{"id":"https://openalex.org/W23427608","doi":null,"title":"Learning to play Tetris applying reinforcement learning methods.","display_name":"Learning to play Tetris applying reinforcement learning methods.","publication_year":2008,"publication_date":"2008-01-01","ids":{"openalex":"https://openalex.org/W23427608","mag":"23427608"},"language":"en","primary_location":{"id":"mag:23427608","doi":null,"is_oa":false,"landing_page_url":"https://dblp.uni-trier.de/db/conf/esann/esann2008.html#GrossFS08","pdf_url":null,"source":{"id":"https://openalex.org/S4306421047","display_name":"The European Symposium on Artificial Neural Networks","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":"The European Symposium on Artificial Neural Networks","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/A5101666987","display_name":"Alexander Gro\u00df","orcid":"https://orcid.org/0009-0004-7516-0479","observed_orcids":["https://orcid.org/0009-0004-7516-0479"]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Alexander Gro\u00df","raw_affiliation_strings":[],"raw_orcid":"https://orcid.org/0009-0004-7516-0479","affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5036939264","display_name":"Jan Friedland","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Jan Friedland","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5078096723","display_name":"Friedhelm Schwenker","orcid":"https://orcid.org/0000-0001-5118-0812","observed_orcids":["https://orcid.org/0000-0001-5118-0812"]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Friedhelm Schwenker","raw_affiliation_strings":[],"raw_orcid":"https://orcid.org/0000-0001-5118-0812","affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":0,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":7,"citation_normalized_percentile":{"value":0.00193023,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":88,"max":96},"biblio":{"volume":null,"issue":null,"first_page":"131","last_page":"136"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10462","display_name":"Reinforcement Learning in Robotics","score":0.5835000276565552,"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":0.5835000276565552,"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":0.41530001163482666,"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/T13904","display_name":"Artificial Intelligence Applications","score":0.00019999999494757503,"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/tetris","display_name":"Tetris","score":0.9980000257492065},{"id":"https://openalex.org/keywords/reinforcement-learning","display_name":"reinforcement learning","score":0.906000018119812},{"id":"https://openalex.org/keywords/temporal-difference-learning","display_name":"temporal difference learning","score":0.996999979019165},{"id":"https://openalex.org/keywords/state-value-function","display_name":"state value function","score":0.7820000052452087},{"id":"https://openalex.org/keywords/epsilon-greedy-policy","display_name":"epsilon-greedy policy","score":0.984000027179718},{"id":"https://openalex.org/keywords/reward-function","display_name":"reward function","score":0.7760000228881836},{"id":"https://openalex.org/keywords/game-agents","display_name":"game-playing agents","score":0.6759999990463257},{"id":"https://openalex.org/keywords/game-tree-search","display_name":"game tree search","score":0.5730000138282776},{"id":"https://openalex.org/keywords/evaluation-function","display_name":"evaluation function","score":0.7519999742507935}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7013246417045593},{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.6940546631813049},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.63158118724823},{"id":"https://openalex.org/C127705205","wikidata":"https://www.wikidata.org/wiki/Q5748245","display_name":"Heuristics","level":2,"score":0.5966220498085022},{"id":"https://openalex.org/C95815963","wikidata":"https://www.wikidata.org/wiki/Q1377033","display_name":"Game