{"id":"https://openalex.org/W2574909358","doi":null,"title":"Fear and hope emerge from anticipation in model-based reinforcement learning","display_name":"Fear and hope emerge from anticipation in model-based reinforcement learning","publication_year":2016,"publication_date":"2016-07-09","ids":{"openalex":"https://openalex.org/W2574909358","mag":"2574909358"},"language":"en","primary_location":{"id":"mag:2574909358","doi":null,"is_oa":false,"landing_page_url":"http://dblp.uni-trier.de/db/conf/ijcai/ijcai2016.html#MoerlandBJ16","pdf_url":null,"source":{"id":"https://openalex.org/S4306419999","display_name":"International Joint Conference on Artificial Intelligence","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":null,"license_id":null,"version":null,"is_accepted":false,"is_published":false,"raw_source_name":"International Joint Conference on Artificial Intelligence","raw_type":null},"volume":null,"type":"conference-paper","is_traditional":true,"indexed_in":[],"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/A5003595753","display_name":"Thomas M. Moerland","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I98358874","display_name":"Delft University of Technology","ror":"https://ror.org/02e2c7k09","country_code":"NL","type":"education","lineage":["https://openalex.org/I98358874"]}],"countries":["NL"],"is_corresponding":false,"raw_author_name":"Thomas M. Moerland","raw_affiliation_strings":["Delft University of Technology, CD Delft, the Netherlands"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Delft University of Technology, CD Delft, the Netherlands","institution_ids":["https://openalex.org/I98358874"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5027253360","display_name":"Joost Broekens","orcid":"https://orcid.org/0000-0001-9198-898X","observed_orcids":["https://orcid.org/0000-0001-9198-898X"]},"institutions":[{"id":"https://openalex.org/I98358874","display_name":"Delft University of Technology","ror":"https://ror.org/02e2c7k09","country_code":"NL","type":"education","lineage":["https://openalex.org/I98358874"]}],"countries":["NL"],"is_corresponding":false,"raw_author_name":"Joost Broekens","raw_affiliation_strings":["Delft University of Technology, CD Delft, the Netherlands"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Delft University of Technology, CD Delft, the Netherlands","institution_ids":["https://openalex.org/I98358874"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5074074791","display_name":"Catholijn M. Jonker","orcid":"https://orcid.org/0000-0003-4780-7461","observed_orcids":["https://orcid.org/0000-0003-4780-7461"]},"institutions":[{"id":"https://openalex.org/I98358874","display_name":"Delft University of Technology","ror":"https://ror.org/02e2c7k09","country_code":"NL","type":"education","lineage":["https://openalex.org/I98358874"]}],"countries":["NL"],"is_corresponding":false,"raw_author_name":"Catholijn M. Jonker","raw_affiliation_strings":["Delft University of Technology, CD Delft, the Netherlands"],"raw_orcid":"https://orcid.org/0000-0003-4780-7461","affiliations":[{"raw_affiliation_string":"Delft University of Technology, CD Delft, the Netherlands","institution_ids":["https://openalex.org/I98358874"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I98358874"],"apc_list":null,"apc_paid":null,"fwci":0.9724,"has_fulltext":false,"cited_by_count":15,"citation_normalized_percentile":{"value":0.78389564,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":88,"max":98},"biblio":{"volume":null,"issue":null,"first_page":"848","last_page":"854"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10462","display_name":"Reinforcement Learning in Robotics","score":0.8140000104904175,"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":0.8140000104904175,"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/T14381","display_name":"Psychiatry, Mental Health, Neuroscience","score":0.17739999294281006,"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/T11574","display_name":"Artificial Intelligence in Games","score":0.002099999925121665,"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/emotion-generation","display_name":"emotion generation","score":0.6790000200271606},{"id":"https://openalex.org/keywords/hope","display_name":"hope","score":0.7799999713897705},{"id":"https://openalex.org/keywords/fear","display_name":"fear","score":1.0},{"id":"https://openalex.org/keywords/anticipation","display_name":"anticipation","score":0.9139999747276306},{"id":"https://openalex.org/keywords/model-based-reinforcement-learning","display_name":"model-based reinforcement learning","score":0.9800000190734863},{"id":"https://openalex.org/keywords/forward-modeling","display_name":"forward modeling","score":0.6430000066757202},{"id":"https://openalex.org/keywords/monte-carlo-tree-search","display_name":"Monte Carlo tree search","score":0.8119999766349792},{"id":"https://openalex.org/keywords/uct","display_name":"UCT","score":0.890999972820282},{"id":"https://openalex.org/keywords/sequential-decision-making","display_name":"sequential decision making","score":0.8769999742507935},{"id":"https://openalex.org/keywords/pac-man","display_name":"Pac-Man","score":0.4129999876022339},{"id":"https://openalex.org/keywords/social-actors","display_name":"social