{"id":"https://openalex.org/W7204844270","doi":"https://doi.org/10.48550/arxiv.2608.27757","title":"Beyond Search-Imitation: Prior-Directed Exploration for Searchless Chess","display_name":"Beyond Search-Imitation: Prior-Directed Exploration for Searchless Chess","publication_year":2026,"publication_date":"2026-08-27","ids":{"openalex":"https://openalex.org/W7204844270","doi":"https://doi.org/10.48550/arxiv.2608.27757"},"language":"en","primary_location":{"id":"pmh:oai:arXiv.org:2608.27757","doi":null,"is_oa":true,"landing_page_url":"https://arxiv.org/abs/2608.27757","pdf_url":"https://arxiv.org/pdf/2608.27757","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"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"},"volume":null,"type":"preprint","is_traditional":true,"indexed_in":["arxiv","datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2608.27757","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5114336046","display_name":"Szymon Mi\u0142osz","orcid":"https://orcid.org/0009-0007-7408-7304","observed_orcids":["https://orcid.org/0009-0007-7408-7304"]},"institutions":[{"id":"https://openalex.org/I188884621","display_name":"Lodz University of Technology","ror":"https://ror.org/00s8fpf52","country_code":"PL","type":"education","lineage":["https://openalex.org/I188884621"]}],"countries":["PL"],"is_corresponding":false,"raw_author_name":"Mi\u0142osz, Szymon","raw_affiliation_strings":["Institute of Applied Computer Science , Lodz University of Technology"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Institute of Applied Computer Science , Lodz University of Technology","institution_ids":["https://openalex.org/I188884621"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5025652198","display_name":"Piotr Duch","orcid":"https://orcid.org/0000-0003-0656-1215","observed_orcids":["https://orcid.org/0000-0003-0656-1215"]},"institutions":[{"id":"https://openalex.org/I188884621","display_name":"Lodz University of Technology","ror":"https://ror.org/00s8fpf52","country_code":"PL","type":"education","lineage":["https://openalex.org/I188884621"]}],"countries":["PL"],"is_corresponding":false,"raw_author_name":"Duch, Piotr","raw_affiliation_strings":["Institute of Applied Computer Science , Lodz University of Technology"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Institute of Applied Computer Science , Lodz University of Technology","institution_ids":["https://openalex.org/I188884621"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5000229752","display_name":"Szymon Grabowski","orcid":"https://orcid.org/0000-0003-1714-1224","observed_orcids":["https://orcid.org/0000-0003-1714-1224"]},"institutions":[{"id":"https://openalex.org/I188884621","display_name":"Lodz University of Technology","ror":"https://ror.org/00s8fpf52","country_code":"PL","type":"education","lineage":["https://openalex.org/I188884621"]}],"countries":["PL"],"is_corresponding":false,"raw_author_name":"Grabowski, Szymon","raw_affiliation_strings":["Institute of Applied Computer Science , Lodz University of Technology"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Institute of Applied Computer Science , Lodz University of Technology","institution_ids":["https://openalex.org/I188884621"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I188884621"],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":true,"cited_by_count":0,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"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":1.0,"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":1.0,"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":9.999999747378752e-05,"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":0.0,"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/reverse-kl-divergence","display_name":"reverse KL divergence","score":0.7459999918937683},{"id":"https://openalex.org/keywords/self-play-reinforcement-learning","display_name":"self-play reinforcement learning","score":0.781000018119812},{"id":"https://openalex.org/keywords/alphazero","display_name":"AlphaZero","score":0.4009999930858612},{"id":"https://openalex.org/keywords/monte-carlo-tree-search","display_name":"Monte Carlo tree search","score":0.7070000171661377},{"id":"https://openalex.org/keywords/puzzle-solving","display_name":"puzzle solving","score":0.5519999861717224},{"id":"https://openalex.org/keywords/sampling-temperature","display_name":"sampling