{"id":"https://openalex.org/W4407184530","doi":"https://doi.org/10.48550/arxiv.2502.01672","title":"Doubly Robust Monte Carlo Tree Search","display_name":"Doubly Robust Monte Carlo Tree Search","publication_year":2025,"publication_date":"2025-02-01","ids":{"openalex":"https://openalex.org/W4407184530","doi":"https://doi.org/10.48550/arxiv.2502.01672"},"language":"en","primary_location":{"id":"pmh:oai:arXiv.org:2502.01672","doi":null,"is_oa":true,"landing_page_url":"http://arxiv.org/abs/2502.01672","pdf_url":"https://arxiv.org/pdf/2502.01672","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":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},"volume":null,"type":"preprint","indexed_in":["arxiv","datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2502.01672","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":null,"display_name":"Liu, Manqing","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Liu, Manqing","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5077007622","display_name":"Andrew L. Beam","orcid":"https://orcid.org/0000-0002-6657-2787","observed_orcids":["https://orcid.org/0000-0002-6657-2787"]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Beam, Andrew L.","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":0,"corresponding_author_ids":[],"corresponding_institution_ids":[],"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":0.9247999787330627,"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":0.9247999787330627,"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":0.06949999928474426,"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":0.0017000000225380063,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/doubly-robust-estimation","display_name":"doubly robust estimation","score":0.8370000123977661},{"id":"https://openalex.org/keywords/off-policy-evaluation","display_name":"off-policy evaluation","score":0.8309999704360962},{"id":"https://openalex.org/keywords/monte-carlo-tree-search","display_name":"Monte Carlo tree search","score":0.8820000290870667},{"id":"https://openalex.org/keywords/sample-efficiency","display_name":"sample efficiency","score":0.9490000009536743},{"id":"https://openalex.org/keywords/variance-reduction","display_name":"variance reduction","score":0.8180000185966492},{"id":"https://openalex.org/keywords/tic-tac-toe","display_name":"Tic-Tac-Toe","score":0.8769999742507935},{"id":"https://openalex.org/keywords/language-models","display_name":"language models","score":0.4129999876022339},{"id":"https://openalex.org/keywords/decision-making-under-uncertainty","display_name":"decision making under uncertainty","score":0.5130000114440918}],"concepts":[{"id":"https://openalex.org/C19499675","wikidata":"https://www.wikidata.org/wiki/Q232207","display_name":"Monte Carlo method","level":2,"score":0.7463672161102295},{"id":"https://openalex.org/C46149586","wikidata":"https://www.wikidata.org/wiki/Q11785332","display_name":"Monte Carlo tree search","level":3,"score":0.6643059849739075},{"id":"https://openalex.org/C121864883","wikidata":"https://www.wikidata.org/wiki/Q677916","display_name":"Statistical physics","level":1,"score":0.417923241853714},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.3825533986091614},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.28069743514060974},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.2378188967704773},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.2104588747024536}],"mesh":[],"locations_count":2,"locations":[{"id":"pmh:oai:arXiv.org:2502.01672","doi":null,"is_oa":true,"landing_page_url":"http://arxiv.org/abs/2502.01672","pdf_url":"https://arxiv.org/pdf/2502.01672","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":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},{"id":"doi:10.48550/arxiv.2502.01672","doi":"https://doi.org/10.48550/arxiv.2502.01672","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2502.01672","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":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":null,"is_accepted":false,"is_published":null,"raw_source_name":null,"raw_type":"Preprint"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2502.01672","doi":null,"is_oa":true,"landing_page_url":"http://arxiv.org/abs/2502.01672","pdf_url":"https://arxiv.org/pdf/2502.01672","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":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},"sustainable_development_goals":[],"sustainable_development_goals_aurora":[],"study_designs":[],"awards":[],"funders":[],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4407184530.pdf","grobid_xml":"https://content.openalex.org/works/W4407184530.grobid-xml"},"referenced_works_count":0,"referenced_works":[],"related_works":["https://openalex.org/W4391375266","https://openalex.org/W2899084033","https://openalex.org/W2748952813","https://openalex.org/W2571592646","https://openalex.org/W4247855592","https://openalex.org/W2740304877","https://openalex.org/W2978000411","https://openalex.org/W2390279801","https://openalex.org/W4391913857","https://openalex.org/W2005266888"],"abstract_inverted_index":{"We":[0],"present":[1],"Doubly":[2,14],"Robust":[3,15],"Monte":[4,20],"Carlo":[5,21],"Tree":[6,22],"Search":[7,23],"(DR-MCTS),":[8],"a":[9,38,86,99,128],"novel":[10],"algorithm":[11],"that":[12,41,112],"integrates":[13],"(DR)":[16],"off-policy":[17],"estimation":[18],"into":[19],"(MCTS)":[24],"to":[25,85],"enhance":[26],"sample":[27,116,144],"efficiency":[28,145],"and":[29,53,63],"decision":[30],"quality":[31],"in":[32,61,139],"complex":[33],"environments.":[34],"Our":[35,108],"approach":[36],"introduces":[37],"hybrid":[39],"estimator":[40],"combines":[42],"MCTS":[43,121],"rollouts":[44],"with":[45,122],"DR":[46],"estimation,":[47],"offering":[48],"theoretical":[49],"guarantees":[50],"of":[51],"unbiasedness":[52],"variance":[54],"reduction":[55],"under":[56],"specified":[57],"conditions.":[58],"Empirical":[59],"evaluations":[60],"Tic-Tac-Toe":[62],"the":[64],"partially":[65],"observable":[66],"VirtualHome":[67,95],"environment":[68],"demonstrate":[69],"DR-MCTS's":[70,134],"superior":[71],"performance":[72],"over":[73],"standard":[74,91,106,120],"MCTS.":[75,92,107],"In":[76,93],"Tic-Tac-Toe,":[77],"DR-MCTS":[78,97,113],"achieves":[79],"an":[80],"88%":[81],"win":[82,88],"rate":[83,89,102],"compared":[84],"10%":[87],"for":[90,105,136],"compound":[94],"tasks,":[96],"attains":[98],"20.7%":[100],"success":[101],"versus":[103],"10.3%":[104],"scaling":[109],"analysis":[110],"reveals":[111],"exhibits":[114],"better":[115],"efficiency,":[117],"notably":[118],"outperforming":[119],"larger":[123],"language":[124],"models":[125],"while":[126],"using":[127],"smaller":[129],"model.":[130],"These":[131],"results":[132],"underscore":[133],"potential":[135],"efficient":[137],"decision-making":[138],"complex,":[140],"real-world":[141],"scenarios":[142],"where":[143],"is":[146],"paramount.":[147]},"counts_by_year":[],"updated_date":"2026-08-26T07:47:46.906454","created_date":"2025-10-10T00:00:00"}