{"id":"https://openalex.org/W3177493366","doi":"https://doi.org/10.1007/s10458-021-09514-w","title":"Recent advances in leveraging human guidance for sequential decision-making tasks","display_name":"Recent advances in leveraging human guidance for sequential decision-making tasks","publication_year":2021,"publication_date":"2021-06-23","ids":{"openalex":"https://openalex.org/W3177493366","doi":"https://doi.org/10.1007/s10458-021-09514-w","mag":"3177493366"},"language":"en","primary_location":{"id":"doi:10.1007/s10458-021-09514-w","is_oa":false,"landing_page_url":"https://doi.org/10.1007/s10458-021-09514-w","pdf_url":null,"source":{"id":"https://openalex.org/S5405189","display_name":"Autonomous Agents and Multi-Agent Systems","issn_l":"1387-2532","issn":["1387-2532","1573-7454"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319900","host_organization_name":"Springer Science+Business Media","host_organization_lineage":["https://openalex.org/P4310319900","https://openalex.org/P4310319965"],"host_organization_lineage_names":["Springer Science+Business Media","Springer Nature"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Autonomous Agents and Multi-Agent Systems","raw_type":"journal-article"},"type":"article","indexed_in":["arxiv","crossref"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2107.05825","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":null,"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, The University of Texas at Austin, Austin, USA"],"raw_orcid":"https://orcid.org/0000-0001-6681-3360","affiliations":[{"raw_affiliation_string":"Department of Computer Science, The University of Texas at Austin, Austin, USA","institution_ids":["https://openalex.org/I86519309"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Faraz Torabi","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":"Faraz Torabi","raw_affiliation_strings":["Department of Computer Science, The University of Texas at Austin, Austin, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Computer Science, The University of Texas at Austin, Austin, USA","institution_ids":["https://openalex.org/I86519309"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Garrett Warnell","orcid":null},"institutions":[{"id":"https://openalex.org/I166416128","display_name":"DEVCOM Army Research Laboratory","ror":"https://ror.org/011hc8f90","country_code":"US","type":"government","lineage":["https://openalex.org/I1304082316","https://openalex.org/I1330347796","https://openalex.org/I166416128","https://openalex.org/I2802705668","https://openalex.org/I4210154437"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Garrett Warnell","raw_affiliation_strings":["U.S. Army Research Laboratory, Adelphi, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"U.S. Army Research Laboratory, Adelphi, USA","institution_ids":["https://openalex.org/I166416128"]}]},{"author_position":"last","author":{"id":null,"display_name":"Peter Stone","orcid":null},"institutions":[{"id":"https://openalex.org/I2800278093","display_name":"Sony Corporation (United States)","ror":"https://ror.org/05k91zb11","country_code":"US","type":"company","lineage":["https://openalex.org/I2800278093"]},{"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, The University of Texas at Austin, Austin, USA","Sony AI, Austin, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Computer Science, The University of Texas at Austin, Austin, USA","institution_ids":["https://openalex.org/I86519309"]},{"raw_affiliation_string":"Sony AI, Austin, USA","institution_ids":["https://openalex.org/I2800278093"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I86519309"],"apc_list":{"value":2990,"currency":"USD","value_usd":2990},"apc_paid":null,"fwci":1.6905,"has_fulltext":false,"cited_by_count":14,"citation_normalized_percentile":{"value":0.86725153,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":99},"biblio":{"volume":"35","issue":"2","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":0.2840000092983246,"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":0.2840000092983246,"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/T12026","display_name":"Explainable Artificial Intelligence (XAI)","score":0.23029999434947968,"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":0.11479999870061874,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.6538000106811523},{"id":"https://openalex.org/keywords/action","display_name":"Action (physics)","score":0.5206000208854675},{"id":"https://openalex.org/keywords/reinforcement-learning","display_name":"Reinforcement learning","score":0.3540000021457672},{"id":"https://openalex.org/keywords/applications-of-artificial-intelligence","display_name":"Applications of artificial intelligence","score":0.2946000099182129},{"id":"https://openalex.org/keywords/control","display_name":"Control (management)","score":0.28790000081062317},{"id":"https://openalex.org/keywords/deep-learning","display_name":"Deep learning","score":0.274399995803833}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7196999788284302},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.6538000106811523},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5834000110626221},{"id":"https://openalex.org/C2780791683","wikidata":"https://www.wikidata.org/wiki/Q846785","display_name":"Action (physics)","level":2,"score":0.5206000208854675},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.37290000915527344},{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.3540000021457672},{"id":"https://openalex.org/C107457646","wikidata":"https://www.wikidata.org/wiki/Q207434","display_name":"Human\u2013computer interaction","level":1,"score":0.3140999972820282},{"id":"https://openalex.org/C157170001","wikidata":"https://www.wikidata.org/wiki/Q4781507","display_name":"Applications of artificial intelligence","level":2,"score":0.2946000099182129},{"id":"https://openalex.org/C2775924081","wikidata":"https://www.wikidata.org/wiki/Q55608371","display_name":"Control (management)","level":2,"score":0.28790000081062317},{"id":"https://openalex.org/C108583219","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep learning","level":2,"score":0.274399995803833},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.2736000120639801},{"id":"https://openalex.org/C186370098","wikidata":"https://www.wikidata.org/wiki/Q442787","display_name":"Energy (signal processing)","level":2,"score":0.27250000834465027},{"id":"https://openalex.org/C14036430","wikidata":"https://www.wikidata.org/wiki/Q3736076","display_name":"Function (biology)","level":2,"score":0.2603999972343445},{"id":"https://openalex.org/C74072328","wikidata":"https://www.wikidata.org/wiki/Q1142726","display_name":"Intelligent agent","level":2,"score":0.2574999928474426},{"id":"https://openalex.org/C166109690","wikidata":"https://www.wikidata.org/wiki/Q4677422","display_name":"Action selection","level":3,"score":0.25049999356269836}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1007/s10458-021-09514-w","is_oa":false,"landing_page_url":"https://doi.org/10.1007/s10458-021-09514-w","pdf_url":null,"source":{"id":"https://openalex.org/S5405189","display_name":"Autonomous Agents and Multi-Agent Systems","issn_l":"1387-2532","issn":["1387-2532","1573-7454"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319900","host_organization_name":"Springer Science+Business Media","host_organization_lineage":["https://openalex.org/P4310319900","https://openalex.org/P4310319965"],"host_organization_lineage_names":["Springer Science+Business Media","Springer Nature"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Autonomous Agents and Multi-Agent Systems","raw_type":"journal-article"},{"id":"pmh:oai:arXiv.org:2107.05825","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2107.05825","pdf_url":"https://arxiv.org/pdf/2107.05825","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"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2107.05825","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2107.05825","pdf_url":"https://arxiv.org/pdf/2107.05825","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"},"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G1380569734","display_name":null,"funder_award_id":"IIS-1724157","funder_id":"https://openalex.org/F4320335353","funder_display_name":"National Science Foundation of Sri Lanka"},{"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/G4146842226","display_name":null,"funder_award_id":"IIS-1637736","funder_id":"https://openalex.org/F4320335353","funder_display_name":"National Science Foundation of Sri