{"id":"https://openalex.org/W3132083418","doi":null,"title":"Divide-and-Conquer Monte Carlo Tree Search","display_name":"Divide-and-Conquer Monte Carlo Tree Search","publication_year":2021,"publication_date":"2021-05-04","ids":{"openalex":"https://openalex.org/W3132083418","mag":"3132083418"},"language":"en","primary_location":{"id":"mag:3132083418","doi":null,"is_oa":false,"landing_page_url":"https://openreview.net/pdf?id=Nj8EIrSu5O","pdf_url":null,"source":null,"license":null,"license_id":null,"version":null,"is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":null},"volume":null,"type":"article","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/A5014848044","display_name":"Giambattista Parascandolo","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I35440088","display_name":"ETH Zurich","ror":"https://ror.org/05a28rw58","country_code":"CH","type":"education","lineage":["https://openalex.org/I2799323385","https://openalex.org/I35440088"]}],"countries":["CH"],"is_corresponding":false,"raw_author_name":"Giambattista Parascandolo","raw_affiliation_strings":["Swiss Federal Institute of Technology"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Swiss Federal Institute of Technology","institution_ids":["https://openalex.org/I35440088"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5047352800","display_name":"Lars Buesing","orcid":"https://orcid.org/0000-0002-3258-3728","observed_orcids":["https://orcid.org/0000-0002-3258-3728"]},"institutions":[{"id":"https://openalex.org/I4210090411","display_name":"Google DeepMind (United Kingdom)","ror":"https://ror.org/00971b260","country_code":"GB","type":"company","lineage":["https://openalex.org/I4210090411","https://openalex.org/I4210128969"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Lars Buesing","raw_affiliation_strings":["DeepMind"],"raw_orcid":"https://orcid.org/0000-0002-3258-3728","affiliations":[{"raw_affiliation_string":"DeepMind","institution_ids":["https://openalex.org/I4210090411"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5080814522","display_name":"Josh Merel","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I4210090411","display_name":"Google DeepMind (United Kingdom)","ror":"https://ror.org/00971b260","country_code":"GB","type":"company","lineage":["https://openalex.org/I4210090411","https://openalex.org/I4210128969"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Josh Merel","raw_affiliation_strings":["DeepMind"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"DeepMind","institution_ids":["https://openalex.org/I4210090411"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5014567358","display_name":"Leonard Hasenclever","orcid":"https://orcid.org/0000-0003-1844-696X","observed_orcids":["https://orcid.org/0000-0003-1844-696X"]},"institutions":[{"id":"https://openalex.org/I4210090411","display_name":"Google DeepMind (United Kingdom)","ror":"https://ror.org/00971b260","country_code":"GB","type":"company","lineage":["https://openalex.org/I4210090411","https://openalex.org/I4210128969"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Leonard Hasenclever","raw_affiliation_strings":["DeepMind"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"DeepMind","institution_ids":["https://openalex.org/I4210090411"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5029807267","display_name":"John Aslanides","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I4210090411","display_name":"Google DeepMind (United Kingdom)","ror":"https://ror.org/00971b260","country_code":"GB","type":"company","lineage":["https://openalex.org/I4210090411","https://openalex.org/I4210128969"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"John Aslanides","raw_affiliation_strings":["DeepMind"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"DeepMind","institution_ids":["https://openalex.org/I4210090411"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5034507822","display_name":"Jessica B. Hamrick","orcid":"https://orcid.org/0000-0002-3860-0429","observed_orcids":["https://orcid.org/0000-0002-3860-0429"]},"institutions":[{"id":"https://openalex.org/I4210090411","display_name":"Google DeepMind (United Kingdom)","ror":"https://ror.org/00971b260","country_code":"GB","type":"company","lineage":["https://openalex.org/I4210090411","https://openalex.org/I4210128969"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Jessica