{"id":"https://openalex.org/W2985140959","doi":"https://doi.org/10.24963/ijcai.2020/332","title":"Generalized Mean Estimation in Monte-Carlo Tree Search","display_name":"Generalized Mean Estimation in Monte-Carlo Tree Search","publication_year":2020,"publication_date":"2020-07-01","ids":{"openalex":"https://openalex.org/W2985140959","doi":"https://doi.org/10.24963/ijcai.2020/332","mag":"2985140959"},"language":"en","primary_location":{"id":"doi:10.24963/ijcai.2020/332","is_oa":true,"landing_page_url":"https://doi.org/10.24963/ijcai.2020/332","pdf_url":"https://www.ijcai.org/proceedings/2020/0332.pdf","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the Twenty-Ninth International Joint Conference on Artificial Intelligence","raw_type":"proceedings-article"},"type":"preprint","indexed_in":["arxiv","crossref","datacite"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://www.ijcai.org/proceedings/2020/0332.pdf","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5061282536","display_name":"Tuan Dam","orcid":"https://orcid.org/0000-0001-7422-139X"},"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":"Tuan Dam","raw_affiliation_strings":["Department of Computer Science, Technische Universit\u00e4t Darmstadt, Germany","[Dept. of Computer Science, Technische Universit\u00e4t Darmstadt, Germany]"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Computer Science, Technische Universit\u00e4t Darmstadt, Germany","institution_ids":["https://openalex.org/I31512782"]},{"raw_affiliation_string":"[Dept. of Computer Science, Technische Universit\u00e4t Darmstadt, Germany]","institution_ids":["https://openalex.org/I31512782"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5066979765","display_name":"Pascal Klink","orcid":"https://orcid.org/0000-0001-5318-3785"},"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":"Pascal Klink","raw_affiliation_strings":["Department of Computer Science, Technische Universit\u00e4t Darmstadt, Germany","[Dept. of Computer Science, Technische Universit\u00e4t Darmstadt, Germany]"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Computer Science, Technische Universit\u00e4t Darmstadt, Germany","institution_ids":["https://openalex.org/I31512782"]},{"raw_affiliation_string":"[Dept. of Computer Science, Technische Universit\u00e4t Darmstadt, Germany]","institution_ids":["https://openalex.org/I31512782"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5063752250","display_name":"Carlo D\u2019Eramo","orcid":"https://orcid.org/0000-0003-2712-118X"},"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":"Carlo D'Eramo","raw_affiliation_strings":["Department of Computer Science, Technische Universit\u00e4t Darmstadt, Germany","[Dept. of Computer Science, Technische Universit\u00e4t Darmstadt, Germany]"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Computer Science, Technische Universit\u00e4t Darmstadt, Germany","institution_ids":["https://openalex.org/I31512782"]},{"raw_affiliation_string":"[Dept. of Computer Science, Technische Universit\u00e4t Darmstadt, Germany]","institution_ids":["https://openalex.org/I31512782"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5071367253","display_name":"Jan Peters","orcid":"https://orcid.org/0000-0002-5266-8091"},"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/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":"Jan Peters","raw_affiliation_strings":["Department of Computer Science, Technische Universit\u00e4t Darmstadt, Germany","Robot Learning Group, Max Planck Institute for Intelligent Systems, T\u00fcbingen, Germany"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Computer Science, Technische Universit\u00e4t Darmstadt, Germany","institution_ids":["https://openalex.org/I31512782"]},{"raw_affiliation_string":"Robot Learning Group, Max Planck Institute for Intelligent Systems, T\u00fcbingen, Germany","institution_ids":["https://openalex.org/I4210135521"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5017983137","display_name":"Joni Pajarinen","orcid":"https://orcid.org/0000-0003-4469-8191"},"institutions":[{"id":"https://openalex.org/I166825849","display_name":"Tampere University","ror":"https://ror.org/033003e23","country_code":"FI","type":"education","lineage":["https://openalex.org/I166825849"]}],"countries":["FI"],"is_corresponding":false,"raw_author_name":"Joni Pajarinen","raw_affiliation_strings":["Computing