{"id":"https://openalex.org/W3116263860","doi":"https://doi.org/10.1109/tg.2021.3067723","title":"Learning to Play Imperfect-Information Games by Imitating an Oracle Planner","display_name":"Learning to Play Imperfect-Information Games by Imitating an Oracle Planner","publication_year":2021,"publication_date":"2021-03-22","ids":{"openalex":"https://openalex.org/W3116263860","doi":"https://doi.org/10.1109/tg.2021.3067723","mag":"3116263860"},"language":"en","primary_location":{"id":"doi:10.1109/tg.2021.3067723","is_oa":true,"landing_page_url":"https://doi.org/10.1109/tg.2021.3067723","pdf_url":"https://ieeexplore.ieee.org/ielx7/7782673/9797039/09382923.pdf","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":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Transactions on Games","raw_type":"journal-article"},"type":"preprint","indexed_in":["arxiv","crossref","datacite"],"open_access":{"is_oa":true,"oa_status":"hybrid","oa_url":"https://ieeexplore.ieee.org/ielx7/7782673/9797039/09382923.pdf","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5065850081","display_name":"Rinu Boney","orcid":"https://orcid.org/0000-0002-6968-7109"},"institutions":[{"id":"https://openalex.org/I9927081","display_name":"Aalto University","ror":"https://ror.org/020hwjq30","country_code":"FI","type":"education","lineage":["https://openalex.org/I9927081"]}],"countries":["FI"],"is_corresponding":true,"raw_author_name":"Rinu Boney","raw_affiliation_strings":["Department of Computer Science, Aalto University, Espoo, Finland","[Department of Computer Science, Aalto University, 174277 Aalto, Finland, (e-mail: rinu.boney@aalto.fi)]"],"affiliations":[{"raw_affiliation_string":"Department of Computer Science, Aalto University, Espoo, Finland","institution_ids":["https://openalex.org/I9927081"]},{"raw_affiliation_string":"[Department of Computer Science, Aalto University, 174277 Aalto, Finland, (e-mail: rinu.boney@aalto.fi)]","institution_ids":["https://openalex.org/I9927081"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5103933556","display_name":"Alexander Ilin","orcid":"https://orcid.org/0000-0001-6419-3006"},"institutions":[{"id":"https://openalex.org/I9927081","display_name":"Aalto University","ror":"https://ror.org/020hwjq30","country_code":"FI","type":"education","lineage":["https://openalex.org/I9927081"]}],"countries":["FI"],"is_corresponding":false,"raw_author_name":"Alexander Ilin","raw_affiliation_strings":["Department of Computer Science, Aalto University, Espoo, Finland","[Department of Computer Science, Aalto University, 174277 Aalto, Finland, (e-mail: alexander.ilin@aalto.fi)]"],"affiliations":[{"raw_affiliation_string":"Department of Computer Science, Aalto University, Espoo, Finland","institution_ids":["https://openalex.org/I9927081"]},{"raw_affiliation_string":"[Department of Computer Science, Aalto University, 174277 Aalto, Finland, (e-mail: alexander.ilin@aalto.fi)]","institution_ids":["https://openalex.org/I9927081"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5057931031","display_name":"Juho Kannala","orcid":"https://orcid.org/0000-0001-5088-4041"},"institutions":[{"id":"https://openalex.org/I9927081","display_name":"Aalto University","ror":"https://ror.org/020hwjq30","country_code":"FI","type":"education","lineage":["https://openalex.org/I9927081"]}],"countries":["FI"],"is_corresponding":false,"raw_author_name":"Juho Kannala","raw_affiliation_strings":["Department of Computer Science, Aalto University, Espoo, Finland","[Department of Computer Science, Aalto University, 174277 Aalto, Finland, (e-mail: juho.kannala@aalto.fi)]"],"affiliations":[{"raw_affiliation_string":"Department of Computer Science, Aalto University, Espoo, Finland","institution_ids":["https://openalex.org/I9927081"]},{"raw_affiliation_string":"[Department of Computer Science, Aalto University, 174277 Aalto, Finland, (e-mail: juho.kannala@aalto.fi)]","institution_ids":["https://openalex.org/I9927081"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5111903210","display_name":"Jarno Sepp\u00e4nen","orcid":null},"institutions":[{"id":"https://openalex.org/I1323065761","display_name":"Statistics Finland","ror":"https://ror.org/01n1rg855","country_code":"FI","type":"other","lineage":["https://openalex.org/I1323065761"]}],"countries":["FI"],"is_corresponding":false,"raw_author_name":"Jarno