{"id":"https://openalex.org/W7138356815","doi":"https://doi.org/10.1609/aaai.v40i20.38784","title":"Faster Game Solving via Hyperparameter Schedules","display_name":"Faster Game Solving via Hyperparameter Schedules","publication_year":2026,"publication_date":"2026-03-14","ids":{"openalex":"https://openalex.org/W7138356815","doi":"https://doi.org/10.1609/aaai.v40i20.38784"},"language":null,"primary_location":{"id":"doi:10.1609/aaai.v40i20.38784","is_oa":true,"landing_page_url":"https://doi.org/10.1609/aaai.v40i20.38784","pdf_url":"https://ojs.aaai.org/index.php/AAAI/article/download/38784/42746","source":{"id":"https://openalex.org/S4210191458","display_name":"Proceedings of the AAAI Conference on Artificial Intelligence","issn_l":"2159-5399","issn":["2159-5399","2374-3468"],"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/P4310320058","host_organization_name":"Association for the Advancement of Artificial Intelligence","host_organization_lineage":["https://openalex.org/P4310320058"],"host_organization_lineage_names":["Association for the Advancement of Artificial Intelligence"],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the AAAI Conference on Artificial Intelligence","raw_type":"journal-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"diamond","oa_url":"https://ojs.aaai.org/index.php/AAAI/article/download/38784/42746","any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":null,"display_name":"Naifeng Zhang","orcid":null},"institutions":[{"id":"https://openalex.org/I74973139","display_name":"Carnegie Mellon University","ror":"https://ror.org/05x2bcf33","country_code":"US","type":"education","lineage":["https://openalex.org/I74973139"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Naifeng Zhang","raw_affiliation_strings":["Carnegie Mellon University"],"affiliations":[{"raw_affiliation_string":"Carnegie Mellon University","institution_ids":["https://openalex.org/I74973139"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Stephen Marcus McAleer","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Stephen Marcus McAleer","raw_affiliation_strings":["Anthropic"],"affiliations":[{"raw_affiliation_string":"Anthropic","institution_ids":[]}]},{"author_position":"last","author":{"id":null,"display_name":"Tuomas Sandholm","orcid":null},"institutions":[{"id":"https://openalex.org/I74973139","display_name":"Carnegie Mellon University","ror":"https://ror.org/05x2bcf33","country_code":"US","type":"education","lineage":["https://openalex.org/I74973139"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Tuomas Sandholm","raw_affiliation_strings":["Carnegie Mellon University\nStrategy Robot, Inc.\nStrategic Machine, Inc.\nOptimized Markets, Inc"],"affiliations":[{"raw_affiliation_string":"Carnegie Mellon University\nStrategy Robot, Inc.\nStrategic Machine, Inc.\nOptimized Markets, Inc","institution_ids":["https://openalex.org/I74973139"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I74973139"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":true,"cited_by_count":0,"citation_normalized_percentile":{"value":0.57226981,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":"40","issue":"20","first_page":"17319","last_page":"17326"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11574","display_name":"Artificial Intelligence in Games","score":0.705299973487854,"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":0.705299973487854,"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":0.11739999800920486,"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"}},{"id":"https://openalex.org/T10462","display_name":"Reinforcement Learning in Robotics","score":0.030700000002980232,"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/discounting","display_name":"Discounting","score":0.848800003528595},{"id":"https://openalex.org/keywords/regret","display_name":"Regret","score":0.715399980545044},{"id":"https://openalex.org/keywords/iterated-function","display_name":"Iterated function","score":0.6208999752998352},{"id":"https://openalex.org/keywords/convergence","display_name":"Convergence (economics)","score":0.5986999869346619},{"id":"https://openalex.org/keywords/nash-equilibrium","display_name":"Nash