{"id":"https://openalex.org/W2965723696","doi":"https://doi.org/10.24963/ijcai.2019/884","title":"Leveraging Human Guidance for Deep Reinforcement Learning Tasks","display_name":"Leveraging Human Guidance for Deep Reinforcement Learning Tasks","publication_year":2019,"publication_date":"2019-07-28","ids":{"openalex":"https://openalex.org/W2965723696","doi":"https://doi.org/10.24963/ijcai.2019/884","mag":"2965723696"},"language":"en","primary_location":{"id":"doi:10.24963/ijcai.2019/884","is_oa":true,"landing_page_url":"https://doi.org/10.24963/ijcai.2019/884","pdf_url":"https://www.ijcai.org/proceedings/2019/0884.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":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://www.ijcai.org/proceedings/2019/0884.pdf","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5101649950","display_name":"Ruohan Zhang","orcid":"https://orcid.org/0000-0001-6681-3360"},"institutions":[{"id":"https://openalex.org/I86519309","display_name":"The University of Texas at Austin","ror":"https://ror.org/00hj54h04","country_code":"US","type":"education","lineage":["https://openalex.org/I86519309"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Ruohan Zhang","raw_affiliation_strings":["Department of Computer Science, University of Texas at Austin, USA"],"affiliations":[{"raw_affiliation_string":"Department of Computer Science, University of Texas at Austin, USA","institution_ids":["https://openalex.org/I86519309"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5027320988","display_name":"Faraz Torabi","orcid":"https://orcid.org/0000-0001-7320-108X"},"institutions":[{"id":"https://openalex.org/I86519309","display_name":"The University of Texas at Austin","ror":"https://ror.org/00hj54h04","country_code":"US","type":"education","lineage":["https://openalex.org/I86519309"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Faraz Torabi","raw_affiliation_strings":["Department of Computer Science, University of Texas at Austin, USA"],"affiliations":[{"raw_affiliation_string":"Department of Computer Science, University of Texas at Austin, USA","institution_ids":["https://openalex.org/I86519309"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5103107194","display_name":"Lin Guan","orcid":"https://orcid.org/0000-0002-2625-707X"},"institutions":[{"id":"https://openalex.org/I86519309","display_name":"The University of Texas at Austin","ror":"https://ror.org/00hj54h04","country_code":"US","type":"education","lineage":["https://openalex.org/I86519309"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Lin Guan","raw_affiliation_strings":["Department of Computer Science, University of Texas at Austin, USA"],"affiliations":[{"raw_affiliation_string":"Department of Computer Science, University of Texas at Austin, USA","institution_ids":["https://openalex.org/I86519309"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5103584849","display_name":"Dana H. Ballard","orcid":null},"institutions":[{"id":"https://openalex.org/I86519309","display_name":"The University of Texas at Austin","ror":"https://ror.org/00hj54h04","country_code":"US","type":"education","lineage":["https://openalex.org/I86519309"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Dana H. Ballard","raw_affiliation_strings":["Department of Computer Science, University of Texas at Austin, USA"],"affiliations":[{"raw_affiliation_string":"Department of Computer Science, University of Texas at Austin, USA","institution_ids":["https://openalex.org/I86519309"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5001594330","display_name":"Peter Stone","orcid":"https://orcid.org/0000-0002-6795-420X"},"institutions":[{"id":"https://openalex.org/I86519309","display_name":"The University of Texas at Austin","ror":"https://ror.org/00hj54h04","country_code":"US","type":"education","lineage":["https://openalex.org/I86519309"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Peter Stone","raw_affiliation_strings":["Department of Computer Science, University of Texas at Austin, USA"],"affiliations":[{"raw_affiliation_string":"Department of Computer Science, University of Texas at Austin, USA","institution_ids":["https://openalex.org/I86519309"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":5,"corresponding_author_ids":["https://openalex.org/A5101649950"],"corresponding_institution_ids":["https://openalex.org/I86519309"],"apc_list":null,"apc_paid":null,"fwci":6.069,"has_fulltext":true,"cited_by_count":69,"citation_normalized_percentile":{"value":0.9699308,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":90,"max":100},"biblio":{"volume":null,"issue":null,"first_page":"6339","last_page":"6346"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10462","display_name":"Reinforcement Learning in Robotics","score":0.9998999834060669,"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":0.9998999834060669,"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/T10653","display_name":"Robot Manipulation and Learning","score":0.9919000267982483,"subfield":{"id":"https://openalex.org/subfields/2207","display_name":"Control and Systems