Seppanen","raw_affiliation_strings":["Supercell, Helsinki, Finland","[Supercell, Helsinki, Finland, (e-mail: jarno.seppanen@supercell.com)]"],"affiliations":[{"raw_affiliation_string":"Supercell, Helsinki, Finland","institution_ids":[]},{"raw_affiliation_string":"[Supercell, Helsinki, Finland, (e-mail: jarno.seppanen@supercell.com)]","institution_ids":["https://openalex.org/I1323065761"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5065850081"],"corresponding_institution_ids":["https://openalex.org/I9927081"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":true,"cited_by_count":0,"citation_normalized_percentile":{"value":0.01187201,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":"14","issue":"2","first_page":"262","last_page":"272"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11574","display_name":"Artificial Intelligence in Games","score":0.9986000061035156,"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":0.9986000061035156,"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":0.9904999732971191,"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":0.9442999958992004,"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/oracle","display_name":"Oracle","score":0.8376322984695435},{"id":"https://openalex.org/keywords/planner","display_name":"Planner","score":0.7827579975128174},{"id":"https://openalex.org/keywords/monte-carlo-tree-search","display_name":"Monte Carlo tree search","score":0.7797181606292725},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7472730278968811},{"id":"https://openalex.org/keywords/perfect-information","display_name":"Perfect information","score":0.6848254203796387},{"id":"https://openalex.org/keywords/observability","display_name":"Observability","score":0.6539308428764343},{"id":"https://openalex.org/keywords/action","display_name":"Action (physics)","score":0.6008872985839844},{"id":"https://openalex.org/keywords/imperfect","display_name":"Imperfect","score":0.5455659031867981},{"id":"https://openalex.org/keywords/tree","display_name":"Tree (set theory)","score":0.545509397983551},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4732024371623993},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.3720657229423523},{"id":"https://openalex.org/keywords/operations-research","display_name":"Operations research","score":0.3236236572265625},{"id":"https://openalex.org/keywords/mathematical-economics","display_name":"Mathematical economics","score":0.2018132209777832},{"id":"https://openalex.org/keywords/monte-carlo-method","display_name":"Monte Carlo method","score":0.13825666904449463},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.10817888379096985}],"concepts":[{"id":"https://openalex.org/C55166926","wikidata":"https://www.wikidata.org/wiki/Q2892946","display_name":"Oracle","level":2,"score":0.8376322984695435},{"id":"https://openalex.org/C2776999362","wikidata":"https://www.wikidata.org/wiki/Q2349274","display_name":"Planner","level":2,"score":0.7827579975128174},{"id":"https://openalex.org/C46149586","wikidata":"https://www.wikidata.org/wiki/Q11785332","display_name":"Monte Carlo tree search","level":3,"score":0.7797181606292725},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7472730278968811},{"id":"https://openalex.org/C123676819","wikidata":"https://www.wikidata.org/wiki/Q1074338","display_name":"Perfect information","level":2,"score":0.6848254203796387},{"id":"https://openalex.org/C36299963","wikidata":"https://www.wikidata.org/wiki/Q1369844","display_name":"Observability","level":2,"score":0.6539308428764343},{"id":"https://openalex.org/C2780791683","wikidata":"https://www.wikidata.org/wiki/Q846785","display_name":"Action (physics)","level":2,"score":0.6008872985839844},{"id":"https://openalex.org/C2780310539","wikidata":"https://www.wikidata.org/wiki/Q12547192","display_name":"Imperfect","level":2,"score":0.5455659031867981},{"id":"https://openalex.org/C113174947","wikidata":"https://www.wikidata.org/wiki/Q2859736","display_name":"Tree (set theory)","level":2,"score":0.545509397983551},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4732024371623993},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.3720657229423523},{"id":"https://openalex.org/C42475967","wikidata":"https://www.wikidata.org/wiki/Q194292","display_name":"Operations