B. Hamrick","raw_affiliation_strings":["DeepMind"],"raw_orcid":"https://orcid.org/0000-0002-3860-0429","affiliations":[{"raw_affiliation_string":"DeepMind","institution_ids":["https://openalex.org/I4210090411"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5062951341","display_name":"Nicolas Heess","orcid":"https://orcid.org/0000-0001-7876-9256","observed_orcids":["https://orcid.org/0000-0001-7876-9256"]},"institutions":[{"id":"https://openalex.org/I1291425158","display_name":"Google (United States)","ror":"https://ror.org/00njsd438","country_code":"US","type":"company","lineage":["https://openalex.org/I1291425158","https://openalex.org/I4210128969"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Nicolas Heess","raw_affiliation_strings":["Google,,,,,"],"raw_orcid":"https://orcid.org/0000-0001-7876-9256","affiliations":[{"raw_affiliation_string":"Google,,,,,","institution_ids":["https://openalex.org/I1291425158"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5078482673","display_name":"Alexander Neitz","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I4210135521","display_name":"Max Planck Institute for Intelligent Systems","ror":"https://ror.org/04fq9j139","country_code":"DE","type":"facility","lineage":["https://openalex.org/I149899117","https://openalex.org/I4210135521"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Alexander Neitz","raw_affiliation_strings":["Max-Planck-Institute for Intelligent Systems, Max-Planck Institute"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Max-Planck-Institute for Intelligent Systems, Max-Planck Institute","institution_ids":["https://openalex.org/I4210135521"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5005085749","display_name":"Th\u00e9ophane Weber","orcid":"https://orcid.org/0000-0001-6230-952X","observed_orcids":["https://orcid.org/0000-0001-6230-952X"]},"institutions":[{"id":"https://openalex.org/I1291425158","display_name":"Google (United States)","ror":"https://ror.org/00njsd438","country_code":"US","type":"company","lineage":["https://openalex.org/I1291425158","https://openalex.org/I4210128969"]},{"id":"https://openalex.org/I4210090411","display_name":"Google DeepMind (United Kingdom)","ror":"https://ror.org/00971b260","country_code":"GB","type":"company","lineage":["https://openalex.org/I4210090411","https://openalex.org/I4210128969"]}],"countries":["GB","US"],"is_corresponding":false,"raw_author_name":"Th\u00e9ophane Weber","raw_affiliation_strings":["Google DeepMind;"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Google DeepMind;","institution_ids":["https://openalex.org/I1291425158","https://openalex.org/I4210090411"]}]}],"institutions":[],"countries_distinct_count":4,"institutions_distinct_count":4,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.0,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"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/T10462","display_name":"Reinforcement Learning in Robotics","score":0.8413000106811523,"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":0.8413000106811523,"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/T10906","display_name":"AI-based Problem Solving and Planning","score":0.09640000015497208,"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":0.05939999967813492,"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/monte-carlo-tree-search","display_name":"Monte Carlo tree search","score":0.8199999928474426},{"id":"https://openalex.org/keywords/sequential-planning","display_name":"sequential planning","score":0.5270000100135803},{"id":"https://openalex.org/keywords/grid-world","display_name":"grid world","score":0.8109999895095825},{"id":"https://openalex.org/keywords/continuous-control","display_name":"continuous control","score":0.8009999990463257}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7167956829071045},{"id":"https://openalex.org/C46149586","wikidata":"https://www.wikidata.org/wiki/Q11785332","display_name":"Monte Carlo tree search","level":3,"score":0.6685107350349426},{"id":"https://openalex.org/C71559656","wikidata":"https://www.wikidata.org/wiki/Q671298","display_name":"Divide and conquer algorithms","level":2,"score":0.641486644744873},{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.5071277618408203},{"id":"https://openalex.org/C113174947","wikidata":"https://www.wikidata.org/wiki/Q2859736","display_name":"Tree (set theory)","level":2,"score":0.49701955914497375},{"id":"https://openalex.org/C42812","wikidata":"https://www.wikidata.org/wiki/Q1082910","display_name":"Partition (number theory)","level":2,"score":0.4357704520225525},{"id":"https://openalex.org/C126255220","wikidata":"https://www.wikidata.org/wiki/Q141495","display_name":"Mathematical optimization","level":1,"score":0.4287967085838318},{"id":"https://openalex.org/C2778112365","wikidata":"https://www.wikidata.org/wiki/Q3511065","display_name":"Sequence (biology)","level":2,"score":0.42398083209991455},{"id":"https://openalex.org/C19499675","wikidata":"https://www.wikidata.org/wiki/Q232207","display_name":"Monte Carlo method","level":2,"score":0.4234992563724518},{"id":"https://openalex.org/C2780598303","wikidata":"https://www.wikidata.org/wiki/Q65921492","display_name":"Flexibility (engineering)","level":2,"score":0.41041839122772217},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.31993815302848816},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.24076661467552185},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.17478466033935547},{"id":"https://openalex.org/C54355233","wikidata":"https://www.wikidata.org/wiki/Q7162","display_name":"Genetics","level":1,"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/C114614502","wikidata":"https://www.wikidata.org/wiki/Q76592","display_name":"Combinatorics","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/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"mag:3132083418","doi":null,"is_oa":false,"landing_page_url":"https://openreview.net/pdf?id=Nj8EIrSu5O","pdf_url":null,"source":null,"license":null,"license_id":null,"version":null,"is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":null}],"best_oa_location":null,"sustainable_development_goals":[],"study_designs":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":["https://openalex.org/W3019127492","https://openalex.org/W2141388186","https://openalex.org/W2397074156","https://openalex.org/W2744982099","https://openalex.org/W6991434418","https://openalex.org/W4416530355","https://openalex.org/W3022234704","https://openalex.org/W1821581985","https://openalex.org/W7212328577","https://openalex.org/W2407383140"],"abstract_inverted_index":{"Standard":[0],"planners":[1],"for":[2,45,103,140,154],"sequential":[3,20,167],"decision":[4],"making":[5],"(including":[6],"Monte":[7,98],"Carlo":[8,99],"planning,":[9],"tree":[10],"search,":[11],"dynamic":[12],"programming,":[13],"etc.)":[14],"are":[15,124],"constrained":[16],"by":[17,72,108],"an":[18,56,62,77],"implicit":[19],"planning":[21,95,162,176],"assumption:":[22],"The":[23,130],"order":[24,177],"in":[25,34,182,185,190],"which":[26,35,114],"a":[27,73,94,136],"plan":[28,107],"is":[29,31,37],"constructed":[30],"the":[32,46,86,89,105,117],"same":[33],"it":[36,84],"executed.":[38],"We":[39,92,169],"consider":[40],"alternatives":[41],"to":[42,88,160,179],"this":[43,172],"assumption":[44],"class":[47],"of":[48,55,76,80,110,135,145],"goal-directed":[49,64],"Reinforcement":[50],"Learning":[51],"(RL)":[52],"problems.":[53],"Instead":[54],"environment":[57],"transition":[58],"model,":[59],"we":[60],"assume":[61],"imperfect,":[63],"policy.":[65],"This":[66],"low-level":[67],"policy":[68],"can":[69],"be":[70],"improved":[71,180],"plan,":[74],"consisting":[75],"appropriate":[78,142],"sequence":[79],"sub-goals":[81,113],"that":[82,123,164,171],"guide":[83],"from":[85],"start":[87],"goal":[90],"state.":[91],"propose":[93],"algorithm,":[96],"Divide-and-Conquer":[97],"Tree":[100],"Search":[101],"(DC-MCTS),":[102],"approximating":[104],"optimal":[106],"means":[109],"proposing":[111],"intermediate":[112],"hierarchically":[115],"partition":[116],"initial":[118],"tasks":[119,147,184],"into":[120],"simpler":[121],"ones":[122],"then":[125],"solved":[126],"independently":[127],"and":[128],"recursively.":[129],"algorithm":[131],"critically":[132],"makes":[133],"use":[134],"learned":[137],"sub-goal":[138,156],"proposal":[139],"finding":[141],"partitions":[143],"trees":[144],"new":[146],"based":[148],"on":[149],"prior":[150],"experience.":[151],"Different":[152],"strategies":[153,163],"learning":[155],"proposals":[157],"give":[158],"rise":[159],"different":[161],"strictly":[165],"generalize":[166],"planning.":[168],"show":[170],"algorithmic":[173],"flexibility":[174],"over":[175],"leads":[178],"results":[181],"navigation":[183],"grid-worlds":[186],"as":[187,189],"well":[188],"challenging":[191],"continuous":[192],"control":[193],"environments.":[194]},"counts_by_year":[],"updated_date":"2025-11-06T04:12:42.849631","created_date":"2021-03-01T00:00:00"}