{"id":"https://openalex.org/W2789066082","doi":"https://doi.org/10.1609/aaai.v32i1.11739","title":"Learning to Interact With Learning Agents","display_name":"Learning to Interact With Learning Agents","publication_year":2018,"publication_date":"2018-04-29","ids":{"openalex":"https://openalex.org/W2789066082","doi":"https://doi.org/10.1609/aaai.v32i1.11739","mag":"2789066082"},"language":"en","primary_location":{"id":"doi:10.1609/aaai.v32i1.11739","is_oa":true,"landing_page_url":"https://doi.org/10.1609/aaai.v32i1.11739","pdf_url":"https://ojs.aaai.org/index.php/AAAI/article/download/11739/11598","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/11739/11598","any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5027711113","display_name":"Adish Singla","orcid":"https://orcid.org/0000-0001-9922-0668"},"institutions":[{"id":"https://openalex.org/I4210121786","display_name":"Max Planck Institute for Software Systems","ror":"https://ror.org/02pe2kf23","country_code":"DE","type":"facility","lineage":["https://openalex.org/I149899117","https://openalex.org/I4210121786"]}],"countries":["DE"],"is_corresponding":true,"raw_author_name":"Adish Singla","raw_affiliation_strings":["MPI-SWS"],"affiliations":[{"raw_affiliation_string":"MPI-SWS","institution_ids":["https://openalex.org/I4210121786"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5059354479","display_name":"Hamed Hassani","orcid":"https://orcid.org/0000-0002-9448-8750"},"institutions":[{"id":"https://openalex.org/I36788626","display_name":"California University of Pennsylvania","ror":"https://ror.org/01spssf70","country_code":"US","type":"education","lineage":["https://openalex.org/I36788626"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Hamed Hassani","raw_affiliation_strings":["University of Pennsylvania"],"affiliations":[{"raw_affiliation_string":"University of Pennsylvania","institution_ids":["https://openalex.org/I36788626"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5003040843","display_name":"Andreas Krause","orcid":"https://orcid.org/0000-0001-7260-9673"},"institutions":[{"id":"https://openalex.org/I35440088","display_name":"ETH Zurich","ror":"https://ror.org/05a28rw58","country_code":"CH","type":"education","lineage":["https://openalex.org/I2799323385","https://openalex.org/I35440088"]}],"countries":["CH"],"is_corresponding":false,"raw_author_name":"Andreas Krause","raw_affiliation_strings":["ETH  Zurich"],"affiliations":[{"raw_affiliation_string":"ETH  Zurich","institution_ids":["https://openalex.org/I35440088"]}]}],"institutions":[],"countries_distinct_count":3,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5027711113"],"corresponding_institution_ids":["https://openalex.org/I4210121786"],"apc_list":null,"apc_paid":null,"fwci":1.7707,"has_fulltext":true,"cited_by_count":8,"citation_normalized_percentile":{"value":0.84751773,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":96},"biblio":{"volume":"32","issue":"1","first_page":null,"last_page":null},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T12101","display_name":"Advanced Bandit Algorithms Research","score":1.0,"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"}},"topics":[{"id":"https://openalex.org/T12101","display_name":"Advanced Bandit Algorithms Research","score":1.0,"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/T12072","display_name":"Machine Learning and Algorithms","score":0.9983999729156494,"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/T10462","display_name":"Reinforcement Learning in Robotics","score":0.9923999905586243,"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/regret","display_name":"Regret","score":0.8843125104904175},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7082277536392212},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.6015450954437256},{"id":"https://openalex.org/keywords/process","display_name":"Process (computing)","score":0.566882312297821},{"id":"https://openalex.org/keywords/ask-price","display_name":"Ask price","score":0.5275527834892273},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.48533812165260315},{"id":"https://openalex.org/keywords/advice","display_name":"Advice (programming)","score":0.4195248484611511}],"concepts":[{"id":"https://openalex.org/C50817715","wikidata":"https://www.wikidata.org/wiki/Q79895177","display_name":"Regret","level":2,"score":0.8843125104904175},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7082277536392212},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6015450954437256},{"id":"https://openalex.org/C98045186","wikidata":"https://www.wikidata.org/wiki/Q205663","display_name":"Process (computing)","level":2,"score":0.566882312297821},{"id":"https://openalex.org/C90329073","wikidata":"https://www.wikidata.org/wiki/Q914232","display_name":"Ask price","level":2,"score":0.5275527834892273},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.48533812165260315},{"id":"https://openalex.org/C2779955035","wikidata":"https://www.wikidata.org/wiki/Q4686785","display_name":"Advice (programming)","level":2,"score":0.4195248484611511},{"id":"https://openalex.org/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","level":0,"score":0.0},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.0},{"id":"https://openalex.org/C136264566","wikidata":"https://www.wikidata.org/wiki/Q159810","display_name":"Economy","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}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1609/aaai.v32i1.11739","is_oa":true,"landing_page_url":"https://doi.org/10.1609/aaai.v32i1.11739","pdf_url":"https://ojs.aaai.org/index.php/AAAI/article/download/11739/11598","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"},{"id":"pmh:oai:pure.mpg.de:item_3038033","is_oa":false,"landing_page_url":"http://hdl.handle.net/21.11116/0000-0003-4204-E","pdf_url":null,"source":{"id":"https://openalex.org/S4306400654","display_name":"MPG.PuRe (Max Planck Society)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I149899117","host_organization_name":"Max Planck Society","host_organization_lineage":["https://openalex.org/I149899117"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Thirty-Second AAAI Conference on Artificial Intelligence","raw_type":"info:eu-repo/semantics/conferenceObject"}],"best_oa_location":{"id":"doi:10.1609/aaai.v32i1.11739","is_oa":true,"landing_page_url":"https://doi.org/10.1609/aaai.v32i1.11739","pdf_url":"https://ojs.aaai.org/index.php/AAAI/article/download/11739/11598","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":0.4399999976158142,"id":"https://metadata.un.org/sdg/4","display_name":"Quality Education"}],"awards":[{"id":"https://openalex.org/G3631313543","display_name":null,"funder_award_id":"Fellowship","funder_id":"https://openalex.org/F4320308943","funder_display_name":"Microsoft Research"},{"id":"https://openalex.org/G4621158401","display_name":null,"funder_award_id":"Fellowship","funder_id":"https://openalex.org/F4320320924","funder_display_name":"Schweizerischer Nationalfonds zur F\u00f6rderung der Wissenschaftlichen Forschung"},{"id":"https://openalex.org/G6894402473","display_name":null,"funder_award_id":"Fellowship","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"},{"id":"https://openalex.org/G848032724","display_name":null,"funder_award_id":"Science","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"},{"id":"https://openalex.org/G8632685092","display_name":null,"funder_award_id":"Nano-Tera.ch","funder_id":"https://openalex.org/F4320320924","funder_display_name":"Schweizerischer Nationalfonds zur F\u00f6rderung der Wissenschaftlichen Forschung"}],"funders":[{"id":"https://openalex.org/F4320306076","display_name":"National Science Foundation","ror":"https://ror.org/021nxhr62"},{"id":"https://openalex.org/F4320308943","display_name":"Microsoft Research","ror":"https://ror.org/00d0nc645"},{"id":"https://openalex.org/F4320320924","display_name":"Schweizerischer Nationalfonds zur F\u00f6rderung der Wissenschaftlichen Forschung","ror":"https://ror.org/00yjd3n13"}],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W2789066082.pdf","grobid_xml":"https://content.openalex.org/works/W2789066082.grobid-xml"},"referenced_works_count":51,"referenced_works":["https://openalex.org/W77456527","https://openalex.org/W172143579","https://openalex.org/W603830301","https://openalex.org/W858396460","https://openalex.org/W1552540037","https://openalex.org/W1570963478","https://openalex.org/W1666672054","https://openalex.org/W1876956220","https://openalex.org/W1979675141","https://openalex.org/W1987292194","https://openalex.org/W1988790447","https://openalex.org/W2049934117","https://openalex.org/W2056921512","https://openalex.org/W2077723394","https://openalex.org/W2077902449","https://openalex.org/W2093825590","https://openalex.org/W2097160297","https://openalex.org/W