research","level":1,"score":0.3236236572265625},{"id":"https://openalex.org/C144237770","wikidata":"https://www.wikidata.org/wiki/Q747534","display_name":"Mathematical economics","level":1,"score":0.2018132209777832},{"id":"https://openalex.org/C19499675","wikidata":"https://www.wikidata.org/wiki/Q232207","display_name":"Monte Carlo method","level":2,"score":0.13825666904449463},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.10817888379096985},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.0},{"id":"https://openalex.org/C28826006","wikidata":"https://www.wikidata.org/wiki/Q33521","display_name":"Applied mathematics","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/C134306372","wikidata":"https://www.wikidata.org/wiki/Q7754","display_name":"Mathematical analysis","level":1,"score":0.0},{"id":"https://openalex.org/C115903868","wikidata":"https://www.wikidata.org/wiki/Q80993","display_name":"Software engineering","level":1,"score":0.0},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.0},{"id":"https://openalex.org/C62520636","wikidata":"https://www.wikidata.org/wiki/Q944","display_name":"Quantum mechanics","level":1,"score":0.0}],"mesh":[],"locations_count":5,"locations":[{"id":"doi:10.1109/tg.2021.3067723","is_oa":true,"landing_page_url":"https://doi.org/10.1109/tg.2021.3067723","pdf_url":"https://ieeexplore.ieee.org/ielx7/7782673/9797039/09382923.pdf","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":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Transactions on Games","raw_type":"journal-article"},{"id":"pmh:oai:aaltodoc.aalto.fi:123456789/118216","is_oa":true,"landing_page_url":"https://arxiv.org/abs/2012.12186","pdf_url":"https://arxiv.org/pdf/2012.12186","source":{"id":"https://openalex.org/S4306401662","display_name":"Aaltodoc (Aalto University)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I9927081","host_organization_name":"Aalto University","host_organization_lineage":["https://openalex.org/I9927081"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"publishedVersion"},{"id":"pmh:oai:arXiv.org:2012.12186","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2012.12186","pdf_url":"https://arxiv.org/pdf/2012.12186","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},{"id":"doi:10.48550/arxiv.2012.12186","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2012.12186","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":null,"is_accepted":false,"is_published":null,"raw_source_name":null,"raw_type":"article"},{"id":"mag:3116263860","is_oa":false,"landing_page_url":null,"pdf_url":null,"source":null,"license":null,"license_id":null,"version":null,"is_accepted":false,"is_published":null,"raw_source_name":null,"raw_type":null}],"best_oa_location":{"id":"doi:10.1109/tg.2021.3067723","is_oa":true,"landing_page_url":"https://doi.org/10.1109/tg.2021.3067723","pdf_url":"https://ieeexplore.ieee.org/ielx7/7782673/9797039/09382923.pdf","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":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Transactions on Games","raw_type":"journal-article"},"sustainable_development_goals":[{"score":0.5799999833106995,"id":"https://metadata.un.org/sdg/11","display_name":"Sustainable cities and communities"}],"awards":[],"funders":[],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W3116263860.pdf","grobid_xml":"https://content.openalex.org/works/W3116263860.grobid-xml"},"referenced_works_count":59,"referenced_works":["https://openalex.org/W35251828","https://openalex.org/W1540121360","https://openalex.org/W1646839507","https://openalex.org/W1908253641","https://openalex.org/W2019257274","https://openalex.org/W2020254732","https://openalex.org/W2029757490","https://openalex.org/W2036131226","https://openalex.org/W2039522160","https://openalex.org/W2048751428","https://openalex.org/W2099873274","https://openalex.org/W2103315867","https://openalex.org/W2113228754","https://openalex.org/W2126316555","https://openalex.org/W2145224651","https://openalex.org/W2145339207","https://openalex.org/W2150823748","https://openalex.org/W2151210636","https://openalex.org/W2168165432","https://openalex.org/