{"id":"https://openalex.org/W4378746517","doi":"https://doi.org/10.3389/frai.2023.1014561","title":"AlphaZe\u2217\u2217: AlphaZero-like baselines for imperfect information games are surprisingly strong","display_name":"AlphaZe\u2217\u2217: AlphaZero-like baselines for imperfect information games are surprisingly strong","publication_year":2023,"publication_date":"2023-05-12","ids":{"openalex":"https://openalex.org/W4378746517","doi":"https://doi.org/10.3389/frai.2023.1014561","pmid":"https://pubmed.ncbi.nlm.nih.gov/37251273"},"language":"en","primary_location":{"id":"doi:10.3389/frai.2023.1014561","is_oa":true,"landing_page_url":"https://doi.org/10.3389/frai.2023.1014561","pdf_url":"https://www.frontiersin.org/articles/10.3389/frai.2023.1014561/pdf","source":{"id":"https://openalex.org/S4210197006","display_name":"Frontiers in Artificial Intelligence","issn_l":"2624-8212","issn":["2624-8212"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310320527","host_organization_name":"Frontiers Media","host_organization_lineage":["https://openalex.org/P4310320527"],"host_organization_lineage_names":["Frontiers Media"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Frontiers in Artificial Intelligence","raw_type":"journal-article"},"type":"article","indexed_in":["crossref","datacite","doaj","pubmed"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://www.frontiersin.org/articles/10.3389/frai.2023.1014561/pdf","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5036345046","display_name":"Jannis Bl\u00fcml","orcid":"https://orcid.org/0000-0002-9400-0946"},"institutions":[{"id":"https://openalex.org/I31512782","display_name":"Technische Universit\u00e4t Darmstadt","ror":"https://ror.org/05n911h24","country_code":"DE","type":"education","lineage":["https://openalex.org/I31512782"]},{"id":"https://openalex.org/I4392021234","display_name":"Hessian Center for Artificial Intelligence","ror":"https://ror.org/014ybqb54","country_code":"DE","type":"facility","lineage":["https://openalex.org/I31512782","https://openalex.org/I4392021234"]}],"countries":["DE"],"is_corresponding":true,"raw_author_name":"Jannis Bl\u00fcml","raw_affiliation_strings":["Artificial Intelligence and Machine Learning Lab, Technical University of Darmstadt, Darmstadt, Germany","Hessian Center for Artificial Intelligence (hessian.AI), Darmstadt, Germany"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Artificial Intelligence and Machine Learning Lab, Technical University of Darmstadt, Darmstadt, Germany","institution_ids":["https://openalex.org/I31512782"]},{"raw_affiliation_string":"Hessian Center for Artificial Intelligence (hessian.AI), Darmstadt, Germany","institution_ids":["https://openalex.org/I4392021234"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5009731204","display_name":"Johannes Czech","orcid":"https://orcid.org/0000-0002-9568-8965"},"institutions":[{"id":"https://openalex.org/I31512782","display_name":"Technische Universit\u00e4t Darmstadt","ror":"https://ror.org/05n911h24","country_code":"DE","type":"education","lineage":["https://openalex.org/I31512782"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Johannes Czech","raw_affiliation_strings":["Artificial Intelligence and Machine Learning Lab, Technical University of Darmstadt, Darmstadt, Germany"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Artificial Intelligence and Machine Learning Lab, Technical University of Darmstadt, Darmstadt, Germany","institution_ids":["https://openalex.org/I31512782"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5037636074","display_name":"Kristian Kersting","orcid":"https://orcid.org/0000-0002-2873-9152"},"institutions":[{"id":"https://openalex.org/I31512782","display_name":"Technische Universit\u00e4t Darmstadt","ror":"https://ror.org/05n911h24","country_code":"DE","type":"education","lineage":["https://openalex.org/I31512782"]},{"id":"https://openalex.org/I4392021234","display_name":"Hessian Center for Artificial Intelligence","ror":"https://ror.org/014ybqb54","country_code":"DE","type":"facility","lineage":["https://openalex.org/I31512782","https://openalex.org/I4392021234"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Kristian