equilibrium","score":0.5228999853134155},{"id":"https://openalex.org/keywords/hyperparameter","display_name":"Hyperparameter","score":0.4968000054359436},{"id":"https://openalex.org/keywords/class","display_name":"Class (philosophy)","score":0.4569999873638153},{"id":"https://openalex.org/keywords/minification","display_name":"Minification","score":0.4244999885559082},{"id":"https://openalex.org/keywords/temporal-discounting","display_name":"Temporal discounting","score":0.3767000138759613}],"concepts":[{"id":"https://openalex.org/C6177178","wikidata":"https://www.wikidata.org/wiki/Q10998070","display_name":"Discounting","level":2,"score":0.848800003528595},{"id":"https://openalex.org/C50817715","wikidata":"https://www.wikidata.org/wiki/Q79895177","display_name":"Regret","level":2,"score":0.715399980545044},{"id":"https://openalex.org/C140479938","wikidata":"https://www.wikidata.org/wiki/Q5254619","display_name":"Iterated function","level":2,"score":0.6208999752998352},{"id":"https://openalex.org/C2777303404","wikidata":"https://www.wikidata.org/wiki/Q759757","display_name":"Convergence (economics)","level":2,"score":0.5986999869346619},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5849000215530396},{"id":"https://openalex.org/C126255220","wikidata":"https://www.wikidata.org/wiki/Q141495","display_name":"Mathematical optimization","level":1,"score":0.5303999781608582},{"id":"https://openalex.org/C46814582","wikidata":"https://www.wikidata.org/wiki/Q23389","display_name":"Nash equilibrium","level":2,"score":0.5228999853134155},{"id":"https://openalex.org/C8642999","wikidata":"https://www.wikidata.org/wiki/Q4171168","display_name":"Hyperparameter","level":2,"score":0.4968000054359436},{"id":"https://openalex.org/C2777212361","wikidata":"https://www.wikidata.org/wiki/Q5127848","display_name":"Class (philosophy)","level":2,"score":0.4569999873638153},{"id":"https://openalex.org/C147764199","wikidata":"https://www.wikidata.org/wiki/Q6865248","display_name":"Minification","level":2,"score":0.4244999885559082},{"id":"https://openalex.org/C2777893452","wikidata":"https://www.wikidata.org/wiki/Q186412","display_name":"Temporal discounting","level":3,"score":0.3767000138759613},{"id":"https://openalex.org/C48103436","wikidata":"https://www.wikidata.org/wiki/Q599031","display_name":"State (computer science)","level":2,"score":0.373199999332428},{"id":"https://openalex.org/C127729010","wikidata":"https://www.wikidata.org/wiki/Q60165","display_name":"Dynamic inconsistency","level":2,"score":0.3686000108718872},{"id":"https://openalex.org/C178562925","wikidata":"https://www.wikidata.org/wiki/Q186412","display_name":"Time preference","level":2,"score":0.3458000123500824},{"id":"https://openalex.org/C57869625","wikidata":"https://www.wikidata.org/wiki/Q1783502","display_name":"Rate of convergence","level":3,"score":0.33959999680519104},{"id":"https://openalex.org/C106189395","wikidata":"https://www.wikidata.org/wiki/Q176789","display_name":"Markov decision process","level":3,"score":0.3050000071525574},{"id":"https://openalex.org/C148220186","wikidata":"https://www.wikidata.org/wiki/Q7111912","display_name":"Outcome (game theory)","level":2,"score":0.29989999532699585},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.290800005197525},{"id":"https://openalex.org/C37404715","wikidata":"https://www.wikidata.org/wiki/Q380679","display_name":"Dynamic programming","level":2,"score":0.2847999930381775},{"id":"https://openalex.org/C177148314","wikidata":"https://www.wikidata.org/wiki/Q170084","display_name":"Generalization","level":2,"score":0.2799000144004822},{"id":"https://openalex.org/C61445026","wikidata":"https://www.wikidata.org/wiki/Q217608","display_name":"Fixed point","level":2,"score":0.25870001316070557},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.257999986410141},{"id":"https://openalex.org/C159886148","wikidata":"https://www.wikidata.org/wiki/Q176645","display_name":"Markov process","level":2,"score":0.2567000091075897},{"id":"https://openalex.org/C2994109249","wikidata":"https://www.wikidata.org/wiki/Q186412","display_name":"Delay