tree","level":4,"score":0.5370136499404907},{"id":"https://openalex.org/C131806220","wikidata":"https://www.wikidata.org/wiki/Q852705","display_name":"Evaluation function","level":2,"score":0.5265025496482849},{"id":"https://openalex.org/C62611344","wikidata":"https://www.wikidata.org/wiki/Q1062658","display_name":"Node (physics)","level":2,"score":0.5183190107345581},{"id":"https://openalex.org/C113174947","wikidata":"https://www.wikidata.org/wiki/Q2859736","display_name":"Tree (set theory)","level":2,"score":0.501488447189331},{"id":"https://openalex.org/C73795354","wikidata":"https://www.wikidata.org/wiki/Q287618","display_name":"Sequential game","level":3,"score":0.4998598098754883},{"id":"https://openalex.org/C196340769","wikidata":"https://www.wikidata.org/wiki/Q7698910","display_name":"Temporal difference learning","level":3,"score":0.47623470425605774},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.4290412962436676},{"id":"https://openalex.org/C46149586","wikidata":"https://www.wikidata.org/wiki/Q11785332","display_name":"Monte Carlo tree search","level":3,"score":0.42801767587661743},{"id":"https://openalex.org/C202556891","wikidata":"https://www.wikidata.org/wiki/Q1584646","display_name":"Repeated game","level":3,"score":0.42371416091918945},{"id":"https://openalex.org/C167573328","wikidata":"https://www.wikidata.org/wiki/Q7439054","display_name":"Screening game","level":4,"score":0.4123912751674652},{"id":"https://openalex.org/C177142836","wikidata":"https://www.wikidata.org/wiki/Q44455","display_name":"Game theory","level":2,"score":0.3822135031223297},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.1850026547908783},{"id":"https://openalex.org/C144237770","wikidata":"https://www.wikidata.org/wiki/Q747534","display_name":"Mathematical economics","level":1,"score":0.1560523808002472},{"id":"https://openalex.org/C19499675","wikidata":"https://www.wikidata.org/wiki/Q232207","display_name":"Monte Carlo method","level":2,"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/C66938386","wikidata":"https://www.wikidata.org/wiki/Q633538","display_name":"Structural engineering","level":1,"score":0.0},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","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/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"mag:23427608","doi":null,"is_oa":false,"landing_page_url":"https://dblp.uni-trier.de/db/conf/esann/esann2008.html#GrossFS08","pdf_url":null,"source":{"id":"https://openalex.org/S4306421047","display_name":"The European Symposium on Artificial Neural Networks","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":"The European Symposium on Artificial Neural Networks","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":7,"referenced_works":["https://openalex.org/W2121863487","https://openalex.org/W2131600418","https://openalex.org/W2146302034","https://openalex.org/W2339916026","https://openalex.org/W2341171179","https://openalex.org/W2911283634","https://openalex.org/W2952045762"],"related_works":["https://openalex.org/W988857921","https://openalex.org/W7100591397","https://openalex.org/W136497129","https://openalex.org/W3206690988","https://openalex.org/W7097996313","https://openalex.org/W7100323006","https://openalex.org/W6959692770","https://openalex.org/W7097641142","https://openalex.org/W7099433845","https://openalex.org/W4283376938"],"abstract_inverted_index":{"In":[0,44,215,314],"this":[1,255,358],"paper":[2,359],"the":[3,13,23,45,53,118,125,149,158,170,174,178,183,194,199,202,209,213,220,229,234,260,264,344],"application":[4],"of":[5,15,127,148,161,177,201,212,263,284,383,389],"reinforcement":[6,352],"learning":[7,18,107,271,278,353,369],"to":[8,21,87,97,226,236,258,322,340,393],"Tetris":[9,33,378],"is":[10,19,81,93,169,223,257,364,380],"investigated,":[11],"particulary":[12],"idea":[14],"temporal":[16,367],"difference":[17,368],"applied":