Kersting","raw_affiliation_strings":["Artificial Intelligence and Machine Learning Lab, Technical University of Darmstadt, Darmstadt, Germany","Centre for Cognitive Science, Technical University of Darmstadt, Darmstadt, Germany","Hessian Center for Artificial Intelligence (hessian.AI), Darmstadt, Germany"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Artificial Intelligence and Machine Learning Lab, Technical University of Darmstadt, Darmstadt, Germany","institution_ids":["https://openalex.org/I31512782"]},{"raw_affiliation_string":"Centre for Cognitive Science, Technical University of Darmstadt, Darmstadt, Germany","institution_ids":["https://openalex.org/I31512782"]},{"raw_affiliation_string":"Hessian Center for Artificial Intelligence (hessian.AI), Darmstadt, Germany","institution_ids":["https://openalex.org/I4392021234"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5036345046"],"corresponding_institution_ids":["https://openalex.org/I31512782","https://openalex.org/I4392021234"],"apc_list":{"value":1150,"currency":"USD","value_usd":1150},"apc_paid":{"value":1999,"currency":"EUR","value_usd":2155},"fwci":0.6401,"has_fulltext":true,"cited_by_count":4,"citation_normalized_percentile":{"value":0.72330795,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":97},"biblio":{"volume":"6","issue":null,"first_page":"1014561","last_page":"1014561"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11574","display_name":"Artificial Intelligence in Games","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"}},"topics":[{"id":"https://openalex.org/T11574","display_name":"Artificial Intelligence in Games","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/T10462","display_name":"Reinforcement Learning in Robotics","score":0.9966999888420105,"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":0.9902999997138977,"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/oracle","display_name":"Oracle","score":0.7868983745574951},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7700710892677307},{"id":"https://openalex.org/keywords/reinforcement-learning","display_name":"Reinforcement learning","score":0.7692317962646484},{"id":"https://openalex.org/keywords/perfect-information","display_name":"Perfect information","score":0.7346735000610352},{"id":"https://openalex.org/keywords/heuristics","display_name":"Heuristics","score":0.5591880083084106},{"id":"https://openalex.org/keywords/heuristic","display_name":"Heuristic","score":0.5238057374954224},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.49114367365837097},{"id":"https://openalex.org/keywords/imperfect","display_name":"Imperfect","score":0.4753384590148926},{"id":"https://openalex.org/keywords/pipeline","display_name":"Pipeline (software)","score":0.475103497505188},{"id":"https://openalex.org/keywords/monte-carlo-tree-search","display_name":"Monte Carlo tree search","score":0.4739803671836853},{"id":"https://openalex.org/keywords/domain","display_name":"Domain (mathematical analysis)","score":0.4554348886013031},{"id":"https://openalex.org/keywords/convergence","display_name":"Convergence (economics)","score":0.4118522107601166},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.41011175513267517},{"id":"https://openalex.org/keywords/theoretical-computer-science","display_name":"Theoretical computer science","score":0.34034815430641174},{"id":"https://openalex.org/keywords/monte-carlo-method","display_name":"Monte Carlo method","score":0.23781698942184448},{"id":"https://openalex.org/keywords/mathematical-economics","display_name":"Mathematical economics","score":0.13244450092315674},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.1255871057510376}],"concepts":[{"id":"https://openalex.org/C55166926","wikidata":"https://www.wikidata.org/wiki/Q2892946","display_name":"Oracle","level":2,"score":0.7868983745574951},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7700710892677307},{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.7692317962646484},{"id":"https://openalex.org/C123676819","wikidata":"https://www.wikidata.org/wiki/Q1074338","display_name":"Perfect