Sciences, Tampere University, Finland"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Computing Sciences, Tampere University, Finland","institution_ids":["https://openalex.org/I166825849"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":3,"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":0.00802176,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"2397","last_page":"2404"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10462","display_name":"Reinforcement Learning in Robotics","score":0.9994000196456909,"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":0.9994000196456909,"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/T12072","display_name":"Machine Learning and Algorithms","score":0.9972000122070312,"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":0.9969000220298767,"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/backup","display_name":"Backup","score":0.7659928798675537},{"id":"https://openalex.org/keywords/monte-carlo-tree-search","display_name":"Monte Carlo tree search","score":0.6985765099525452},{"id":"https://openalex.org/keywords/convergence","display_name":"Convergence (economics)","score":0.678705096244812},{"id":"https://openalex.org/keywords/mathematical-optimization","display_name":"Mathematical optimization","score":0.655940592288971},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6423513889312744},{"id":"https://openalex.org/keywords/tree","display_name":"Tree (set theory)","score":0.6130831837654114},{"id":"https://openalex.org/keywords/monte-carlo-method","display_name":"Monte Carlo method","score":0.5853874683380127},{"id":"https://openalex.org/keywords/markov-decision-process","display_name":"Markov decision process","score":0.559182345867157},{"id":"https://openalex.org/keywords/partially-observable-markov-decision-process","display_name":"Partially observable Markov decision process","score":0.5420613288879395},{"id":"https://openalex.org/keywords/operator","display_name":"Operator (biology)","score":0.5283050537109375},{"id":"https://openalex.org/keywords/speedup","display_name":"Speedup","score":0.5233485102653503},{"id":"https://openalex.org/keywords/node","display_name":"Node (physics)","score":0.5088027119636536},{"id":"https://openalex.org/keywords/markov-chain-monte-carlo","display_name":"Markov chain Monte Carlo","score":0.5053592324256897},{"id":"https://openalex.org/keywords/value","display_name":"Value (mathematics)","score":0.43266117572784424},{"id":"https://openalex.org/keywords/markov-process","display_name":"Markov process","score":0.33654117584228516},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.3256470561027527},{"id":"https://openalex.org/keywords/statistics","display_name":"Statistics","score":0.15199226140975952},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.12840011715888977}],"concepts":[{"id":"https://openalex.org/C2780945871","wikidata":"https://www.wikidata.org/wiki/Q194274","display_name":"Backup","level":2,"score":0.7659928798675537},{"id":"https://openalex.org/C46149586","wikidata":"https://www.wikidata.org/wiki/Q11785332","display_name":"Monte Carlo tree search","level":3,"score":0.6985765099525452},{"id":"https://openalex.org/C2777303404","wikidata":"https://www.wikidata.org/wiki/Q759757","display_name":"Convergence (economics)","level":2,"score":0.678705096244812},{"id":"https://openalex.org/C126255220","wikidata":"https://www.wikidata.org/wiki/Q141495","display_name":"Mathematical optimization","level":1,"score":0.655940592288971},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6423513889312744},{"id":"https://openalex.org/C113174947","wikidata":"https://www.wikidata.org/wiki/Q2859736","display_name":"Tree (set theory)","level":2,"score":0.6130831837654114},{"id":"https://openalex.org/C19499675","wikidata":"https://www.wikidata.org/wiki/Q232207","display_name":"Monte Carlo method","level":2,"score":0.5853874683380127},{"id":"https://openalex.org/C106189395","wikidata":"https://www.wikidata.org/wiki/Q176789","display_name":"Markov decision process","level":3,"score":0.559182345867157},{"id":"https://openalex.org/C17098449","wikidata":"https://www.wikidata.org/wiki/Q176814","display_name":"Partially observable Markov decision process","level":4,"score":0.5420613288879395},{"id":"https://openalex.org/C17020691","wikidata":"https://www.wikidata.org/wiki/Q139677","display_name":"Operator (biology)","level":5,"score":0.5283050537109375},{"id":"https://openalex.org/C68339613","wikidata":"https://www.wikidata.org/wiki/Q1549489","display_name":"Speedup","level":2,"score":0.5233485102653503},{"id":"https://openalex.org/C62611344","wikidata":"https://www.wikidata.org/wiki/Q1062658","display_name":"Node (physics)","level":2,"score":0.5088027119636536},{"id":"https://openalex.org/C111350023","wikidata":"https://www.wikidata.org/wiki/Q1191869","display_name":"Markov chain Monte Carlo","level":3,"score":0.5053592324256897},{"id":"https://openalex.org/C2776291640","wikidata":"https://www.wikidata.org/wiki/Q2912517","display_name":"Value (mathematics)","level":2,"score":0.43266117572784424},{"id":"https://openalex.org/C159886148","wikidata":"https://www.wikidata.org/wiki/Q176645","display_name":"Markov process","level":2,"score":0.33654117584228516},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.3256470561027527},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.15199226140975952},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.12840011715888977},{"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/C77088390","wikidata":"https://www.wikidata.org/wiki/Q8513","display_name":"Database","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/C104317684","wikidata":"https://www.wikidata.org/wiki/Q7187","display_name":"Gene","level":2,"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/C86339819","wikidata":"https://www.wikidata.org/wiki/Q407384","display_name":"Transcription factor","level":3,"score":0.0},{"id":"https://openalex.org/C158448853","wikidata":"https://www.wikidata.org/wiki/Q425218","display_name":"Repressor","level":4,"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/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.0},{"id":"https://openalex.org/C66938386","wikidata":"https://www.wikidata.org/wiki/Q633538","display_name":"Structural engineering","level":1,"score":0.0},{"id":"https://openalex.org/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","level":0,"score":0.0},{"id":"https://openalex.org/C55493867","wikidata":"https://www.wikidata.org/wiki/Q7094","display_name":"Biochemistry","level":1,"score":0.0}],"mesh":[],"locations_count":4,"locations":[{"id":"doi:10.24963/ijcai.2020/332","is_oa":true,"landing_page_url":"https://doi.org/10.24963/ijcai.2020/332","pdf_url":"https://www.ijcai.org/proceedings/2020/0332.pdf","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the Twenty-Ninth International Joint Conference on Artificial Intelligence","raw_type":"proceedings-article"},{"id":"pmh:oai:arXiv.org:1911.00384","is_oa":true,"landing_page_url":"http://arxiv.org/abs/1911.00384","pdf_url":"https://arxiv.org/pdf/1911.00384","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"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":"mag:2985140959","is_oa":true,"landing_page_url":"https://arxiv.org/pdf/1911.00384.pdf","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"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":"arXiv (Cornell University)","raw_type":null},{"id":"doi:10.48550/arxiv.1911.00384","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.1911.00384","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"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":null,"raw_source_name":null,"raw_type":"article"}],"best_oa_location":{"id":"doi:10.24963/ijcai.2020/332","is_oa":true,"landing_page_url":"https://doi.org/10.24963/ijcai.2020/332","pdf_url":"https://www.ijcai.org/proceedings/2020/0332.pdf","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the Twenty-Ninth International Joint Conference on Artificial Intelligence","raw_type":"proceedings-article"},"sustainable_development_goals":[{"display_name":"Peace, Justice and strong institutions","score":0.8100000023841858,"id":"https://metadata.un.org/sdg/16"}],"awards":[{"id":"https://openalex.org/G2553111511","display_name":null,"funder_award_id":"PA 3179/1-1","funder_id":"https://openalex.org/F4320320879","funder_display_name":"Deutsche Forschungsgemeinschaft"},{"id":"https://openalex.org/G5880680131","display_name":"Goal-based Open-ended Autonomous Learning Robots","funder_award_id":"713010","funder_id":"https://openalex.org/F4320320300","funder_display_name":"European Commission"},{"id":"https://openalex.org/G6403792536","display_name":"Policy Learning of Motor Skills for Humanoid