{"id":"https://openalex.org/W2036677526","doi":"https://doi.org/10.1109/roman.2012.6343863","title":"Monte Carlo preference elicitation for learning additive reward functions","display_name":"Monte Carlo preference elicitation for learning additive reward functions","publication_year":2012,"publication_date":"2012-09-01","ids":{"openalex":"https://openalex.org/W2036677526","doi":"https://doi.org/10.1109/roman.2012.6343863","mag":"2036677526"},"language":"en","primary_location":{"id":"doi:10.1109/roman.2012.6343863","is_oa":false,"landing_page_url":"https://doi.org/10.1109/roman.2012.6343863","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2012 IEEE RO-MAN: The 21st IEEE International Symposium on Robot and Human Interactive Communication","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":false,"oa_status":"closed","oa_url":null,"any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5086237721","display_name":"Stephanie Rosenthal","orcid":"https://orcid.org/0000-0002-7583-4590"},"institutions":[{"id":"https://openalex.org/I74973139","display_name":"Carnegie Mellon University","ror":"https://ror.org/05x2bcf33","country_code":"US","type":"education","lineage":["https://openalex.org/I74973139"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Stephanie Rosenthal","raw_affiliation_strings":["Carnegie Mellon University, Pittsburgh, PA, USA","Carnegie-Mellon University, Pittsburgh, Pa., USA#TAB#"],"affiliations":[{"raw_affiliation_string":"Carnegie Mellon University, Pittsburgh, PA, USA","institution_ids":["https://openalex.org/I74973139"]},{"raw_affiliation_string":"Carnegie-Mellon University, Pittsburgh, Pa., USA#TAB#","institution_ids":["https://openalex.org/I74973139"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5088276691","display_name":"Manuela Veloso","orcid":"https://orcid.org/0000-0001-6738-238X"},"institutions":[{"id":"https://openalex.org/I74973139","display_name":"Carnegie Mellon University","ror":"https://ror.org/05x2bcf33","country_code":"US","type":"education","lineage":["https://openalex.org/I74973139"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Manuela Veloso","raw_affiliation_strings":["Carnegie Mellon University, Pittsburgh, PA, USA","Carnegie-Mellon University, Pittsburgh, Pa., USA#TAB#"],"affiliations":[{"raw_affiliation_string":"Carnegie Mellon University, Pittsburgh, PA, USA","institution_ids":["https://openalex.org/I74973139"]},{"raw_affiliation_string":"Carnegie-Mellon University, Pittsburgh, Pa., USA#TAB#","institution_ids":["https://openalex.org/I74973139"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5086237721"],"corresponding_institution_ids":["https://openalex.org/I74973139"],"apc_list":null,"apc_paid":null,"fwci":0.3789517,"has_fulltext":false,"cited_by_count":2,"citation_normalized_percentile":{"value":0.71418314,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":94},"biblio":{"volume":"11","issue":null,"first_page":"886","last_page":"891"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10462","display_name":"Reinforcement Learning in Robotics","score":0.9976999759674072,"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":0.9976999759674072,"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/T11303","display_name":"Bayesian Modeling and Causal Inference","score":0.991599977016449,"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/T12423","display_name":"Software Reliability and Analysis Research","score":0.9661999940872192,"subfield":{"id":"https://openalex.org/subfields/1712","display_name":"Software"},"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/computer-science","display_name":"Computer science","score":0.6818246245384216},{"id":"https://openalex.org/keywords/preference-learning","display_name":"Preference learning","score":0.6711865067481995},{"id":"https://openalex.org/keywords/monte-carlo-method","display_name":"Monte Carlo method","score":0.6638568639755249},{"id":"https://openalex.org/keywords/preference-elicitation","display_name":"Preference elicitation","score":0.6092138290405273},{"id":"https://openalex.org/keywords/set","display_name":"Set (abstract data type)","score":0.5642518401145935},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5546947121620178},{"id":"https://openalex.org/keywords/preference","display_name":"Preference","score":0.5507763028144836},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.49458858370780945},{"id":"https://openalex.org/keywords/reinforcement-learning","display_name":"Reinforcement learning","score":0.4738374650478363},{"id":"https://openalex.org/keywords/scaling","display_name":"Scaling","score":0.4686509966850281},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.4379864037036896},{"id":"https://openalex.org/keywords/monte-carlo-tree-search","display_name":"Monte Carlo tree search","score":0.42313000559806824},{"id":"https://openalex.org/keywords/mathematical-optimization","display_name":"Mathematical optimization","score":0.4194006323814392},{"id":"https://openalex.org/keywords/function","display_name":"Function (biology)","score":0.4112965166568756},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.2433285415172577},{"id":"https://openalex.org/keywords/statistics","display_name":"Statistics","score":0.14548653364181519}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6818246245384216},{"id":"https://openalex.org/C181204326","wikidata":"https://www.wikidata.org/wiki/Q7239820","display_name":"Preference learning","level":3,"score":0.6711865067481995},{"id":"https://openalex.org/C19499675","wikidata":"https://www.wikidata.org/wiki/Q232207","display_name":"Monte Carlo method","level":2,"score":0.6638568639755249},{"id":"https://openalex.org/C2777868144","wikidata":"https://www.wikidata.org/wiki/Q7239817","display_name":"Preference