information","level":2,"score":0.7346735000610352},{"id":"https://openalex.org/C127705205","wikidata":"https://www.wikidata.org/wiki/Q5748245","display_name":"Heuristics","level":2,"score":0.5591880083084106},{"id":"https://openalex.org/C173801870","wikidata":"https://www.wikidata.org/wiki/Q201413","display_name":"Heuristic","level":2,"score":0.5238057374954224},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.49114367365837097},{"id":"https://openalex.org/C2780310539","wikidata":"https://www.wikidata.org/wiki/Q12547192","display_name":"Imperfect","level":2,"score":0.4753384590148926},{"id":"https://openalex.org/C43521106","wikidata":"https://www.wikidata.org/wiki/Q2165493","display_name":"Pipeline (software)","level":2,"score":0.475103497505188},{"id":"https://openalex.org/C46149586","wikidata":"https://www.wikidata.org/wiki/Q11785332","display_name":"Monte Carlo tree search","level":3,"score":0.4739803671836853},{"id":"https://openalex.org/C36503486","wikidata":"https://www.wikidata.org/wiki/Q11235244","display_name":"Domain (mathematical analysis)","level":2,"score":0.4554348886013031},{"id":"https://openalex.org/C2777303404","wikidata":"https://www.wikidata.org/wiki/Q759757","display_name":"Convergence (economics)","level":2,"score":0.4118522107601166},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.41011175513267517},{"id":"https://openalex.org/C80444323","wikidata":"https://www.wikidata.org/wiki/Q2878974","display_name":"Theoretical computer science","level":1,"score":0.34034815430641174},{"id":"https://openalex.org/C19499675","wikidata":"https://www.wikidata.org/wiki/Q232207","display_name":"Monte Carlo method","level":2,"score":0.23781698942184448},{"id":"https://openalex.org/C144237770","wikidata":"https://www.wikidata.org/wiki/Q747534","display_name":"Mathematical economics","level":1,"score":0.13244450092315674},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.1255871057510376},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"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/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","level":0,"score":0.0},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","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/C115903868","wikidata":"https://www.wikidata.org/wiki/Q80993","display_name":"Software engineering","level":1,"score":0.0},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.0},{"id":"https://openalex.org/C50522688","wikidata":"https://www.wikidata.org/wiki/Q189833","display_name":"Economic growth","level":1,"score":0.0},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.0}],"mesh":[],"locations_count":8,"locations":[{"id":"doi:10.3389/frai.2023.1014561","is_oa":true,"landing_page_url":"https://doi.org/10.3389/frai.2023.1014561","pdf_url":"https://www.frontiersin.org/articles/10.3389/frai.2023.1014561/pdf","source":{"id":"https://openalex.org/S4210197006","display_name":"Frontiers in Artificial Intelligence","issn_l":"2624-8212","issn":["2624-8212"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310320527","host_organization_name":"Frontiers Media","host_organization_lineage":["https://openalex.org/P4310320527"],"host_organization_lineage_names":["Frontiers Media"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Frontiers in Artificial Intelligence","raw_type":"journal-article"},{"id":"pmid:37251273","is_oa":false,"landing_page_url":"https://pubmed.ncbi.nlm.nih.gov/37251273","pdf_url":null,"source":{"id":"https://openalex.org/S4306525036","display_name":"PubMed","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I1299303238","host_organization_name":"National Institutes of Health","host_organization_lineage":["https://openalex.org/I1299303238"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Frontiers in artificial intelligence","raw_type":null},{"id":"pmh:oai:pubmedcentral.nih.gov:10213697","is_oa":true,"landing_page_url":"https://www.ncbi.nlm.nih.gov/pmc/articles/10213697","pdf_url":"https://pmc.ncbi.nlm.nih.gov/articles/PMC10213697/pdf/frai-06-1014561.pdf","source":{"id":"https://openalex.org/S2764455111","display_name":"PubMed Central","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I1299303238","host_organization_name":"National Institutes of