{"id":"https://openalex.org/W4376851448","doi":"https://doi.org/10.1109/tg.2023.3276849","title":"Learning to Generalize With Object-Centric Agents in the Open World Survival Game <i>Crafter</i>","display_name":"Learning to Generalize With Object-Centric Agents in the Open World Survival Game <i>Crafter</i>","publication_year":2023,"publication_date":"2023-05-16","ids":{"openalex":"https://openalex.org/W4376851448","doi":"https://doi.org/10.1109/tg.2023.3276849"},"language":"en","primary_location":{"id":"doi:10.1109/tg.2023.3276849","is_oa":false,"landing_page_url":"http://dx.doi.org/10.1109/tg.2023.3276849","pdf_url":null,"source":{"id":"https://openalex.org/S4210224842","display_name":"IEEE Transactions on Games","issn_l":"2475-1502","issn":["2475-1502","2475-1510"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Transactions on Games","raw_type":"journal-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/A5077426397","display_name":"Aleksandar Stani\u0107","orcid":"https://orcid.org/0000-0002-6399-7536"},"institutions":[{"id":"https://openalex.org/I15196421","display_name":"University of Applied Sciences and Arts of Southern Switzerland","ror":"https://ror.org/05ep8g269","country_code":"CH","type":"education","lineage":["https://openalex.org/I15196421"]},{"id":"https://openalex.org/I2614128279","display_name":"Dalle Molle Institute for Artificial Intelligence Research","ror":"https://ror.org/013355g38","country_code":"CH","type":"facility","lineage":["https://openalex.org/I15196421","https://openalex.org/I2614128279","https://openalex.org/I57201433"]}],"countries":["CH"],"is_corresponding":false,"raw_author_name":"Aleksandar Stani\u0107","raw_affiliation_strings":["IDSIA, USI, SUPSI, Lugano, Switzerland"],"raw_orcid":"https://orcid.org/0000-0002-6399-7536","affiliations":[{"raw_affiliation_string":"IDSIA, USI, SUPSI, Lugano, Switzerland","institution_ids":["https://openalex.org/I2614128279","https://openalex.org/I15196421"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5034342631","display_name":"Yujin Tang","orcid":"https://orcid.org/0000-0003-2387-2090"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Yujin Tang","raw_affiliation_strings":["Google Brain, Tokyo, Japan"],"raw_orcid":"https://orcid.org/0000-0003-2387-2090","affiliations":[{"raw_affiliation_string":"Google Brain, Tokyo, Japan","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101406445","display_name":"David Ha","orcid":"https://orcid.org/0000-0002-3598-5036"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"David Ha","raw_affiliation_strings":["Stability AI, Tokyo, Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Stability AI, Tokyo, Japan","institution_ids":[]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5071172037","display_name":"J\u00fcrgen Schmidhuber","orcid":null},"institutions":[{"id":"https://openalex.org/I15196421","display_name":"University of Applied Sciences and Arts of Southern Switzerland","ror":"https://ror.org/05ep8g269","country_code":"CH","type":"education","lineage":["https://openalex.org/I15196421"]},{"id":"https://openalex.org/I2614128279","display_name":"Dalle Molle Institute for Artificial Intelligence Research","ror":"https://ror.org/013355g38","country_code":"CH","type":"facility","lineage":["https://openalex.org/I15196421","https://openalex.org/I2614128279","https://openalex.org/I57201433"]},{"id":"https://openalex.org/I71920554","display_name":"King Abdullah University of Science and Technology","ror":"https://ror.org/01q3tbs38","country_code":"SA","type":"education","lineage":["https://openalex.org/I71920554"]}],"countries":["CH","SA"],"is_corresponding":false,"raw_author_name":"J\u00fcrgen Schmidhuber","raw_affiliation_strings":["IDSIA, USI, SUPSI, Lugano, Switzerland","AI Initiative, KAUST, Thuwal, Saudi Arabia"],"raw_orcid":"https://orcid.org/0000-0002-1468-6758","affiliations":[{"raw_affiliation_string":"IDSIA, USI, SUPSI, Lugano, Switzerland","institution_ids":["https://openalex.org/I2614128279","https://openalex.org/I15196421"]},{"raw_affiliation_string":"AI Initiative, KAUST, Thuwal, Saudi Arabia","institution_ids":["https://openalex.org/I71920554"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":4,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.3263,"has_fulltext":false,"cited_by_count":2,"citation_normalized_percentile":{"value":0.63116223,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":95,"max":96},"biblio":{"volume":"16","issue":"2","first_page":"384","last_page":"395"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10462","display_name":"Reinforcement Learning in Robotics","score":0.9987000226974487,"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":0.9987000226974487,"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":0.9897000193595886,"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":0.9804999828338623,"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/benchmark","display_name":"Benchmark (surveying)","score":0.7166634202003479},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7107473015785217},{"id":"https://openalex.org/keywords/generalization","display_name":"Generalization","score":0.7097424268722534},{"id":"https://openalex.org/keywords/reinforcement-learning","display_name":"Reinforcement learning","score":0.6552750468254089},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.6367015242576599},{"id":"https://openalex.org/keywords/set","display_name":"Set (abstract data type)","score":0.6352343559265137},{"id":"https://openalex.org/keywords/object","display_name":"Object (grammar)","score":0.6172236204147339},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.46282440423965454},{"id":"https://openalex.org/keywords/margin","display_name":"Margin (machine learning)","score":0.43840643763542175},{"id":"https://openalex.org/keywords/programming-language","display_name":"Programming language","score":0.14045143127441406},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.10858291387557983}],"concepts":[{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.7166634202003479},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7107473015785217},{"id":"https://openalex.org/C177148314","wikidata":"https://www.wikidata.org/wiki/Q170084","display_name":"Generalization","level":2,"score":0.7097424268722534},{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.6552750468254089},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6367015242576599},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.6352343559265137},{"id":"https://openalex.org/C2781238097","wikidata":"https://www.wikidata.org/wiki/Q175026","display_name":"Object (grammar)","level":2,"score":0.6172236204147339},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.46282440423965454},{"id":"https://openalex.org/C774472","wikidata":"https://www.wikidata.org/wiki/Q6760393","display_name":"Margin (machine learning)","level":2,"score":0.43840643763542175},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.14045143127441406},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.10858291387557983},{"id":"https://openalex.org/C134306372","wikidata":"https://www.wikidata.org/wiki/Q7754","display_name":"Mathematical analysis","level":1,"score":0.0},{"id":"https://openalex.org/C205649164","wikidata":"https://www.wikidata.org/wiki/Q1071","display_name":"Geography","level":0,"score":0.0},{"id":"https://openalex.org/C13280743","wikidata":"https://www.wikidata.org/wiki/Q131089","display_name":"Geodesy","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/tg.2023.3276849","is_oa":false,"landing_page_url":"http://dx.doi.org/10.1109/tg.2023.3276849","pdf_url":null,"source":{"id":"https://openalex.org/S4210224842","display_name":"IEEE Transactions on Games","issn_l":"2475-1502","issn":["2475-1502","2475-1510"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Transactions on Games","raw_type":"journal-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":116,"referenced_works":["https://openalex.org/W185620388","https://openalex.org/W1191599655","https://openalex.org/W1526844937","https://openalex.org/W1662842982","https://openalex.org/W1863227302","https://openalex.org/W1891300059","https://openalex.org/W2038794597","https://openalex.org/W2064675550","https://openalex.org/W2089217417","https://openalex.org/W2108598243","https://openalex.org/W2116386744","https://openalex.org/W2122053572","https://openalex.org/W2145339207","https://openalex.org/W2148837383","https://openalex.org/W2150468603","https://openalex.org/W2274801302","https://openalex.org/W2547416798","https://openalex.org/W2727840223","https://openalex.org/W2736601468","https://openalex.org/W2749807327","https://openalex.org/W2754517384","https://openalex.org/W2761873684","https://openalex.org/W2781585732","https://openalex.org/W2786615588","https://openalex.org/W2889987506","https://openalex.org/W2896457183","https://openalex.org/W2905342215","https://openalex.org/W2941355526","https://openalex.org/W2962991582","https://openalex.org/W2963403143","https://openalex.org/W2963473082","https://openalex.org/W2963871073","https://openalex.org/W2964846271","https://openalex.org/W2979308149","https://openalex.org/W3012502279","https://openalex.org/W3037784242","https://openalex.org/W3092744199","https://openalex.org/W3096609285","https://openalex.org/W3101438731","https://openalex.org/W3122690883","https://openalex.org/W3127433878","https://openalex.org/W3166796161","https://openalex.org/W3174979085","https://openalex.org/W3190965961","https://openalex.org/W3205321526","https://openalex.org/W3212249145","https://openalex.org/W4221139679","https://openalex.org/W4225323055","https://openalex.org/W4225550826","https://openalex.org/W4226067525","https://openalex.org/W4226246634","https://openalex.org/W4283460722","https://openalex.org/W4286976660","https://openalex.org/W4287280733","https://openalex.org/W4287554891","https://openalex.org/W4287586139","https://openalex.org/W4289292284","https://openalex.org/W4295246696","https://openalex.org/W4295720520","https://openalex.org/W4306706417","https://openalex.org/W4315487473","https://openalex.org/W4385245566","https://openalex.org/W6627932998","https://