2101379030","https://openalex.org/W2118849971","https://openalex.org/W2124987122","https://openalex.org/W2140679654","https://openalex.org/W2148825261","https://openalex.org/W2174904372","https://openalex.org/W2178225304","https://openalex.org/W2398650862","https://openalex.org/W2768395342","https://openalex.org/W2949220790","https://openalex.org/W2951945213","https://openalex.org/W2952412049","https://openalex.org/W2962821829","https://openalex.org/W2963297691","https://openalex.org/W2963352368","https://openalex.org/W2963528280","https://openalex.org/W2964163363","https://openalex.org/W3125634603","https://openalex.org/W4239944506","https://openalex.org/W4248437541","https://openalex.org/W4292022450","https://openalex.org/W4299976370","https://openalex.org/W4300825327","https://openalex.org/W4301602758","https://openalex.org/W6618347045","https://openalex.org/W6634426871","https://openalex.org/W6637001620","https://openalex.org/W6645014807","https://openalex.org/W6663955052","https://openalex.org/W6669877065","https://openalex.org/W6674610798","https://openalex.org/W6685610511","https://openalex.org/W6685697101","https://openalex.org/W6732288629"],"related_works":["https://openalex.org/W1788769502","https://openalex.org/W4300938612","https://openalex.org/W2961085424","https://openalex.org/W2758477799","https://openalex.org/W2951751878","https://openalex.org/W1507350478","https://openalex.org/W4246875181","https://openalex.org/W1595172814","https://openalex.org/W4306674287","https://openalex.org/W4231722738"],"abstract_inverted_index":{"AI":[0],"and":[1,9,15,114,168,239],"machine":[2],"learning":[3,17,21,38,58,74,193,247],"methods":[4],"are":[5],"increasingly":[6],"interacting":[7],"with":[8,62,134,147],"seeking":[10,76],"information":[11],"from":[12,111,207],"people,":[13],"robots,":[14],"other":[16],"agents.":[18],"Consequently,":[19],"the":[20,35,54,97,105,112,135,143,148,157,166,169,188,192,196,202,208,212,246,250],"dynamics":[22,248],"of":[23,37,53,56,150,195,201,249],"these":[24,47],"agents":[25],"creates":[26],"fundamentally":[27],"new":[28],"challenges":[29,48,89],"for":[30,221],"existing":[31],"methods.":[32],"Motivated":[33],"by":[34,49,104,198,205],"application":[36],"to":[39,43,77,87,116,124,131,174,190,216],"offer":[40],"personalized":[41],"deals":[42],"users,":[44],"we":[45,68,230,240],"highlight":[46],"studying":[50],"a":[51,73,176,184],"variant":[52],"framework":[55],"\"online":[57],"using":[59],"expert":[60,71,98,137,153,214,252],"advice":[61],"bandit":[63,84],"feedback.\"":[64],"In":[65],"our":[66,232],"setting,":[67],"consider":[69,183],"each":[70],"as":[72],"agent,":[75],"more":[78],"accurately":[79],"reflect":[80],"real-world":[81],"applications.":[82],"The":[83],"feedback":[85,110,203],"leads":[86],"additional":[88,227],"in":[90],"this":[91,119,226],"setting:":[92],"at":[93,118,218],"time":[94,219,223],"t,":[95],"only":[96],"it":[99,128,140,171,215],"that":[100,235],"has":[101],"been":[102],"selected":[103,213],"central":[106],"algorithm":[107],"(forecaster)":[108],"receives":[109],"environment":[113],"gets":[115],"learn":[117,217],"time.":[120],"A":[121],"natural":[122],"question":[123],"ask":[125],"is":[126,129,172],"whether":[127],"possible":[130],"be":[132],"competitive":[133,146],"best":[136,251],"j*":[138],"had":[139],"seen":[141],"all":[142],"feedback,":[144],"i.e.,":[145,210],"policy":[149],"always":[151],"selecting":[152],"j*.":[154,253],"We":[155,181],"prove":[156],"following":[158],"hardness":[159],"result":[160],"\u2014":[161],"without":[162],"any":[163],"coordination":[164,228],"between":[165],"forecaster":[167,177,189,233],"experts,":[170],"impossible":[173],"design":[175,231],"achieving":[178],"no-regret":[179,237],"guarantees.":[180],"then":[182],"practical":[185],"assumption":[186],"allowing":[187],"guide":[191],"process":[194],"experts":[197],"blocking":[199],"some":[200,222],"observed":[204],"them":[206],"environment,":[209],"restricting":[211],"t":[220],"steps.":[224],"With":[225],"power,":[229],"LIL":[234],"achieves":[236],"guarantees,":[238],"provide":[241],"regret":[242],"bounds":[243],"dependent":[244],"on":[245]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2024,"cited_by_count":1},{"year":2022,"cited_by_count":1},{"year":2021,"cited_by_count":2},{"year":2020,"cited_by_count":1},{"year":2019,"cited_by_count":2}],"updated_date":"2026-04-18T07:56:08.524223","created_date":"2025-10-10T00:00:00"}