Health","host_organization_lineage":["https://openalex.org/I1299303238"],"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":"Front Artif Intell","raw_type":"Text"},{"id":"pmh:oai:doaj.org/article:a4162a50373341c681131cbdecb4e585","is_oa":true,"landing_page_url":"https://doaj.org/article/a4162a50373341c681131cbdecb4e585","pdf_url":null,"source":{"id":"https://openalex.org/S4306401280","display_name":"DOAJ (DOAJ: Directory of Open Access Journals)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by-sa","license_id":"https://openalex.org/licenses/cc-by-sa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Frontiers in Artificial Intelligence, Vol 6 (2023)","raw_type":"article"},{"id":"pmh:oai:tubiblio.ulb.tu-darmstadt.de:138055","is_oa":true,"landing_page_url":"https://tuprints.ulb.tu-darmstadt.de/24064","pdf_url":null,"source":{"id":"https://openalex.org/S4377196390","display_name":"TUbilio (Technical University of Darmstadt)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I31512782","host_organization_name":"Technische Universit\u00e4t Darmstadt","host_organization_lineage":["https://openalex.org/I31512782"],"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":"","raw_type":"Artikel"},{"id":"pmh:oai:tubiblio.ulb.tu-darmstadt.de:147878","is_oa":false,"landing_page_url":"http://tubiblio.ulb.tu-darmstadt.de/147878/","pdf_url":null,"source":{"id":"https://openalex.org/S4377196390","display_name":"TUbilio (Technical University of Darmstadt)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I31512782","host_organization_name":"Technische Universit\u00e4t Darmstadt","host_organization_lineage":["https://openalex.org/I31512782"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"Artikel"},{"id":"pmh:oai:tuprints.ulb.tu-darmstadt.de:24064","is_oa":true,"landing_page_url":"https://tuprints.ulb.tu-darmstadt.de/24064/10/frai-06-1014561.pdf","pdf_url":null,"source":{"id":"https://openalex.org/S4306401590","display_name":"Technischen Universit\u00e4t Darmstadt","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I31512782","host_organization_name":"Technische Universit\u00e4t Darmstadt","host_organization_lineage":["https://openalex.org/I31512782"],"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":"","raw_type":"info:eu-repo/semantics/article"},{"id":"doi:10.26083/tuprints-00024064","is_oa":true,"landing_page_url":"https://doi.org/10.26083/tuprints-00024064","pdf_url":null,"source":{"id":"https://openalex.org/S7407051655","display_name":"TUprints","issn_l":null,"issn":[],"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":null,"is_accepted":false,"is_published":null,"raw_source_name":null,"raw_type":"article-journal"}],"best_oa_location":{"id":"doi:10.3389/frai.2023.1014561","is_oa":true,"landing_page_url":"https://doi.org/10.3389/frai.2023.1014561","pdf_url":"https://www.frontiersin.org/articles/10.3389/frai.2023.1014561/pdf","source":{"id":"https://openalex.org/S4210197006","display_name":"Frontiers in Artificial Intelligence","issn_l":"2624-8212","issn":["2624-8212"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310320527","host_organization_name":"Frontiers Media","host_organization_lineage":["https://openalex.org/P4310320527"],"host_organization_lineage_names":["Frontiers Media"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Frontiers in Artificial Intelligence","raw_type":"journal-article"},"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/16","display_name":"Peace, Justice and strong institutions","score":0.5699999928474426}],"awards":[],"funders":[{"id":"https://openalex.org/F4320321961","display_name":"Hessisches Ministerium f\u00fcr Wissenschaft und