openalex.org/W6639612657","https://openalex.org/W6694537288","https://openalex.org/W6702162793","https://openalex.org/W6718986230","https://openalex.org/W6721634521","https://openalex.org/W6728881815","https://openalex.org/W6741002519","https://openalex.org/W6742720488","https://openalex.org/W6743756900","https://openalex.org/W6747387971","https://openalex.org/W6752279500","https://openalex.org/W6752675014","https://openalex.org/W6753526802","https://openalex.org/W6755207826","https://openalex.org/W6755477022","https://openalex.org/W6756555864","https://openalex.org/W6757797181","https://openalex.org/W6757988111","https://openalex.org/W6758420182","https://openalex.org/W6759669191","https://openalex.org/W6761839350","https://openalex.org/W6762284573","https://openalex.org/W6763704883","https://openalex.org/W6766312635","https://openalex.org/W6766900654","https://openalex.org/W6768501859","https://openalex.org/W6769570503","https://openalex.org/W6770507128","https://openalex.org/W6771750343","https://openalex.org/W6774279402","https://openalex.org/W6779809370","https://openalex.org/W6780225908","https://openalex.org/W6780226713","https://openalex.org/W6780559895","https://openalex.org/W6783890883","https://openalex.org/W6783988234","https://openalex.org/W6786745199","https://openalex.org/W6787728148","https://openalex.org/W6790830454","https://openalex.org/W6792018038","https://openalex.org/W6795386847","https://openalex.org/W6796366729","https://openalex.org/W6799838802","https://openalex.org/W6800764332","https://openalex.org/W6801642480","https://openalex.org/W6804342959","https://openalex.org/W6804601995","https://openalex.org/W6810065975","https://openalex.org/W6810334672","https://openalex.org/W6811329337","https://openalex.org/W6811405349","https://openalex.org/W6840133048","https://openalex.org/W6845979276"],"related_works":["https://openalex.org/W2378211422","https://openalex.org/W4321353415","https://openalex.org/W2745001401","https://openalex.org/W2130974462","https://openalex.org/W2028665553","https://openalex.org/W2086519370","https://openalex.org/W4246352526","https://openalex.org/W2121910908","https://openalex.org/W915438175","https://openalex.org/W4230315250"],"abstract_inverted_index":{"Reinforcement":[0],"learning":[1],"agents":[2,66,89,97,140,175,187,222,230],"must":[3],"generalize":[4,49],"beyond":[5,169],"their":[6],"training":[7,16],"experience.":[8],"Prior":[9],"work":[10,113],"has":[11],"focused":[12],"mostly":[13],"on":[14,50,114,148,158],"identical":[15],"and":[17,56,93,136],"evaluation":[18],"environments.":[19],"Starting":[20],"from":[21],"the":[22,65,70,128,149,159,184,194,220],"recently":[23],"introduced":[24],"<italic":[25,62,115,161,200,214],"xmlns:mml=\"http://www.w3.org/1998/Math/MathML\"":[26,63,116,162,201,215],"xmlns:xlink=\"http://www.w3.org/1999/xlink\">Crafter</i>":[27,117,163],"benchmark,":[28],"a":[29,37,133,154,203],"2-D":[30],"open":[31],"world":[32],"survival":[33],"game,":[34],"we":[35,217],"introduce":[36,94,199],"new":[38,155,207],"set":[39,204],"of":[40,72,108,205],"environments":[41,208],"suitable":[42],"for":[43,81,111],"evaluating":[44],"some":[45],"agent's":[46],"ability":[47],"to":[48,57,91,224],"previously":[51],"unseen":[52],"(numbers":[53],"of)":[54],"objects":[55],"adapt":[58],"quickly":[59],"(meta-learning).":[60],"In":[61,165],"xmlns:xlink=\"http://www.w3.org/1999/xlink\">Crafter</i>,":[64],"are":[67],"evaluated":[68],"by":[69,132,146],"number":[71],"unlocked":[73],"achievements":[74,145],"(such":[75],"as":[76],"collecting":[77],"resources)":[78],"when":[79,167],"trained":[80,168],"1":[82,170],"M":[83,171],"steps.":[84],"We":[85,103,121,152,181,198],"show":[86,122,182,218],"that":[87,98,123,137,183,209,219],"current":[88,221],"struggle":[90],"generalize,":[92,225],"novel":[95,228],"object-centric":[96,229],"improve":[99,188],"over":[100,189],"strong":[101],"baselines.":[102],"also":[104,236],"provide":[105],"critical":[106],"insights":[107],"general":[109],"interest":[110],"future":[112],"through":[118],"several":[119],"experiments.":[120],"careful":[124],"hyperparameter":[125],"tuning":[126],"improves":[127],"PPO":[129,186],"baseline":[130],"agent":[131],"large":[134],"margin":[135],"even":[138,192],"feedforward":[139,190],"can":[141,176],"unlock":[142,177],"almost":[143,178],"all":[144,179],"relying":[147],"inventory":[150,195],"display.":[151],"achieve":[153,231],"state-of-the-art":[156,232],"performance":[157],"original":[160],"environment.":[164],"addtion,":[166],"steps,":[172],"our":[173,227],"tuned":[174],"achievements.":[180],"recurrent":[185],"ones,":[191],"with":[193],"information":[196],"removed.":[197],"xmlns:xlink=\"http://www.w3.org/1999/xlink\">Crafter</i>OOD,":[202,216],"15":[206],"evaluate":[210],"OOD":[211,233],"generalization.":[212],"On":[213],"fail":[223],"whereas":[226],"generalization":[234],"while":[235],"being":[237],"interpretable.":[238],"Our":[239],"code":[240],"is":[241],"public.":[242]},"counts_by_year":[{"year":2025,"cited_by_count":2}],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2025-10-10T00:00:00"}