{"id":"https://openalex.org/W3131816034","doi":null,"title":"The impacts of known and unknown demonstrator irrationality on reward inference","display_name":"The impacts of known and unknown demonstrator irrationality on reward inference","publication_year":2021,"publication_date":"2021-05-04","ids":{"openalex":"https://openalex.org/W3131816034","mag":"3131816034"},"language":"en","primary_location":{"id":"mag:3131816034","doi":null,"is_oa":false,"landing_page_url":"https://openreview.net/pdf?id=CzRSsOG6JDw","pdf_url":null,"source":null,"license":null,"license_id":null,"version":null,"is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":null},"volume":null,"type":"article","indexed_in":[],"open_access":{"is_oa":false,"oa_status":"closed","oa_url":null,"any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":null,"display_name":"Lawrence S. Chan","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I95457486","display_name":"University of California, Berkeley","ror":"https://ror.org/01an7q238","country_code":"US","type":"education","lineage":["https://openalex.org/I95457486"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Lawrence S. Chan","raw_affiliation_strings":["University of California\u2013Berkeley"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of California\u2013Berkeley","institution_ids":["https://openalex.org/I95457486"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5034938018","display_name":"Andrew Critch","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I95457486","display_name":"University of California, Berkeley","ror":"https://ror.org/01an7q238","country_code":"US","type":"education","lineage":["https://openalex.org/I95457486"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Andrew Critch","raw_affiliation_strings":["University of California\u2013Berkeley"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of California\u2013Berkeley","institution_ids":["https://openalex.org/I95457486"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5005997281","display_name":"Anca D. Dragan","orcid":"https://orcid.org/0000-0001-6312-5466","observed_orcids":["https://orcid.org/0000-0001-6312-5466"]},"institutions":[{"id":"https://openalex.org/I95457486","display_name":"University of California, Berkeley","ror":"https://ror.org/01an7q238","country_code":"US","type":"education","lineage":["https://openalex.org/I95457486"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Anca D. Dragan","raw_affiliation_strings":["University of California\u2013Berkeley"],"raw_orcid":"https://orcid.org/0000-0001-6312-5466","affiliations":[{"raw_affiliation_string":"University of California\u2013Berkeley","institution_ids":["https://openalex.org/I95457486"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I95457486"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.03110752,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"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":0.9994999766349792,"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":0.9994999766349792,"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/T12072","display_name":"Machine Learning and Algorithms","score":0.00019999999494757503,"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":9.999999747378752e-05,"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/human-rationality","display_name":"human rationality","score":0.515999972820282},{"id":"https://openalex.org/keywords/markov-decision-process","display_name":"Markov decision process","score":0.8009999990463257},{"id":"https://openalex.org/keywords/bellman-equation","display_name":"Bellman equation","score":0.9459999799728394},{"id":"https://openalex.org/keywords/model-misspecification","display_name":"model misspecification","score":0.7839999794960022},{"id":"https://openalex.org/keywords/inverse-reinforcement-learning","display_name":"inverse reinforcement learning","score":0.699999988079071}],"concepts":[{"id":"https://openalex.org/C2776214188","wikidata":"https://www.wikidata.org/wiki/Q408386","display_name":"Inference","level":2,"score":0.8820680975914001},{"id":"https://openalex.org/C2777019708","wikidata":"https://www.wikidata.org/wiki/Q1412340","display_name":"Irrationality","level":3,"score":0.864850640296936},{"id":"https://openalex.org/C94931360","wikidata":"https://www.wikidata.org/wiki/Q607728","display_name":"Irrational number","level":2,"score":0.6691815853118896},{"id":"https://openalex.org/C201717286","wikidata":"https://www.wikidata.org/wiki/Q938185","display_name":"Rationality","level":2,"score":0.5879335999488831},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5685287714004517},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4797724187374115},{"id":"https://openalex.org/C160234255","wikidata":"https://www.wikidata.org/wiki/Q812535","display_name":"Bayesian