Lanka"},{"id":"https://openalex.org/G462198915","display_name":null,"funder_award_id":"IIS-1651089","funder_id":"https://openalex.org/F4320335353","funder_display_name":"National Science Foundation of Sri Lanka"},{"id":"https://openalex.org/G5790664769","display_name":null,"funder_award_id":"RFP2- 000","funder_id":"https://openalex.org/F4320317463","funder_display_name":"Future of Life Institute"}],"funders":[{"id":"https://openalex.org/F4320306994","display_name":"Lockheed Martin","ror":"https://ror.org/026er9r08"},{"id":"https://openalex.org/F4320307102","display_name":"Intel Corporation","ror":"https://ror.org/01ek73717"},{"id":"https://openalex.org/F4320307943","display_name":"Raytheon Company","ror":"https://ror.org/0354t7b78"},{"id":"https://openalex.org/F4320317463","display_name":"Future of Life Institute","ror":null},{"id":"https://openalex.org/F4320332180","display_name":"Defense Advanced Research Projects Agency","ror":"https://ror.org/02caytj08"},{"id":"https://openalex.org/F4320335353","display_name":"National Science Foundation of Sri Lanka","ror":"https://ror.org/010xaa060"},{"id":"https://openalex.org/F4320337345","display_name":"Office of Naval Research","ror":"https://ror.org/00rk2pe57"},{"id":"https://openalex.org/F4320338295","display_name":"Army Research Laboratory","ror":"https://ror.org/011hc8f90"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":198,"referenced_works":["https://openalex.org/W32403112","https://openalex.org/W67472587","https://openalex.org/W114159433","https://openalex.org/W1536323281","https://openalex.org/W1539716820","https://openalex.org/W1592847719","https://openalex.org/W1769933788","https://openalex.org/W1772076007","https://openalex.org/W1888002310","https://openalex.org/W1895481937","https://openalex.org/W1931877416","https://openalex.org/W1963873191","https://openalex.org/W1969897050","https://openalex.org/W1977124739","https://openalex.org/W1977655452","https://openalex.org/W1986014385","https://openalex.org/W1987540542","https://openalex.org/W1996847178","https://openalex.org/W1999874108","https://openalex.org/W2002675616","https://openalex.org/W2004210808","https://openalex.org/W2007571554","https://openalex.org/W2010916807","https://openalex.org/W2013643315","https://openalex.org/W2027879843","https://openalex.org/W2046376809","https://openalex.org/W2063471043","https://openalex.org/W2071555787","https://openalex.org/W2074056782","https://openalex.org/W2082764616","https://openalex.org/W2086791339","https://openalex.org/W2098441518","https://openalex.org/W2098584016","https://openalex.org/W2098774185","https://openalex.org/W2103254706","https://openalex.org/W2105670030","https://openalex.org/W2106793164","https://openalex.org/W2109910161","https://openalex.org/W2110304639","https://openalex.org/W2116157560","https://openalex.org/W2116671302","https://openalex.org/W2118756286","https://openalex.org/W2121110499","https://openalex.org/W2121517924","https://openalex.org/W2122777916","https://openalex.org/W2127516259","https://openalex.org/W2128272608","https://openalex.org/W2134491302","https://openalex.org/W2145339207","https://openalex.org/W2147544021","https://openalex.org/W2149897770","https://openalex.org/W2150468603","https://openalex.org/W2154023516","https://openalex.org/W2155027007","https://openalex.org/W2155307968","https://openalex.org/W2156869222","https://openalex.org/W2158782408","https://openalex.org/W2166302491","https://openalex.org/W2167224731","https://openalex.org/W2172058945","https://openalex.org/W2173564293","https://openalex.org/W2257979135","https://openalex.org/W2290104316","https://openalex.org/W2294422333","https://openalex.org/W2296673577","https://openalex.org/W2335959470","https://openalex.org/W2410842990","https://openalex.org/W2468114283","https://openalex.org/W2469134594","https://openalex.org/W2487442924","https://openalex.org/W2520859141","https://openalex.org/W2551182329","https://openalex.org/W2553882142","https://openalex.org/W2559085405","https://openalex.org/W2573393487","https://openalex.org/W2580300496","https://openalex.org/W2594829461","https://openalex.org/W2595845486","https://openalex.org/W2598992495","https://openalex.org/W2605368761","https://openalex.org/W2618170641","https://openalex.org/W2626804490","https://openalex.org/W2735318784","https://openalex.org/