{"id":"https://openalex.org/W4296426154","doi":"https://doi.org/10.1109/cog51982.2022.9893625","title":"Agent X: Improving Exploration vs Exploitation in the State of the Art Angry Birds AI","display_name":"Agent X: Improving Exploration vs Exploitation in the State of the Art Angry Birds AI","publication_year":2022,"publication_date":"2022-08-21","ids":{"openalex":"https://openalex.org/W4296426154","doi":"https://doi.org/10.1109/cog51982.2022.9893625"},"language":"en","primary_location":{"id":"doi:10.1109/cog51982.2022.9893625","is_oa":false,"landing_page_url":"https://doi.org/10.1109/cog51982.2022.9893625","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2022 IEEE Conference on Games (CoG)","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/A5016777087","display_name":"Daniel Lutalo","orcid":null},"institutions":[{"id":"https://openalex.org/I118347636","display_name":"Australian National University","ror":"https://ror.org/019wvm592","country_code":"AU","type":"education","lineage":["https://openalex.org/I118347636"]}],"countries":["AU"],"is_corresponding":true,"raw_author_name":"Daniel Lutalo","raw_affiliation_strings":["School of Computing Australian National University,Canberra,Australia","School of Computing Australian National University, Canberra, Australia"],"affiliations":[{"raw_affiliation_string":"School of Computing Australian National University,Canberra,Australia","institution_ids":["https://openalex.org/I118347636"]},{"raw_affiliation_string":"School of Computing Australian National University, Canberra, Australia","institution_ids":["https://openalex.org/I118347636"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":["https://openalex.org/A5016777087"],"corresponding_institution_ids":["https://openalex.org/I118347636"],"apc_list":null,"apc_paid":null,"fwci":0.3977,"has_fulltext":false,"cited_by_count":3,"citation_normalized_percentile":{"value":0.66931459,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":96},"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/T11574","display_name":"Artificial Intelligence in Games","score":0.9995999932289124,"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/T11574","display_name":"Artificial Intelligence in Games","score":0.9995999932289124,"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":0.9983000159263611,"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/T11714","display_name":"Multimodal Machine Learning Applications","score":0.9926000237464905,"subfield":{"id":"https://openalex.org/subfields/1707","display_name":"Computer Vision and Pattern Recognition"},"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/reinforcement-learning","display_name":"Reinforcement learning","score":0.8165775537490845},{"id":"https://openalex.org/keywords/competition","display_name":"Competition (biology)","score":0.678937554359436},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.618270993232727},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.6146971583366394},{"id":"https://openalex.org/keywords/domain","display_name":"Domain (mathematical analysis)","score":0.5710988640785217},{"id":"https://openalex.org/keywords/state","display_name":"State (computer science)","score":0.5192839503288269},{"id":"https://openalex.org/keywords/simple","display_name":"Simple (philosophy)","score":0.4790536165237427},{"id":"https://openalex.org/keywords/balance","display_name":"Balance (ability)","score":0.4433935284614563},{"id":"https://openalex.org/keywords/order","display_name":"Order (exchange)","score":0.4407412111759186},{"id":"https://openalex.org/keywords/cover","display_name":"Cover (algebra)","score":0.4201827049255371},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.16989877820014954},{"id":"https://openalex.org/keywords/psychology","display_name":"Psychology","score":0.15289300680160522},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.11916723847389221},{"id":"https://openalex.org/keywords/ecology","display_name":"Ecology","score":0.10279560089111328},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.08864849805831909},{"id":"https://openalex.org/keywords/business","display_name":"Business","score":0.08395686745643616},{"id":"https://openalex.org/keywords/epistemology","display_name":"Epistemology","score":0.0763232409954071}],"concepts":[{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.8165775537490845},{"id":"https://openalex.org/C91306197","wikidata":"https://www.wikidata.org/wiki/Q45767","display_name":"Competition (biology)","level":2,"score":0.678937554359436},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.618270993232727},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6146971583366394},{"id":"https://openalex.org/C36503486","wikidata":"https://www.wikidata.org/wiki/Q11235244","display_name":"Domain (mathematical analysis)","level":2,"score":0.5710988640785217},{"id":"https://openalex.org/C48103436","wikidata":"https://www.wikidata.org/wiki/Q599031","display_name":"State (computer science)","level":2,"score":0.5192839503288269},{"id":"https://openalex.org/C2780586882","wikidata":"https://www.wikidata.org/wiki/Q7520643","display_name":"Simple (philosophy)","level":2,"score":0.4790536165237427},{"id":"https://openalex.org/C168031717","wikidata":"https://www.wikidata.org/wiki/Q1530280","display_name":"Balance (ability)","level":2,"score":0.4433935284614563},{"id":"https://openalex.org/C182306322","wikidata":"https://www.wikidata.org/wiki/Q1779371","display_name":"Order (exchange)","level":2,"score":0.4407412111759186},{"id":"https://openalex.org/C2780428219","wikidata":"https://www.wikidata.org/wiki/Q16952335","display_name":"Cover (algebra)","level":2,"score":0.4201827049255371},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.16989877820014954},{"id":"https://openalex.org/C15744967","wikidata":"https://www.wikidata.org/wiki/Q9418","display_name":"Psychology","level":0,"score":0.15289300680160522},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.11916723847389221},{"id":"https://openalex.org/C18903297","wikidata":"https://www.wikidata.org/wiki/Q7150","display_name":"Ecology","level":1,"score":0.10279560089111328},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.08864849805831909},{"id":"https://openalex.org/C144133560","wikidata":"https://www.wikidata.org/wiki/Q4830453","display_name":"Business","level":0,"score":0.08395686745643616},{"id":"https://openalex.org/C111472728","wikidata":"https://www.wikidata.org/wiki/Q9471","display_name":"Epistemology","level":1,"score":0.0763232409954071},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.0},{"id":"https://openalex.org/C169760540","wikidata":"https://www.wikidata.org/wiki/Q207011","display_name":"Neuroscience","level":1,"score":0.0},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0},{"id":"https://openalex.org/C78519656","wikidata":"https://www.wikidata.org/wiki/Q101333","display_name":"Mechanical engineering","level":1,"score":0.0},{"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/C10138342","wikidata":"https://www.wikidata.org/wiki/Q43015","display_name":"Finance","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/cog51982.2022.9893625","is_oa":false,"landing_page_url":"https://doi.org/10.1109/cog51982.2022.9893625","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2022 IEEE Conference on Games (CoG)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Peace, Justice and strong institutions","id":"https://metadata.un.org/sdg/16","score":0.6299999952316284}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":20,"referenced_works":["https://openalex.org/W41554520","https://openalex.org/W1760746696","https://openalex.org/W1911071008","https://openalex.org/W2039522160","https://openalex.org/W2121042348","https://openalex.org/W2340540929","https://openalex.org/W2345221957","https://openalex.org/W2345756318","https://openalex.org/W2346002144","https://openalex.org/W2404041238","https://openalex.org/W2434242310","https://openalex.org/W2529170537","https://openalex.org/W2766447205","https://openalex.org/W2885623676","https://openalex.org/W2957360994","https://openalex.org/W2964633903","https://openalex.org/W2977020849","https://openalex.org/W2997768066","https://openalex.org/W6713217526","https://openalex.org/W6749125173"],"related_works":["https://openalex.org/W4306904969","https://openalex.org/W4232403550","https://openalex.org/W623607250","https://openalex.org/W2138720691","https://openalex.org/W4362501864","https://openalex.org/W4380318855","https://openalex.org/W2031695474","https://openalex.org/W4245429118","https://openalex.org/W4205110281","https://openalex.org/W4212927854"],"abstract_inverted_index":{"AI":[0,51],"agents":[1],"have":[2],"successfully":[3],"employed":[4],"deep":[5],"reinforcement":[6],"learning":[7],"methods":[8],"to":[9,39],"surpass":[10],"human":[11],"performance":[12],"in":[13],"various":[14],"new":[15,63,105],"tasks":[16],"over":[17],"the":[18,23,54,76,84,95,99,104,116,127],"past":[19],"decade,":[20],"notably":[21],"including":[22],"domain":[24],"of":[25,87,98,129,137],"games.":[26],"However,":[27],"Angry":[28,49,143],"Birds":[29,50,144],"requires":[30],"complex":[31],"physical":[32],"and":[33,59,80,103,106],"spacial":[34],"reasoning":[35],"that":[36,112],"is":[37],"yet":[38],"be":[40],"captured":[41],"by":[42,125],"such":[43],"means.":[44],"We":[45,82,110,132],"present":[46],"our":[47,88,113],"logic-based":[48],"which":[52,72],"won":[53],"2021":[55],"IJCAI":[56],"AIBIRDS":[57],"competition":[58,85],"propose":[60],"a":[61,123,140],"simple":[62],"method":[64],"we":[65],"call":[66],"Second":[67],"Order":[68],"Thompson":[69],"Sampling":[70],"(SOTS)":[71],"allows":[73],"for":[74,139],"fine-tuning":[75],"balance":[77],"between":[78],"exploration":[79],"exploitation.":[81],"cover":[83],"scores":[86],"entrant":[89],"Agent":[90],"X,":[91],"its":[92],"predecessor":[93],"-":[94],"former":[96],"state":[97],"art":[100],"Bambirds":[101,108,130],"2019,":[102],"improved":[107],"2021.":[109,131],"find":[111],"agent":[114],"has":[115],"best":[117],"all-round":[118],"performance,":[119],"but":[120],"would":[121],"gain":[122],"lot":[124],"incorporating":[126],"improvements":[128],"list":[133],"other":[134],"potential":[135],"areas":[136],"improvement":[138],"future":[141],"superhuman":[142],"AI.":[145]},"counts_by_year":[{"year":2024,"cited_by_count":1},{"year":2023,"cited_by_count":2}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}