{"id":"https://openalex.org/W4296474736","doi":"https://doi.org/10.1109/cog51982.2022.9893588","title":"Supervised and Reinforcement Learning from Observations in Reconnaissance Blind Chess","display_name":"Supervised and Reinforcement Learning from Observations in Reconnaissance Blind Chess","publication_year":2022,"publication_date":"2022-08-21","ids":{"openalex":"https://openalex.org/W4296474736","doi":"https://doi.org/10.1109/cog51982.2022.9893588"},"language":"en","primary_location":{"id":"doi:10.1109/cog51982.2022.9893588","is_oa":false,"landing_page_url":"https://doi.org/10.1109/cog51982.2022.9893588","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/A5074993133","display_name":"Timo Bertram","orcid":"https://orcid.org/0000-0002-9733-8504"},"institutions":[{"id":"https://openalex.org/I4210146193","display_name":"Linz Center of Mechatronics (Austria)","ror":"https://ror.org/05dwv6530","country_code":"AT","type":"company","lineage":["https://openalex.org/I4210146193"]}],"countries":["AT"],"is_corresponding":true,"raw_author_name":"Timo Bertram","raw_affiliation_strings":["JKU Linz,Austria","JKU Linz, Austria"],"affiliations":[{"raw_affiliation_string":"JKU Linz,Austria","institution_ids":["https://openalex.org/I4210146193"]},{"raw_affiliation_string":"JKU Linz, Austria","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5020009031","display_name":"Johannes F\u00fcrnkranz","orcid":"https://orcid.org/0000-0002-1207-0159"},"institutions":[{"id":"https://openalex.org/I4210146193","display_name":"Linz Center of Mechatronics (Austria)","ror":"https://ror.org/05dwv6530","country_code":"AT","type":"company","lineage":["https://openalex.org/I4210146193"]}],"countries":["AT"],"is_corresponding":false,"raw_author_name":"Johannes Furnkranz","raw_affiliation_strings":["JKU Linz,Austria","JKU Linz, Austria"],"affiliations":[{"raw_affiliation_string":"JKU Linz,Austria","institution_ids":["https://openalex.org/I4210146193"]},{"raw_affiliation_string":"JKU Linz, Austria","institution_ids":[]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5010677076","display_name":"Martin M\u0081\u00fcller","orcid":"https://orcid.org/0000-0002-5639-5318"},"institutions":[{"id":"https://openalex.org/I154425047","display_name":"University of Alberta","ror":"https://ror.org/0160cpw27","country_code":"CA","type":"education","lineage":["https://openalex.org/I154425047"]}],"countries":["CA"],"is_corresponding":false,"raw_author_name":"Martin Muller","raw_affiliation_strings":["University of Alberta,Canada","University of Alberta, Canada"],"affiliations":[{"raw_affiliation_string":"University of Alberta,Canada","institution_ids":["https://openalex.org/I154425047"]},{"raw_affiliation_string":"University of Alberta, Canada","institution_ids":["https://openalex.org/I154425047"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5074993133"],"corresponding_institution_ids":["https://openalex.org/I4210146193"],"apc_list":null,"apc_paid":null,"fwci":1.0606,"has_fulltext":false,"cited_by_count":8,"citation_normalized_percentile":{"value":0.80745678,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":91,"max":98},"biblio":{"volume":null,"issue":null,"first_page":"608","last_page":"611"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11574","display_name":"Artificial Intelligence in Games","score":0.9991999864578247,"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":0.9991999864578247,"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":0.998199999332428,"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/T11674","display_name":"Sports Analytics and Performance","score":0.9980000257492065,"subfield":{"id":"https://openalex.org/subfields/2002","display_name":"Economics and Econometrics"},"field":{"id":"https://openalex.org/fields/20","display_name":"Economics, Econometrics and Finance"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/reinforcement-learning","display_name":"Reinforcement learning","score":0.8931829929351807},{"id":"https://openalex.org/keywords/observability","display_name":"Observability","score":0.8866025805473328},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.723966121673584},{"id":"https://openalex.org/keywords/perfect-information","display_name":"Perfect information","score":0.6055241227149963},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5666040778160095},{"id":"https://openalex.org/keywords/state","display_name":"State (computer science)","score":0.514674961566925},{"id":"https://openalex.org/keywords/imperfect","display_name":"Imperfect","score":0.4918229579925537},{"id":"https://openalex.org/keywords/position","display_name":"Position (finance)","score":0.4481019675731659},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.4139710068702698},{"id":"https://openalex.org/keywords/mathematical-economics","display_name":"Mathematical