temperature","score":0.382999986410141},{"id":"https://openalex.org/keywords/fine-tuning","display_name":"fine-tuning","score":0.5450000166893005}],"concepts":[{"id":"https://openalex.org/C2779117054","wikidata":"https://www.wikidata.org/wiki/Q1406345","display_name":"Straddle","level":2,"score":0.6827999949455261},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5382999777793884},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.503600001335144},{"id":"https://openalex.org/C79581498","wikidata":"https://www.wikidata.org/wiki/Q1367530","display_name":"Suite","level":2,"score":0.4765999913215637},{"id":"https://openalex.org/C2780148112","wikidata":"https://www.wikidata.org/wiki/Q1432581","display_name":"Proxy (statistics)","level":2,"score":0.44690001010894775},{"id":"https://openalex.org/C46149586","wikidata":"https://www.wikidata.org/wiki/Q11785332","display_name":"Monte Carlo tree search","level":3,"score":0.39329999685287476},{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.3781999945640564},{"id":"https://openalex.org/C106301342","wikidata":"https://www.wikidata.org/wiki/Q4117933","display_name":"Entropy (arrow of time)","level":2,"score":0.3723999857902527},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.3522999882698059},{"id":"https://openalex.org/C198082294","wikidata":"https://www.wikidata.org/wiki/Q3399648","display_name":"Position (finance)","level":2,"score":0.3393000066280365},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.33009999990463257},{"id":"https://openalex.org/C140779682","wikidata":"https://www.wikidata.org/wiki/Q210868","display_name":"Sampling (signal processing)","level":3,"score":0.32030001282691956},{"id":"https://openalex.org/C44154836","wikidata":"https://www.wikidata.org/wiki/Q45045","display_name":"Simulation","level":1,"score":0.3197000026702881},{"id":"https://openalex.org/C184898388","wikidata":"https://www.wikidata.org/wiki/Q1435712","display_name":"Pairwise comparison","level":2,"score":0.30239999294281006},{"id":"https://openalex.org/C113174947","wikidata":"https://www.wikidata.org/wiki/Q2859736","display_name":"Tree (set theory)","level":2,"score":0.29919999837875366},{"id":"https://openalex.org/C19499675","wikidata":"https://www.wikidata.org/wiki/Q232207","display_name":"Monte Carlo method","level":2,"score":0.2953999936580658},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.29089999198913574},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.2786000072956085},{"id":"https://openalex.org/C2775924081","wikidata":"https://www.wikidata.org/wiki/Q55608371","display_name":"Control (management)","level":2,"score":0.2766000032424927},{"id":"https://openalex.org/C2776291640","wikidata":"https://www.wikidata.org/wiki/Q2912517","display_name":"Value (mathematics)","level":2,"score":0.27619999647140503},{"id":"https://openalex.org/C84525736","wikidata":"https://www.wikidata.org/wiki/Q831366","display_name":"Decision tree","level":2,"score":0.25099998712539673}],"mesh":[],"locations_count":2,"locations":[{"id":"pmh:oai:arXiv.org:2608.27757","doi":null,"is_oa":true,"landing_page_url":"https://arxiv.org/abs/2608.27757","pdf_url":"https://arxiv.org/pdf/2608.27757","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"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.2608.27757","doi":"https://doi.org/10.48550/arxiv.2608.27757","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2608.27757","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"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":false,"raw_source_name":null,"raw_type":"Preprint"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2608.27757","doi":null,"is_oa":true,"landing_page_url":"https://arxiv.org/abs/2608.27757","pdf_url":"https://arxiv.org/pdf/2608.27757","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"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"},"sustainable_development_goals":[],"study_designs":[],"awards":[],"funders":[],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W7204844270.pdf","grobid_xml":"https://content.openalex.org/works/W7204844270.grobid-xml"},"referenced_works_count":24,"referenced_works":["https://openalex.org/W1821462560","https://openalex.org/W2581377246","https://openalex.org/W2736601468","https://openalex.org/W2799151646","https://openalex.org/W