Engineering"},"field":{"id":"https://openalex.org/fields/22","display_name":"Engineering"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T12026","display_name":"Explainable Artificial Intelligence (XAI)","score":0.9871000051498413,"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":0.8346778154373169},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7997593879699707},{"id":"https://openalex.org/keywords/imitation","display_name":"Imitation","score":0.5914056897163391},{"id":"https://openalex.org/keywords/action","display_name":"Action (physics)","score":0.5759260058403015},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5527068376541138},{"id":"https://openalex.org/keywords/human\u2013computer-interaction","display_name":"Human\u2013computer interaction","score":0.5294304490089417},{"id":"https://openalex.org/keywords/error-driven-learning","display_name":"Error-driven learning","score":0.4120975732803345},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.3242667317390442},{"id":"https://openalex.org/keywords/psychology","display_name":"Psychology","score":0.07719114422798157}],"concepts":[{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.8346778154373169},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7997593879699707},{"id":"https://openalex.org/C126388530","wikidata":"https://www.wikidata.org/wiki/Q1131737","display_name":"Imitation","level":2,"score":0.5914056897163391},{"id":"https://openalex.org/C2780791683","wikidata":"https://www.wikidata.org/wiki/Q846785","display_name":"Action (physics)","level":2,"score":0.5759260058403015},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5527068376541138},{"id":"https://openalex.org/C107457646","wikidata":"https://www.wikidata.org/wiki/Q207434","display_name":"Human\u2013computer interaction","level":1,"score":0.5294304490089417},{"id":"https://openalex.org/C47932503","wikidata":"https://www.wikidata.org/wiki/Q5395689","display_name":"Error-driven learning","level":3,"score":0.4120975732803345},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.3242667317390442},{"id":"https://openalex.org/C15744967","wikidata":"https://www.wikidata.org/wiki/Q9418","display_name":"Psychology","level":0,"score":0.07719114422798157},{"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/C77805123","wikidata":"https://www.wikidata.org/wiki/Q161272","display_name":"Social psychology","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}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.24963/ijcai.2019/884","is_oa":true,"landing_page_url":"https://doi.org/10.24963/ijcai.2019/884","pdf_url":"https://www.ijcai.org/proceedings/2019/0884.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"}],"best_oa_location":{"id":"doi:10.24963/ijcai.2019/884","is_oa":true,"landing_page_url":"https://doi.org/10.24963/ijcai.2019/884","pdf_url":"https://www.ijcai.org/proceedings/2019/0884.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":[{"display_name":"Peace, Justice and strong institutions","score":0.7799999713897705,"id":"https://metadata.un.org/sdg/16"}],"awards":[{"id":"https://openalex.org/G1482799704","display_name":null,"funder_award_id":"IIS-1651089","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"},{"id":"https://openalex.org/G187671969","display_name":null,"funder_award_id":"IIS-1637736","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"},{"id":"https://openalex.org/G3609089545","display_name":null,"funder_award_id":"N00014-18-2243","funder_id":"https://openalex.org/F4320310620","funder_display_name":"University of Texas at Austin"},{"id":"https://openalex.org/G3881771821","display_name":null,"funder_award_id":"N00014-18-2243","funder_id":"https://openalex.org/F4320337345","funder_display_name":"Office of Naval Research"},{"id":"https://openalex.org/G5029475413","display_name":null,"funder_award_id":"IIS-1724157","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"},{"id":"https://openalex.org/G6991911153","display_name":"EAGER: Human-Aware Navigation in Populated Indoor Environments","funder_award_id":"1651089","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"},{"id":"https://openalex.org/G829377574","display_name":null,"funder_award_id":"1724157","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"},{"id":"https://openalex.org/G8653745736","display_name":"NRI: Robots that Learn to Communicate through Natural Human Dialog","funder_award_id":"1637736","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"},{"id":"https://openalex.org/G8876996369","display_name":null,"funder_award_id":"N00014","funder_id":"https://openalex.org/F4320337345","funder_display_name":"Office of Naval Research"}],"funders":[{"id":"https://openalex.org/F4320306076","display_name":"National Science Foundation","ror":"https://ror.org/021nxhr62"},{"id":"https://openalex.org/F4320310620","display_name":"University of Texas at Austin","ror":"https://ror.org/00hj54h04"},{"id":"https://openalex.org/F4320332161","display_name":"National Institutes of Health","ror":"https://ror.org/01cwqze88"},{"id":"https://openalex.org/F4320332180","display_name":"Defense Advanced Research Projects