elicitation","level":3,"score":0.6092138290405273},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.5642518401145935},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5546947121620178},{"id":"https://openalex.org/C2781249084","wikidata":"https://www.wikidata.org/wiki/Q908656","display_name":"Preference","level":2,"score":0.5507763028144836},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.49458858370780945},{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.4738374650478363},{"id":"https://openalex.org/C99844830","wikidata":"https://www.wikidata.org/wiki/Q102441924","display_name":"Scaling","level":2,"score":0.4686509966850281},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.4379864037036896},{"id":"https://openalex.org/C46149586","wikidata":"https://www.wikidata.org/wiki/Q11785332","display_name":"Monte Carlo tree search","level":3,"score":0.42313000559806824},{"id":"https://openalex.org/C126255220","wikidata":"https://www.wikidata.org/wiki/Q141495","display_name":"Mathematical optimization","level":1,"score":0.4194006323814392},{"id":"https://openalex.org/C14036430","wikidata":"https://www.wikidata.org/wiki/Q3736076","display_name":"Function (biology)","level":2,"score":0.4112965166568756},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.2433285415172577},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.14548653364181519},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","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},{"id":"https://openalex.org/C78458016","wikidata":"https://www.wikidata.org/wiki/Q840400","display_name":"Evolutionary biology","level":1,"score":0.0},{"id":"https://openalex.org/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","level":0,"score":0.0},{"id":"https://openalex.org/C187736073","wikidata":"https://www.wikidata.org/wiki/Q2920921","display_name":"Management","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":1,"locations":[{"id":"doi:10.1109/roman.2012.6343863","is_oa":false,"landing_page_url":"https://doi.org/10.1109/roman.2012.6343863","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2012 IEEE RO-MAN: The 21st IEEE International Symposium on Robot and Human Interactive Communication","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.44999998807907104,"display_name":"Reduced inequalities","id":"https://metadata.un.org/sdg/10"}],"awards":[],"funders":[{"id":"https://openalex.org/F4320306076","display_name":"National Science Foundation","ror":"https://ror.org/021nxhr62"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":24,"referenced_works":["https://openalex.org/W137544591","https://openalex.org/W1487906226","https://openalex.org/W1986808060","https://openalex.org/W1994004584","https://openalex.org/W1999874108","https://openalex.org/W2051203581","https://openalex.org/W2061504687","https://openalex.org/W2061562262","https://openalex.org/W2098774185","https://openalex.org/W2102626845","https://openalex.org/W2114550657","https://openalex.org/W2127470768","https://openalex.org/W2131175218","https://openalex.org/W2134883545","https://openalex.org/W2150818585","https://openalex.org/W2324814459","https://openalex.org/W2327169998","https://openalex.org/W2470364387","https://openalex.org/W2799700442","https://openalex.org/W4237826793","https://openalex.org/W6605518036","https://openalex.org/W6674884181","https://openalex.org/W6679526636","https://openalex.org/W6679973322"],"related_works":["https://openalex.org/W2159111852","https://openalex.org/W271352469","https://openalex.org/W2937325523","https://openalex.org/W64851098","https://openalex.org/W1562775108","https://openalex.org/W2050663403","https://openalex.org/W3136325136","https://openalex.org/W2126528747","https://openalex.org/W4205377104","https://openalex.org/W2073850970"],"abstract_inverted_index":{"AI":[0],"agents":[1],"including":[2],"robots":[3],"often":[4],"use":[5],"reward":[6,26,55,75],"functions":[7,27],"to":[8,17,69,77,124,135,165],"evaluate":[9,88],"tradeoffs":[10],"between":[11,108],"different":[12,54],"states":[13],"and":[14,16,61,87],"actions":[15],"determine":[18],"optimal":[19],"policies.":[20],"We":[21,153],"are":[22,39,133],"particularly":[23],"interested":[24],"in":[25,73,101,175],"that":[28,38,145,155],"can":[29],"be":[30],"decomposed":[31],"into":[32],"an":[33,79],"additive":[34],"sum":[35],"of":[36,46,99,139,162,167,170],"subrewards":[37,52,72],"computed":[40],"on":[41],"independent":[42],"subproblems":[43],"or":[44],"features":[45],"the":[47,71,74,96,103,113,142,168,176],"state":[48],"space.":[49],"If":[50],"these":[51],"capture":[53],"metrics,":[56],"such":[57],"as":[58],"user":[59],"satisfaction":[60],"task":[62],"completion":[63],"time,":[64],"it":[65,120],"is":[66,121],"unclear":[67],"how":[68],"scale":[70],"function":[76],"produce":[78],"appropriate":[80],"policy.":[81],"In":[82],"this":[83],"work,":[84],"we":[85,146],"propose":[86],"a":[89,137,150,160],"novel":[90],"Monte":[91,177],"Carlo":[92,178],"method":[93],"for":[94,159],"learning":[95],"scaling":[97,143,171],"factors":[98,144],"subrewards,":[100],"which":[102],"training":[104],"elicits":[105,115],"humans'":[106],"preferences":[107,116,132,163],"two":[109],"state-action":[110],"scenarios.":[111],"Because":[112],"algorithm":[114,157],"over":[117,141],"explicit":[118],"scenarios,":[119],"less":[122],"susceptible":[123],"human":[125],"error":[126],"than":[127],"previous":[128],"elicitation":[129],"approaches.":[130],"The":[131],"used":[134,174],"generate":[136],"set":[138],"inequalities":[140],"solve":[147],"efficiently":[148],"using":[149],"linear":[151],"program.":[152],"show":[154],"our":[156],"asks":[158],"number":[161,169],"proportional":[164],"log":[166],"factor":[172],"hypotheses":[173],"method.":[179]},"counts_by_year":[{"year":2020,"cited_by_count":1},{"year":2015,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}