W2736629007","https://openalex.org/W2754517384","https://openalex.org/W2765629358","https://openalex.org/W2766354286","https://openalex.org/W2766447205","https://openalex.org/W2769112066","https://openalex.org/W2785324569","https://openalex.org/W2786760026","https://openalex.org/W2786808285","https://openalex.org/W2788517538","https://openalex.org/W2792164665","https://openalex.org/W2794281269","https://openalex.org/W2796290181","https://openalex.org/W2799064164","https://openalex.org/W2801182767","https://openalex.org/W2803281228","https://openalex.org/W2805623918","https://openalex.org/W2810602713","https://openalex.org/W2884915206","https://openalex.org/W2887493770","https://openalex.org/W2887503931","https://openalex.org/W2887806157","https://openalex.org/W2889659926","https://openalex.org/W2889990052","https://openalex.org/W2890026535","https://openalex.org/W2890319312","https://openalex.org/W2892024327","https://openalex.org/W2894766094","https://openalex.org/W2895299763","https://openalex.org/W2895640967","https://openalex.org/W2897762477","https://openalex.org/W2900293887","https://openalex.org/W2902907165","https://openalex.org/W2911383979","https://openalex.org/W2914626659","https://openalex.org/W2919115771","https://openalex.org/W2925362180","https://openalex.org/W2939047085","https://openalex.org/W2945438069","https://openalex.org/W2946160813","https://openalex.org/W2946501375","https://openalex.org/W2946780324","https://openalex.org/W2947813496","https://openalex.org/W2947918549","https://openalex.org/W2950226226","https://openalex.org/W2962787969","https://openalex.org/W2962793481","https://openalex.org/W2962845991","https://openalex.org/W2962871243","https://openalex.org/W2962894046","https://openalex.org/W2962965915","https://openalex.org/W2963082988","https://openalex.org/W2963367680","https://openalex.org/W2963403143","https://openalex.org/W2963489214","https://openalex.org/W2963503775","https://openalex.org/W2963513865","https://openalex.org/W2963709863","https://openalex.org/W2963802910","https://openalex.org/W2964021598","https://openalex.org/W2964055695","https://openalex.org/W2964177756","https://openalex.org/W2964227312","https://openalex.org/W2964460729","https://openalex.org/W2965273749","https://openalex.org/W2965723696","https://openalex.org/W2968227116","https://openalex.org/W2970003882","https://openalex.org/W2973266032","https://openalex.org/W2974377482","https://openalex.org/W2976087789","https://openalex.org/W2976205474","https://openalex.org/W2980102702","https://openalex.org/W2981038142","https://openalex.org/W2981701630","https://openalex.org/W2982316857","https://openalex.org/W2983096300","https://openalex.org/W2989068617","https://openalex.org/W2996784529","https://openalex.org/W2997423597","https://openalex.org/W2997842202","https://openalex.org/W3003156477","https://openalex.org/W3005857605","https://openalex.org/W3009130550","https://openalex.org/W3039563104","https://openalex.org/W3041498386","https://openalex.org/W3043142510","https://openalex.org/W3044004758","https://openalex.org/W3089642969","https://openalex.org/W3100675723","https://openalex.org/W3101780148","https://openalex.org/W3102987364","https://openalex.org/W3175395689","https://openalex.org/W3197594072","https://openalex.org/W4206434057","https://openalex.org/W4232512588","https://openalex.org/W6624921604","https://openalex.org/W6638018090","https://openalex.org/W6677916085","https://openalex.org/W6680724558","https://openalex.org/W6682849425","https://openalex.org/W6685664872","https://openalex.org/W6691478525","https://openalex.org/W6696265566","https://openalex.org/W6718092244","https://openalex.org/W6729863922","https://openalex.org/W6730844258","https://openalex.org/W6732033900","https://openalex.org/W6734502593","https://openalex.org/W6736217450","https://openalex.org/W6748972340","https://openalex.org/W6751955673","https://openalex.org/W6758209225","https://openalex.org/W6761160594","https://openalex.org/W6843699536"],"related_works":[],"abstract_inverted_index":null,"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2024,"cited_by_count":9},{"year":2023,"cited_by_count":2},{"year":2022,"cited_by_count":1},{"year":2021,"cited_by_count":1}],"updated_date":"2026-07-23T08:03:31.855105","created_date":"2021-07-05T00:00:00"}