061524","https://openalex.org/W4310083477","https://openalex.org/W4293797372","https://openalex.org/W4238052600","https://openalex.org/W3005176110","https://openalex.org/W2768698792","https://openalex.org/W1984742304"],"abstract_inverted_index":{"The":[0],"sample-complexity":[1],"of":[2,31],"Reinforcement":[3],"Learning":[4],"(RL)":[5],"techniques":[6],"still":[7],"represents":[8],"a":[9,32,88],"challenge":[10],"for":[11,79],"scaling":[12],"up":[13],"RL":[14,101],"to":[15,20,25,34,48,59,90,106],"unsolved":[16],"domains.":[17],"One":[18],"way":[19],"alleviate":[21],"this":[22,63],"problem":[23],"is":[24,39,53,84,104],"leverage":[26],"samples":[27],"from":[28],"the":[29,51,56,76,92,113],"policy":[30],"demonstrator":[33],"learn":[35],"faster.":[36],"However,":[37],"advice":[38,43,70,80],"normally":[40],"limited,":[41],"hence":[42],"should":[44],"ideally":[45],"be":[46,60],"directed":[47],"states":[49],"where":[50,75],"agent":[52,77,93],"uncertain":[54],"on":[55],"best":[57],"action":[58],"applied.":[61],"In":[62],"work,":[64],"we":[65],"propose":[66],"Requesting":[67],"Confidence-Moderated":[68],"Policy":[69],"(RCMP),":[71],"an":[72],"action-advising":[73],"framework":[74],"asks":[78],"when":[81],"its":[82],"uncertainty":[83,94],"high.":[85],"We":[86],"describe":[87],"technique":[89],"estimate":[91],"with":[95],"minor":[96],"modifications":[97],"in":[98,112],"standard":[99],"value-based":[100],"methods.":[102],"RCMP":[103],"shown":[105],"perform":[107],"better":[108],"than":[109],"several":[110],"baselines":[111],"Atari":[114],"Pong":[115],"domain.":[116]},"counts_by_year":[],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}