discounting","level":3,"score":0.25040000677108765},{"id":"https://openalex.org/C147297375","wikidata":"https://www.wikidata.org/wiki/Q6674930","display_name":"Look-ahead","level":2,"score":0.2502000033855438}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1609/aaai.v40i20.38784","is_oa":true,"landing_page_url":"https://doi.org/10.1609/aaai.v40i20.38784","pdf_url":"https://ojs.aaai.org/index.php/AAAI/article/download/38784/42746","source":{"id":"https://openalex.org/S4210191458","display_name":"Proceedings of the AAAI Conference on Artificial Intelligence","issn_l":"2159-5399","issn":["2159-5399","2374-3468"],"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/P4310320058","host_organization_name":"Association for the Advancement of Artificial Intelligence","host_organization_lineage":["https://openalex.org/P4310320058"],"host_organization_lineage_names":["Association for the Advancement of Artificial Intelligence"],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the AAAI Conference on Artificial Intelligence","raw_type":"journal-article"}],"best_oa_location":{"id":"doi:10.1609/aaai.v40i20.38784","is_oa":true,"landing_page_url":"https://doi.org/10.1609/aaai.v40i20.38784","pdf_url":"https://ojs.aaai.org/index.php/AAAI/article/download/38784/42746","source":{"id":"https://openalex.org/S4210191458","display_name":"Proceedings of the AAAI Conference on Artificial Intelligence","issn_l":"2159-5399","issn":["2159-5399","2374-3468"],"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/P4310320058","host_organization_name":"Association for the Advancement of Artificial Intelligence","host_organization_lineage":["https://openalex.org/P4310320058"],"host_organization_lineage_names":["Association for the Advancement of Artificial Intelligence"],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the AAAI Conference on Artificial Intelligence","raw_type":"journal-article"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W7138356815.pdf","grobid_xml":"https://content.openalex.org/works/W7138356815.grobid-xml"},"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"Counterfactual":[0],"regret":[1],"minimization":[2],"(CFR)":[3],"algorithms":[4],"are":[5],"a":[6,24,59,91,122,162],"foundational":[7],"class":[8],"of":[9,19,80,125,165],"methods":[10],"for":[11,168],"solving":[12,169],"imperfect-information":[13],"games,":[14],"with":[15,58,120],"the":[16,42,78,166],"time":[17],"average":[18],"their":[20],"iterates":[21],"converging":[22],"to":[23,73,111,116,141],"Nash":[25],"equilibrium":[26],"in":[27,149],"two-player":[28,170],"zero-sum":[29,171],"games.":[30,172],"Prior":[31],"state-of-the-art":[32],"variants,":[33],"Discounted":[34],"CFR":[35,53,99],"(DCFR)":[36],"and":[37,108,152],"Predictive":[38],"CFR+":[39],"(PCFR+),":[40],"achieved":[41],"fastest":[43],"known":[44],"practical":[45],"performance":[46],"by":[47],"improving":[48],"convergence":[49,119],"rates":[50],"over":[51,101],"vanilla":[52],"through":[54],"discounting":[55,61,71,100],"early":[56,106],"iterations":[57],"fixed":[60],"scheme.":[62],"More":[63],"recently,":[64],"Dynamic":[65],"DCFR":[66],"(DDCFR)":[67],"introduced":[68],"agent-learned":[69],"dynamic":[70],"schemes":[72],"further":[74],"accelerate":[75],"convergence,":[76],"at":[77],"cost":[79],"increased":[81],"complexity.":[82],"To":[83],"address":[84],"this,":[85],"we":[86],"propose":[87],"Hyperparameter":[88],"Schedules":[89],"(HSs),":[90],"remarkably":[92],"simple,":[93],"training-free":[94],"framework":[95],"that":[96,130],"dynamically":[97],"adjusts":[98],"time.":[102],"HSs":[103,131],"aggressively":[104],"downweight":[105],"updates":[107],"gradually":[109],"transition":[110],"trusting":[112],"late-stage":[113],"strategies,":[114],"leading":[115],"substantially":[117],"faster":[118],"only":[121],"few":[123],"lines":[124],"code":[126],"modifications.":[127],"We":[128],"show":[129],"derived":[132],"from":[133],"just":[134],"three":[135],"small":[136],"extensive-form":[137,151],"games":[138,144],"generalize":[139],"effectively":[140],"17":[142],"diverse":[143],"(including":[145],"large-scale":[146],"realistic":[147],"poker)":[148],"both":[150],"normal-form":[153],"settings,":[154],"without":[155],"any":[156],"game-specific":[157],"tuning.":[158],"Our":[159],"method":[160],"establishes":[161],"new":[163],"state":[164],"art":[167]},"counts_by_year":[],"updated_date":"2026-03-20T20:47:17.329874","created_date":"2026-02-12T00:00:00"}