Agency","ror":"https://ror.org/02caytj08"},{"id":"https://openalex.org/F4320337345","display_name":"Office of Naval Research","ror":"https://ror.org/00rk2pe57"}],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W2965723696.pdf","grobid_xml":"https://content.openalex.org/works/W2965723696.grobid-xml"},"referenced_works_count":81,"referenced_works":["https://openalex.org/W41554520","https://openalex.org/W1536323281","https://openalex.org/W1931877416","https://openalex.org/W1986014385","https://openalex.org/W1999874108","https://openalex.org/W2074056782","https://openalex.org/W2098441518","https://openalex.org/W2098584016","https://openalex.org/W2109910161","https://openalex.org/W2116157560","https://openalex.org/W2116671302","https://openalex.org/W2118756286","https://openalex.org/W2121110499","https://openalex.org/W2145339207","https://openalex.org/W2150468603","https://openalex.org/W2154023516","https://openalex.org/W2158782408","https://openalex.org/W2166302491","https://openalex.org/W2257979135","https://openalex.org/W2290053245","https://openalex.org/W2294422333","https://openalex.org/W2553882142","https://openalex.org/W2557026499","https://openalex.org/W2563829177","https://openalex.org/W2573393487","https://openalex.org/W2580300496","https://openalex.org/W2591957724","https://openalex.org/W2592285981","https://openalex.org/W2605368761","https://openalex.org/W2612448678","https://openalex.org/W2626804490","https://openalex.org/W2729615412","https://openalex.org/W2735025040","https://openalex.org/W2736629007","https://openalex.org/W2754517384","https://openalex.org/W2760057500","https://openalex.org/W2769112066","https://openalex.org/W2785324569","https://openalex.org/W2788517538","https://openalex.org/W2789740610","https://openalex.org/W2794908222","https://openalex.org/W2801182767","https://openalex.org/W2804020409","https://openalex.org/W2805623918","https://openalex.org/W2884247313","https://openalex.org/W2885138528","https://openalex.org/W2887503931","https://openalex.org/W2889659926","https://openalex.org/W2895299763","https://openalex.org/W2898227854","https://openalex.org/W2904145923","https://openalex.org/W2946501375","https://openalex.org/W2949600457","https://openalex.org/W2950226226","https://openalex.org/W2962787969","https://openalex.org/W2962871243","https://openalex.org/W2962903234","https://openalex.org/W2963277051","https://openalex.org/W2963489214","https://openalex.org/W2963513865","https://openalex.org/W2963802910","https://openalex.org/W2964460729","https://openalex.org/W2965273749","https://openalex.org/W2974377482","https://openalex.org/W2997423597","https://openalex.org/W3006334608","https://openalex.org/W3103780890","https://openalex.org/W4214717370","https://openalex.org/W4289288058","https://openalex.org/W4295837424","https://openalex.org/W4297669644","https://openalex.org/W4300110528","https://openalex.org/W4320013936","https://openalex.org/W4321392130","https://openalex.org/W6650265722","https://openalex.org/W6718092244","https://openalex.org/W6790825729","https://openalex.org/W6791858558","https://openalex.org/W6803771590","https://openalex.org/W6864558200","https://openalex.org/W6892110240"],"related_works":["https://openalex.org/W2202218907","https://openalex.org/W2371091044","https://openalex.org/W2171010636","https://openalex.org/W87513465","https://openalex.org/W1966803121","https://openalex.org/W2391666574","https://openalex.org/W2786230833","https://openalex.org/W3203256658","https://openalex.org/W2352650970","https://openalex.org/W1544514152"],"abstract_inverted_index":{"Reinforcement":[0],"learning":[1,72],"agents":[2],"can":[3,23],"learn":[4],"to":[5,19,33,44],"solve":[6,20],"sequential":[7],"decision":[8],"tasks":[9,22,57],"by":[10],"interacting":[11],"with":[12],"the":[13,30,45,88],"environment.":[14],"Human":[15],"knowledge":[16],"of":[17,49,69,93],"how":[18],"these":[21],"be":[24,52],"incorporated":[25],"using":[26],"imitation":[27],"learning,":[28],"where":[29],"agent":[31],"learns":[32],"imitate":[34],"human":[35,39,61,78],"demonstrated":[36],"decisions.":[37],"However,":[38],"guidance":[40,50,79],"is":[41],"not":[42],"limited":[43],"demonstrations.":[46,85],"Other":[47],"types":[48],"could":[51],"more":[53],"suitable":[54],"for":[55],"certain":[56],"and":[58,91],"require":[59],"less":[60],"effort.":[62],"This":[63],"survey":[64],"provides":[65],"a":[66],"high-level":[67],"overview":[68],"five":[70],"recent":[71],"frameworks":[73],"that":[74],"primarily":[75],"rely":[76],"on":[77],"other":[80],"than":[81],"conventional,":[82],"step-by-step":[83],"action":[84],"We":[86,96],"review":[87],"motivation,":[89],"assumption,":[90],"implementation":[92],"each":[94],"framework.":[95],"then":[97],"discuss":[98],"possible":[99],"future":[100],"research":[101],"directions.":[102]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":5},{"year":2024,"cited_by_count":12},{"year":2023,"cited_by_count":8},{"year":2022,"cited_by_count":7},{"year":2021,"cited_by_count":19},{"year":2020,"cited_by_count":13},{"year":2019,"cited_by_count":3},{"year":2018,"cited_by_count":1}],"updated_date":"2026-03-18T14:38:29.013473","created_date":"2025-10-10T00:00:00"}