[20,335],"estimate":[22,259],"state":[24],"value":[25],"function":[26],"V.":[27],"For":[28],"two":[29,401],"predefined":[30],"reward":[31,69],"functions":[32,274],"agents":[34,55,60],"have":[35,109,135,293,319],"been":[36,110,136,294,320,371],"trained":[37,54],"by":[38,63,242,248,266],"using":[39],"a":[40,67,83,94,162,360,381],"\ufffd":[41],"-greedy":[42],"policy.":[43],"numerical":[46],"experiments":[47],"it":[48],"can":[49,56,190,398],"be":[50,191,237,240,399],"observed":[51],"that":[52,189],"outperform":[57],"fixed":[58],"policy":[59],"significantly,":[61],"e.g.":[62],"factor":[64],"5":[65],"for":[66,141,193,304,328,374],"complex":[68],"function.":[70],"Playing":[71],"games,":[72,140],"such":[73,272],"like":[74],"Chess,":[75],"Go,":[76],"Checkers,":[77],"Backgammon":[78,342],"or":[79],"Poker,":[80],"always":[82],"great":[84],"intellectual":[85],"challenge":[86,283],"humans,":[88],"and":[89,99,113,131,204,232,270,300,386],"therefore":[90,233],"game":[91,133,144,154,163,329],"playing":[92,330,375],"sce-":[95],"nario":[96],"test":[98],"evaluate":[100],"artificial":[101,129,288,345],"intelligence":[102,130],"methods,":[103],"in":[104,138,164,254,286,297,306,357,400],"particular":[105],"machine":[106,277],"aspects":[108],"taken":[111],"more":[112,114],"into":[115],"account":[116],"during":[117],"last":[119],"years.":[120],"Many":[121],"methods":[122],"derived":[123],"from":[124],"fields":[126],"traditional":[128],"mathematical":[132],"theory":[134],"utilized":[137],"computer":[139],"in-":[142],"stance,":[143],"trees":[145],"are":[146,185,207],"one":[147],"most":[150],"popular":[151,252],"tools.":[152],"A":[153,251],"tree":[155,184,222],"represents":[156],"all":[157,187,217,228],"possible":[159,230,402],"states":[160,188,211,403],"its":[165],"nodes.":[166],"Starting":[167],"point":[168],"root":[171],"node":[172,196],"representing":[173,186,208],"starting":[175],"configuration":[176],"game.":[179,214],"Children":[180],"nodes":[181,206],"within":[182],"reached":[192],"current":[195],"follow-":[197],"ing":[198,276],"rules":[200],"game,":[203],"leaf":[205],"terminal":[210],"almost":[216],"(interesting)":[218],"games":[219],"complete":[221],"too":[224],"large":[225],"search":[227],"pathes,":[231],"space":[235],"searched":[238],"must":[239],"reduced":[241],"applying":[243],"heuristics":[244],"which":[245,363,391],"were":[246],"tailored":[247],"human":[249],"experts.":[250],"attempt":[253],"direction":[256],"winning":[261],"chance":[262],"player":[265],"so-called":[267],"evaluation":[268,273],"functions,":[269],"utiliz-":[275],"techniques":[279],"became":[280],"an":[281],"important":[282],"research":[285],"modern":[287],"intelligence.":[289],"Artificial":[290],"neural":[291,326,337,346],"networks":[292,327],"successfully":[295],"used":[296,349],"many":[298],"scientific":[299],"real":[301],"world":[302],"applications,":[303],"instance":[305],"pattern":[307],"recognition,":[308],"data":[309],"mining,":[310],"time":[311],"series":[312],"prediction.":[313],"recent":[315],"years":[316],"some":[317],"attempts":[318],"made":[321],"train":[323],"artifi-":[324],"cial":[325],"tasks.":[331],"Tesauro":[332],"(1)":[333],"has":[334,370],"feedforward":[336],"network":[338],"models":[339],"play":[341],"where":[343],"net":[347],"was":[348],"together":[350],"with":[351],"(RL)":[354],"algorithms.":[355],"Here":[356],"RL":[361],"algorithm":[362],"known":[365],"as":[366],"inves-":[372],"tigated":[373],"Tetris.":[376],"The":[377],"board":[379],"grid":[382],"10":[384],"columns":[385],"20":[387],"rows":[388],"cells,":[390],"totals":[392],"200":[394],"cells.":[395],"Every":[396],"cell":[397],"called":[404]},"counts_by_year":[{"year":2024,"cited_by_count":1},{"year":2018,"cited_by_count":2},{"year":2017,"cited_by_count":1},{"year":2015,"cited_by_count":1},{"year":2014,"cited_by_count":1},{"year":2012,"cited_by_count":1}],"updated_date":"2026-10-16T09:59:22.235173","created_date":"2016-06-24T00:00:00"}