3096457737","https://openalex.org/W4382173266","https://openalex.org/W4387215929","https://openalex.org/W4391631327","https://openalex.org/W4406458728","https://openalex.org/W4415420761","https://openalex.org/W4415797334","https://openalex.org/W4415798102","https://openalex.org/W4415990027","https://openalex.org/W4416048648","https://openalex.org/W4416065894","https://openalex.org/W4416134121","https://openalex.org/W4416149849","https://openalex.org/W4416373165","https://openalex.org/W4416383302","https://openalex.org/W4416623184","https://openalex.org/W7128674099","https://openalex.org/W7133208539","https://openalex.org/W7154321583","https://openalex.org/W7161802264"],"related_works":["https://openalex.org/W6948168489","https://openalex.org/W4416149849","https://openalex.org/W7214924654","https://openalex.org/W4322616209","https://openalex.org/W6922673205","https://openalex.org/W4415990027","https://openalex.org/W7165887343","https://openalex.org/W3019643906","https://openalex.org/W2955323835","https://openalex.org/W2906970789"],"abstract_inverted_index":{"Searchless":[0],"chess":[1],"networks":[2],"reach":[3],"human":[4],"master":[5],"strength":[6,53,149,161],"from":[7,131,142],"a":[8,14,38,41,79,118,136,164,176,185,202,208,218,223,254],"single":[9,224],"forward":[10],"pass":[11],"by":[12,64,109],"imitating":[13],"stronger":[15,209],"teacher:":[16],"the":[17,26,68,84,94,96,110,154,169,182,192,229,234,240,248,264,267],"strongest,":[18],"Leela":[19],"Chess":[20],"Zero's":[21],"(Lc0)":[22],"released":[23],"Chessformer,":[24],"distills":[25],"visit":[27],"counts":[28],"of":[29,226],"an":[30,65,104],"AlphaZero-style":[31],"Monte":[32],"Carlo":[33],"Tree":[34],"Search":[35],"(MCTS).":[36],"Imitating":[37],"search":[39],"is":[40,61,120,205],"poor":[42],"proxy":[43],"for":[44,51],"playing":[45,160],"without":[46,217],"one,":[47],"so":[48,91],"we":[49,167],"fine-tune":[50],"single-pass":[52],"with":[54,78,103,253],"self-play":[55,220],"reinforcement":[56],"learning":[57],"(RL).":[58],"Its":[59],"exploration":[60,92],"usually":[62],"supplied":[63],"entropy":[66],"bonus,":[67],"reverse":[69],"Kullback-Leibler":[70],"(KL)":[71],"divergence":[72],"to":[73,133,144],"uniform.":[74],"We":[75],"replace":[76],"it":[77,102,127],"forward,":[80],"mass-covering":[81,268],"KL":[82],"toward":[83],"network's":[85],"own":[86],"MCTS":[87],"prior":[88,97,241,246,269],"(prior-directed":[89],"exploration),":[90],"covers":[93],"moves":[95],"judges":[98],"promising,":[99],"and":[100,139,159,184,228,262],"pair":[101],"entropy-adaptive":[105],"sampling":[106],"temperature,":[107],"set":[108],"value":[111],"head's":[112],"outcome":[113],"uncertainty,":[114],"that":[115,257],"sharpens":[116],"once":[117],"position":[119],"decided.":[121],"In":[122],"about":[123],"two":[124,170],"thousand":[125],"steps":[126],"raises":[128],"puzzle":[129],"accuracy":[130,141,158,172],"93.9%":[132],"94.9%":[134],"on":[135,188],"100,000-puzzle":[137],"suite":[138],"mate-in-four":[140],"77%":[143],"81%":[145],"while":[146,179,197],"holding":[147],"searchless":[148],"at":[150],"or":[151],"slightly":[152],"above":[153],"base.":[155],"Measuring":[156],"tactical":[157,195],"together":[162],"across":[163],"matched-compute":[165],"sweep,":[166],"find":[168],"dissociate:":[171],"gains":[173,196],"fall":[174],"in":[175,271],"one-point":[177],"band":[178],"ratings":[180],"straddle":[181],"base,":[183],"control":[186],"fine-tuned":[187],"puzzles":[189,230],"alone":[190],"posts":[191],"study's":[193],"largest":[194],"shedding":[198],"roughly":[199],"260":[200],"Elo;":[201],"better":[203],"puzzle-solver":[204],"not":[206],"thereby":[207],"player.":[210],"Distribution-level":[211],"measurements":[212],"show":[213],"what":[214],"anchoring":[215],"buys:":[216],"regularizer":[219],"collapses":[221],"onto":[222],"line":[225],"play,":[227],"newly":[231],"solved":[232],"are":[233],"near":[235],"misses":[236],"whose":[237],"winning":[238],"move":[239],"kept":[242],"alive.":[243],"The":[244],"forward-KL":[245],"tops":[247],"rating":[249],"ladder,":[250],"statistically":[251],"tied":[252],"reverse-KL":[255],"anchor":[256],"concentrates":[258],"twice":[259],"as":[260],"hard":[261],"drops":[263],"hardest":[265],"solutions":[266],"keeps":[270],"support.":[272]},"counts_by_year":[],"updated_date":"2026-11-07T11:25:07.637180","created_date":"2026-09-01T00:00:00"}