economics","score":0.09042012691497803},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.0786871612071991}],"concepts":[{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.8931829929351807},{"id":"https://openalex.org/C36299963","wikidata":"https://www.wikidata.org/wiki/Q1369844","display_name":"Observability","level":2,"score":0.8866025805473328},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.723966121673584},{"id":"https://openalex.org/C123676819","wikidata":"https://www.wikidata.org/wiki/Q1074338","display_name":"Perfect information","level":2,"score":0.6055241227149963},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5666040778160095},{"id":"https://openalex.org/C48103436","wikidata":"https://www.wikidata.org/wiki/Q599031","display_name":"State (computer science)","level":2,"score":0.514674961566925},{"id":"https://openalex.org/C2780310539","wikidata":"https://www.wikidata.org/wiki/Q12547192","display_name":"Imperfect","level":2,"score":0.4918229579925537},{"id":"https://openalex.org/C198082294","wikidata":"https://www.wikidata.org/wiki/Q3399648","display_name":"Position (finance)","level":2,"score":0.4481019675731659},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.4139710068702698},{"id":"https://openalex.org/C144237770","wikidata":"https://www.wikidata.org/wiki/Q747534","display_name":"Mathematical economics","level":1,"score":0.09042012691497803},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.0786871612071991},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.0},{"id":"https://openalex.org/C10138342","wikidata":"https://www.wikidata.org/wiki/Q43015","display_name":"Finance","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/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","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/C28826006","wikidata":"https://www.wikidata.org/wiki/Q33521","display_name":"Applied mathematics","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/cog51982.2022.9893588","is_oa":false,"landing_page_url":"https://doi.org/10.1109/cog51982.2022.9893588","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":[{"score":0.5199999809265137,"id":"https://metadata.un.org/sdg/16","display_name":"Peace, Justice and strong institutions"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":23,"referenced_works":["https://openalex.org/W2257979135","https://openalex.org/W2537003064","https://openalex.org/W2574978968","https://openalex.org/W2736601468","https://openalex.org/W2772709170","https://openalex.org/W2913781869","https://openalex.org/W2960876848","https://openalex.org/W2964164283","https://openalex.org/W2982316857","https://openalex.org/W2996037775","https://openalex.org/W3044994704","https://openalex.org/W4286910594","https://openalex.org/W4288626409","https://openalex.org/W4295237430","https://openalex.org/W6696772115","https://openalex.org/W6741002519","https://openalex.org/W6746177919","https://openalex.org/W6758650442","https://openalex.org/W6772005887","https://openalex.org/W6780162350","https://openalex.org/W6781244629","https://openalex.org/W6802590814","https://openalex.org/W6810405029"],"related_works":["https://openalex.org/W2360321812","https://openalex.org/W2395295193","https://openalex.org/W3122057932","https://openalex.org/W3088364074","https://openalex.org/W2004230228","https://openalex.org/W1496801567","https://openalex.org/W2113798763","https://openalex.org/W2900431508","https://openalex.org/W2145796981","https://openalex.org/W2610227658"],"abstract_inverted_index":{"In":[0],"this":[1,96,119],"work,":[2],"we":[3,37,49,98],"adapt":[4],"a":[5,30,40],"training":[6],"approach":[7],"inspired":[8],"by":[9,77],"the":[10,16,26,34,51,54,59,78,87,105,116,130,142],"original":[11],"AlphaGo":[12],"system":[13],"to":[14,73,90],"play":[15],"imperfect":[17],"information":[18],"game":[19,35,46,82,144],"of":[20,29,33,53,81,102,118],"Reconnaissance":[21],"Blind":[22],"Chess.":[23],"Using":[24],"only":[25,85],"observations":[27],"instead":[28],"full":[31],"description":[32],"state,":[36],"first":[38],"train":[39],"supervised":[41],"agent":[42,55,111,131],"on":[43,104],"publicly":[44],"available":[45],"records.":[47],"Next,":[48],"increase":[50],"performance":[52,127],"through":[56],"self-play":[57,124],"with":[58],"on-policy":[60],"reinforcement":[61],"learning":[62],"algorithm":[63],"Proximal":[64],"Policy":[65],"optimization.":[66],"We":[67,121],"do":[68],"not":[69],"use":[70,86],"any":[71],"search":[72,136],"avoid":[74],"problems":[75],"caused":[76],"partial":[79],"observability":[80],"states":[83],"and":[84,128,137],"policy":[88],"network":[89],"generate":[91],"moves":[92],"when":[93],"playing.":[94],"With":[95],"approach,":[97],"achieve":[99],"an":[100],"ELO":[101],"1330":[103],"RBC":[106],"leaderboard,":[107],"which":[108],"places":[109],"our":[110],"at":[112,115],"position":[113],"27":[114],"time":[117],"writing.":[120],"see":[122],"that":[123,129],"significantly":[125],"improves":[126],"plays":[132],"acceptably":[133],"well":[134],"without":[135,138],"making":[139],"assumptions":[140],"about":[141],"true":[143],"state.":[145]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2024,"cited_by_count":4},{"year":2023,"cited_by_count":3}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}