Kunst","ror":"https://ror.org/00zd5gr55"}],"has_content":{"grobid_xml":false,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4378746517.pdf"},"referenced_works_count":43,"referenced_works":["https://openalex.org/W177869364","https://openalex.org/W1543187661","https://openalex.org/W1646839507","https://openalex.org/W1922759182","https://openalex.org/W1977989560","https://openalex.org/W1992679782","https://openalex.org/W2029757490","https://openalex.org/W2108234087","https://openalex.org/W2113228754","https://openalex.org/W2144274908","https://openalex.org/W2145224651","https://openalex.org/W2145339207","https://openalex.org/W2257979135","https://openalex.org/W2757711011","https://openalex.org/W2766447205","https://openalex.org/W2902907165","https://openalex.org/W2960876848","https://openalex.org/W2964164283","https://openalex.org/W2967026363","https://openalex.org/W2969287672","https://openalex.org/W2982316857","https://openalex.org/W2996037775","https://openalex.org/W3023265437","https://openalex.org/W3044994704","https://openalex.org/W3106034413","https://openalex.org/W4236965008","https://openalex.org/W4287757305","https://openalex.org/W4310705874","https://openalex.org/W4321428174","https://openalex.org/W6636578284","https://openalex.org/W6675509861","https://openalex.org/W6677972780","https://openalex.org/W6681187623","https://openalex.org/W6684973485","https://openalex.org/W6696767378","https://openalex.org/W6714094001","https://openalex.org/W6728250325","https://openalex.org/W6743367460","https://openalex.org/W6743731764","https://openalex.org/W6749781174","https://openalex.org/W6755963907","https://openalex.org/W6780812528","https://openalex.org/W6781244629"],"related_works":["https://openalex.org/W2360321812","https://openalex.org/W2395295193","https://openalex.org/W3122057932","https://openalex.org/W2909859691","https://openalex.org/W2113798763","https://openalex.org/W3088364074","https://openalex.org/W2004230228","https://openalex.org/W2610227658","https://openalex.org/W2900431508","https://openalex.org/W2145796981"],"abstract_inverted_index":{"In":[0],"recent":[1],"years,":[2],"deep":[3],"neural":[4],"networks":[5],"for":[6,39,69,84,111],"strategy":[7],"games":[8,29,70,112,123],"have":[9,23,35],"made":[10],"significant":[11],"progress.":[12],"AlphaZero-like":[13],"frameworks":[14],"which":[15,106],"combine":[16],"Monte-Carlo":[17],"tree":[18],"search":[19],"with":[20,30,71,113,183],"reinforcement":[21,102],"learning":[22,119],"been":[24,37],"successfully":[25],"applied":[26],"to":[27,53,174],"numerous":[28],"perfect":[31],"information.":[32,115],"However,":[33],"they":[34,64],"not":[36,158],"developed":[38],"domains":[40],"where":[41],"uncertainty":[42],"and":[43,46,61,125,127,176,194],"unknowns":[44],"abound,":[45],"are":[47,65],"therefore":[48],"often":[49],"considered":[50],"unsuitable":[51],"due":[52],"imperfect":[54,72,114],"observations.":[55],"Here,":[56],"we":[57,94],"challenge":[58],"this":[59,92,200],"view":[60],"argue":[62],"that":[63,129],"a":[66,96,132,138],"viable":[67],"alternative":[68],"information-a":[73],"domain":[74],"currently":[75],"dominated":[76],"by":[77],"heuristic":[78],"approaches":[79,198],"or":[80,165],"methods":[81],"explicitly":[82],"designed":[83],"hidden":[85],"information,":[86],"such":[87],"as":[88],"oracle-based":[89,177],"techniques.":[90],"To":[91],"end,":[93],"introduce":[95],"novel":[97],"algorithm":[98],"based":[99],"solely":[100],"on":[101,121],"learning,":[103],"called":[104],"AlphaZe\u2217\u2217,":[105],"is":[107,131,192],"an":[108],"AlphaZero-based":[109],"framework":[110],"We":[116],"examine":[117],"its":[118],"convergence":[120],"the":[122,167],"Stratego":[124,148],"DarkHex":[126],"show":[128],"it":[130,141],"surprisingly":[133],"strong":[134],"baseline,":[135],"while":[136,157],"using":[137],"model-based":[139],"approach:":[140],"achieves":[142],"similar":[143],"win":[144],"rates":[145],"against":[146,163],"other":[147,197],"bots":[149],"like":[150],"Pipeline":[151],"Policy":[152],"Space":[153],"Response":[154],"Oracle":[155],"(P2SRO),":[156],"winning":[159],"in":[160,199],"direct":[161],"comparison":[162],"P2SRO":[164],"reaching":[166],"much":[168],"stronger":[169],"numbers":[170],"of":[171],"DeepNash.":[172],"Compared":[173],"heuristics":[175],"approaches,":[178],"AlphaZe\u2217\u2217":[179],"can":[180],"easily":[181],"deal":[182],"rule":[184],"changes,":[185],"e.g.,":[186],"when":[187],"more":[188],"information":[189],"than":[190],"usual":[191],"given,":[193],"drastically":[195],"outperforms":[196],"respect.":[201]},"counts_by_year":[{"year":2024,"cited_by_count":3},{"year":2023,"cited_by_count":1}],"updated_date":"2026-07-02T09:51:11.867554","created_date":"2025-10-10T00:00:00"}