W2168405694","https://openalex.org/W2322232506","https://openalex.org/W2574978968","https://openalex.org/W2576851011","https://openalex.org/W2602425879","https://openalex.org/W2736601468","https://openalex.org/W2766447205","https://openalex.org/W2773381986","https://openalex.org/W2888231292","https://openalex.org/W2890208098","https://openalex.org/W2892310660","https://openalex.org/W2931903779","https://openalex.org/W2943197047","https://openalex.org/W2960876848","https://openalex.org/W2962957031","https://openalex.org/W2963032742","https://openalex.org/W2963985863","https://openalex.org/W2964223369","https://openalex.org/W2966685683","https://openalex.org/W2982316857","https://openalex.org/W2982534290","https://openalex.org/W2996037775","https://openalex.org/W2996477464","https://openalex.org/W2996896271","https://openalex.org/W4234228486","https://openalex.org/W4312309732","https://openalex.org/W6601392155","https://openalex.org/W6632284170","https://openalex.org/W6640044251","https://openalex.org/W6640174482","https://openalex.org/W6675509861","https://openalex.org/W6682314434","https://openalex.org/W6737726454","https://openalex.org/W6741002519","https://openalex.org/W6748638692","https://openalex.org/W6750724039","https://openalex.org/W6755224613","https://openalex.org/W6760625672","https://openalex.org/W6762119003","https://openalex.org/W6772005887"],"related_works":["https://openalex.org/W3139232179","https://openalex.org/W2889169285","https://openalex.org/W45534592","https://openalex.org/W2788649699","https://openalex.org/W3034291030","https://openalex.org/W2418933646","https://openalex.org/W170748079","https://openalex.org/W2230033167","https://openalex.org/W3121173017","https://openalex.org/W3190944559","https://openalex.org/W3183390056","https://openalex.org/W2025400977","https://openalex.org/W2156718182","https://openalex.org/W2621153329","https://openalex.org/W1784789515","https://openalex.org/W3021310327","https://openalex.org/W1955510565","https://openalex.org/W3197189015","https://openalex.org/W3132532575","https://openalex.org/W2794882716"],"abstract_inverted_index":{"We":[0,47,95,131],"consider":[1],"learning":[2,27],"to":[3,17,36,63,78,85,138,161],"play":[4,86],"multiplayer":[5],"imperfect-information":[6,88],"games":[7,21,145],"with":[8,100,120],"simultaneous":[9],"moves":[10],"and":[11,70,125,151,155],"large":[12,112],"state-action":[13],"spaces.":[14,115],"Previous":[15],"attempts":[16],"tackle":[18,48],"such":[19],"challenging":[20],"have":[22],"largely":[23],"focused":[24],"on":[25,44,166],"model-free":[26],"methods,":[28],"often":[29],"requiring":[30],"hundreds":[31],"of":[32,34,51,67,75,146],"years":[33],"experience":[35],"produce":[37],"competitive":[38],"agents.":[39],"Our":[40],"approach":[41],"is":[42,83,136],"based":[43],"model-based":[45],"planning.":[46],"the":[49,64,68,73,76,87,92,134,144,156],"problem":[50],"partial":[52],"observability":[53],"by":[54,90,164],"first":[55],"building":[56],"an":[57],"(oracle)":[58],"planner":[59,135],"that":[60,98,133],"has":[61],"access":[62],"full":[65],"state":[66],"environment":[69],"then":[71],"distilling":[72],"knowledge":[74],"oracle":[77],"a":[79,121,167],"(follower)":[80],"agent":[81],"which":[82],"trained":[84],"game":[89],"imitating":[91],"oracle\u2019s":[93],"choices.":[94],"experimentally":[96],"show":[97,132],"planning":[99,119],"naive":[101],"Monte":[102],"Carlo":[103],"tree":[104,123],"search":[105,124],"does":[106],"not":[107],"perform":[108],"very":[109],"well":[110],"in":[111,143],"combinatorial":[113],"action":[114,129],"We,":[116],"therefore,":[117],"propose":[118],"fixed-depth":[122],"decoupled":[126],"TS":[127],"for":[128],"selection.":[130],"able":[137],"discover":[139],"efficient":[140],"playing":[141],"strategies":[142],"<italic":[147,152],"xmlns:mml=\"http://www.w3.org/1998/Math/MathML\"":[148,153],"xmlns:xlink=\"http://www.w3.org/1999/xlink\">Clash":[149],"Royale</i>":[150],"xmlns:xlink=\"http://www.w3.org/1999/xlink\">Pommerman</i>":[154],"follower":[157],"policy":[158],"successfully":[159],"learns":[160],"implement":[162],"them":[163],"training":[165],"few":[168],"hundred":[169],"battles.":[170]},"counts_by_year":[],"updated_date":"2026-04-01T17:29:45.350535","created_date":"2025-10-10T00:00:00"}