actors","score":0.4429999887943268},{"id":"https://openalex.org/keywords/robots","display_name":"robots","score":0.42399999499320984}],"concepts":[{"id":"https://openalex.org/C176777502","wikidata":"https://www.wikidata.org/wiki/Q4774623","display_name":"Anticipation (artificial intelligence)","level":2,"score":0.8902662992477417},{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.8132491111755371},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6907471418380737},{"id":"https://openalex.org/C2779662365","wikidata":"https://www.wikidata.org/wiki/Q5416694","display_name":"Event (particle physics)","level":2,"score":0.5378311276435852},{"id":"https://openalex.org/C9652623","wikidata":"https://www.wikidata.org/wiki/Q190109","display_name":"Field (mathematics)","level":2,"score":0.5340824127197266},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5137470960617065},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.3590322732925415},{"id":"https://openalex.org/C202444582","wikidata":"https://www.wikidata.org/wiki/Q837863","display_name":"Pure mathematics","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},{"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/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"mag:2574909358","doi":null,"is_oa":false,"landing_page_url":"http://dblp.uni-trier.de/db/conf/ijcai/ijcai2016.html#MoerlandBJ16","pdf_url":null,"source":{"id":"https://openalex.org/S4306419999","display_name":"International Joint Conference on Artificial Intelligence","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":null,"license_id":null,"version":null,"is_accepted":false,"is_published":false,"raw_source_name":"International Joint Conference on Artificial Intelligence","raw_type":null}],"best_oa_location":null,"sustainable_development_goals":[],"study_designs":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":25,"referenced_works":["https://openalex.org/W1488730473","https://openalex.org/W1515308897","https://openalex.org/W1515851193","https://openalex.org/W1625390266","https://openalex.org/W1758031947","https://openalex.org/W1867691547","https://openalex.org/W1977655452","https://openalex.org/W1980035368","https://openalex.org/W1997543377","https://openalex.org/W2009967740","https://openalex.org/W2012234732","https://openalex.org/W2015514626","https://openalex.org/W2029250100","https://openalex.org/W2046774605","https://openalex.org/W2048226872","https://openalex.org/W2068613599","https://openalex.org/W2072376581","https://openalex.org/W2097778153","https://openalex.org/W2104365695","https://openalex.org/W2109420588","https://openalex.org/W2120618638","https://openalex.org/W2121110499","https://openalex.org/W2121863487","https://openalex.org/W2124674171","https://openalex.org/W2156361796"],"related_works":["https://openalex.org/W2012234732","https://openalex.org/W2610195735","https://openalex.org/W4205236653","https://openalex.org/W2169366102","https://openalex.org/W2398779761","https://openalex.org/W2907082874","https://openalex.org/W2614309179","https://openalex.org/W193768099","https://openalex.org/W2143435361","https://openalex.org/W2103281454"],"abstract_inverted_index":{"Social":[0],"agents":[1,130],"and":[2,8,47,55,74,79,117,120,135,139],"robots":[3],"will":[4],"require":[5],"both":[6,18],"learning":[7,40],"emotional":[9],"capabilities":[10],"to":[11,131],"successfully":[12],"enter":[13],"society.":[14],"This":[15],"paper":[16],"connects":[17],"challenges,":[19],"by":[20],"studying":[21],"models":[22,71,128],"of":[23,65,72],"emotion":[24,112],"generation":[25],"in":[26,32,106,122],"sequential":[27],"decision-making":[28],"agents.":[29],"Previous":[30],"work":[31,69],"this":[33],"field":[34],"has":[35],"focussed":[36],"on":[37,77,115],"model-free":[38],"reinforcement":[39],"(RL).":[41],"However,":[42],"important":[43],"emotions":[44],"like":[45],"hope":[46,73,134],"fear":[48,75,136],"need":[49],"anticipation,":[50],"which":[51],"requires":[52],"a":[53,90,99],"model":[54,100],"forward":[56,81],"simulation.":[57],"Taking":[58],"inspiration":[59],"from":[60],"the":[61],"psychological":[62],"Belief-Desire":[63],"Theory":[64],"Emotions":[66],"(BDTE),":[67],"our":[68],"specifies":[70],"based":[76,101],"best":[78],"worst":[80],"traces.":[82],"To":[83],"efficiently":[84],"estimate":[85],"these":[86],"traces,":[87],"we":[88],"integrate":[89],"well-known":[91],"Monte":[92],"Carlo":[93],"Tree":[94],"Search":[95],"procedure":[96],"(UCT)":[97],"into":[98],"RL":[102,109],"architecture.":[103],"Test":[104],"results":[105],"three":[107],"known":[108],"domains":[110],"illustrate":[111],"dynamics,":[113],"dependencies":[114],"policy":[116],"environmental":[118],"stochasticity,":[119],"plausibility":[121],"individual":[123],"Pacman":[124],"game":[125],"settings.":[126],"Our":[127],"enable":[129],"naturally":[132],"elicit":[133],"during":[137],"learning,":[138],"moreover,":[140],"explain":[141],"what":[142],"anticipated":[143],"event":[144],"caused":[145],"this.":[146]},"counts_by_year":[{"year":2023,"cited_by_count":1},{"year":2022,"cited_by_count":4},{"year":2021,"cited_by_count":2},{"year":2020,"cited_by_count":2},{"year":2019,"cited_by_count":2},{"year":2017,"cited_by_count":4}],"updated_date":"2026-11-03T10:50:19.383937","created_date":"2017-01-26T00:00:00"}