inference","level":3,"score":0.43954741954803467},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.41038841009140015},{"id":"https://openalex.org/C144237770","wikidata":"https://www.wikidata.org/wiki/Q747534","display_name":"Mathematical economics","level":1,"score":0.34301841259002686},{"id":"https://openalex.org/C111472728","wikidata":"https://www.wikidata.org/wiki/Q9471","display_name":"Epistemology","level":1,"score":0.22453764081001282},{"id":"https://openalex.org/C107673813","wikidata":"https://www.wikidata.org/wiki/Q812534","display_name":"Bayesian probability","level":2,"score":0.21848466992378235},{"id":"https://openalex.org/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","level":0,"score":0.2136717140674591},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.18437063694000244},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0},{"id":"https://openalex.org/C2524010","wikidata":"https://www.wikidata.org/wiki/Q8087","display_name":"Geometry","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"mag:3131816034","doi":null,"is_oa":false,"landing_page_url":"https://openreview.net/pdf?id=CzRSsOG6JDw","pdf_url":null,"source":null,"license":null,"license_id":null,"version":null,"is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":null}],"best_oa_location":null,"sustainable_development_goals":[],"study_designs":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":["https://openalex.org/W3213466727","https://openalex.org/W2987338885","https://openalex.org/W2911902289","https://openalex.org/W4382239602","https://openalex.org/W2946249608","https://openalex.org/W4311249297","https://openalex.org/W3099454838","https://openalex.org/W4415189321","https://openalex.org/W2898454860","https://openalex.org/W3033617194"],"abstract_inverted_index":{"Algorithms":[0],"inferring":[1],"rewards":[2],"from":[3],"human":[4,206,229],"behavior":[5],"typically":[6],"assume":[7],"that":[8,35,73,115,128],"people":[9,15],"are":[10,116,217],"(approximately)":[11],"rational.":[12],"In":[13,150],"reality,":[14],"exhibit":[16],"a":[17,104,158,228],"wide":[18],"array":[19],"of":[20,27,47,52,121,139,212],"irrationalities.":[21],"Motivated":[22],"by":[23,54],"understanding":[24],"the":[25,33,50,56,95,122,132,136,140,166,174,221],"benefits":[26],"modeling":[28],"these":[29,67,143],"irrationalities,":[30],"we":[31,126,130,154,203],"analyze":[32],"effects":[34],"demonstrator":[36,80,123],"irrationality":[37,48],"has":[38],"on":[39],"reward":[40,86,112,148,182],"inference.":[41,70,101,149,183],"We":[42,71,184],"propose":[43],"operationalizing":[44],"several":[45,189],"forms":[46],"in":[49,90,188],"language":[51],"MDPs,":[53],"altering":[55],"Bellman":[57],"optimality":[58],"equation,":[59],"and":[60,165,223],"use":[61],"this":[62,186,192],"framework":[63],"to":[64,83,99,106,119,135,230],"study":[65],"how":[66],"alterations":[68],"affect":[69],"find":[72,111,127],"incorrectly":[74],"assuming":[75],"noisy-rationality":[76],"for":[77,181,208,220,227],"an":[78],"irrational":[79],"can":[81,145],"lead":[82],"remarkably":[84],"poor":[85],"inference":[87,93,113],"accuracy,":[88],"even":[89],"situations":[91],"where":[92,160,169],"with":[94],"correct":[96,137],"model":[97,108,138],"leads":[98],"good":[100],"This":[102],"suggests":[103],"need":[105],"either":[107],"irrationalities":[109,144],"or":[110],"algorithms":[114],"more":[117,218],"robust":[118],"misspecification":[120],"model.":[124],"Surprisingly,":[125],"if":[129,153],"give":[131],"learner":[133,222],"access":[134],"demonstrator's":[141],"irrationality,":[142],"actually":[146],"help":[147],"other":[151],"words,":[152],"could":[155],"choose":[156],"between":[157],"world":[159,168,176],"humans":[161,170],"were":[162],"perfectly":[163],"rational":[164],"current":[167,175],"have":[171],"systematic":[172],"biases,":[173],"might":[177,204,224],"counter-intuitively":[178],"be":[179,225],"preferable":[180],"reproduce":[185],"effect":[187],"domains.":[190],"While":[191],"finding":[193],"is":[194,198],"mainly":[195],"conceptual,":[196],"it":[197],"perhaps":[199],"actionable":[200],"as":[201,215],"well:":[202],"ask":[205],"demonstrators":[207],"myopic":[209],"demonstrations":[210],"instead":[211],"optimal":[213],"ones,":[214],"they":[216],"informative":[219],"easier":[226],"generate.":[231]},"counts_by_year":[],"updated_date":"2026-09-27T08:07:27.782135","created_date":"2021-03-01T00:00:00"}