Robots","funder_award_id":"640554","funder_id":"https://openalex.org/F4320320300","funder_display_name":"European Commission"},{"id":"https://openalex.org/G8367549587","display_name":null,"funder_award_id":"3179/1-1","funder_id":"https://openalex.org/F4320320879","funder_display_name":"Deutsche Forschungsgemeinschaft"}],"funders":[{"id":"https://openalex.org/F4320320300","display_name":"European Commission","ror":"https://ror.org/00k4n6c32"},{"id":"https://openalex.org/F4320320879","display_name":"Deutsche Forschungsgemeinschaft","ror":"https://ror.org/018mejw64"}],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W2985140959.pdf","grobid_xml":"https://content.openalex.org/works/W2985140959.grobid-xml"},"referenced_works_count":25,"referenced_works":["https://openalex.org/W120158324","https://openalex.org/W183472599","https://openalex.org/W1496357020","https://openalex.org/W1523281138","https://openalex.org/W1598714892","https://openalex.org/W1714211023","https://openalex.org/W1928468454","https://openalex.org/W2037677626","https://openalex.org/W2075848246","https://openalex.org/W2103012681","https://openalex.org/W2115211925","https://openalex.org/W2134802714","https://openalex.org/W2140365369","https://openalex.org/W2159309155","https://openalex.org/W2168405694","https://openalex.org/W2171084228","https://openalex.org/W2224879568","https://openalex.org/W2257979135","https://openalex.org/W2469051754","https://openalex.org/W2471186604","https://openalex.org/W2778917778","https://openalex.org/W2801558171","https://openalex.org/W3011120880","https://openalex.org/W3012045285","https://openalex.org/W3215037115"],"related_works":["https://openalex.org/W3034650914","https://openalex.org/W2952948446","https://openalex.org/W2075762831","https://openalex.org/W1924578217","https://openalex.org/W3136699581","https://openalex.org/W2950244853","https://openalex.org/W2803516620","https://openalex.org/W2397074156","https://openalex.org/W2101826491","https://openalex.org/W1975806721","https://openalex.org/W2105066050","https://openalex.org/W2800510998","https://openalex.org/W2770459377","https://openalex.org/W3026736587","https://openalex.org/W1902878251","https://openalex.org/W2804460413","https://openalex.org/W761017390","https://openalex.org/W2473144994","https://openalex.org/W2967025328","https://openalex.org/W3007032516"],"abstract_inverted_index":{"We":[0,119,143],"consider":[1],"Monte-Carlo":[2],"Tree":[3],"Search":[4],"(MCTS)":[5],"applied":[6],"to":[7,136,152],"Markov":[8],"Decision":[9],"Processes":[10],"(MDPs)":[11],"and":[12,17,34,45,116,125,167,175],"Partially":[13],"Observable":[14],"MDPs":[15],"(POMDPs),":[16],"the":[18,41,46,58,73,105,114,128,131,139,153,159,181],"well-known":[19,165],"Upper":[20],"Confidence":[21],"bound":[22],"for":[23,87],"Trees":[24],"(UCT)":[25],"algorithm.":[26],"In":[27],"UCT,":[28],"a":[29,53,95,99,111],"tree":[30],"with":[31,70],"nodes":[32,49],"(states)":[33],"edges":[35],"(actions)":[36],"is":[37],"incrementally":[38],"built":[39],"by":[40],"expansion":[42],"of":[43,48,61,85,89,130,150,161,180],"nodes,":[44],"values":[47],"are":[50],"updated":[51],"through":[52],"backup":[54,101],"strategy":[55,102],"based":[56],"on":[57],"average":[59,115],"value":[60,80,91,112],"child":[62],"nodes.":[63],"However,":[64],"it":[65],"has":[66],"been":[67],"shown":[68],"that":[69],"enough":[71],"samples":[72],"maximum":[74,117],"operator":[75,134],"yields":[76],"more":[77],"accurate":[78],"node":[79],"estimates":[81],"than":[82],"averaging.":[83],"Instead":[84],"settling":[86],"one":[88],"these":[90],"estimates,":[92],"we":[93,156],"go":[94],"step":[96],"further":[97],"proposing":[98],"novel":[100],"which":[103,109],"uses":[104],"power":[106,132],"mean":[107,133],"operator,":[108],"computes":[110],"between":[113],"value.":[118],"call":[120],"our":[121,146,162],"new":[122],"approach":[123],"Power-UCT,":[124],"argue":[126],"how":[127],"use":[129],"helps":[135],"speed":[137,177],"up":[138],"learning":[140],"in":[141,164,173],"MCTS.":[142],"theoretically":[144],"analyze":[145],"method":[147,163],"providing":[148],"guarantees":[149],"convergence":[151,176],"optimum.":[154],"Finally,":[155],"empirically":[157],"demonstrate":[158],"effectiveness":[160],"MDP":[166],"POMDP":[168],"benchmarks,":[169],"showing":[170],"significant":[171],"improvement":[172],"performance":[174],"w.r.t.":[178],"state":[179],"art":[182],"algorithms.":[183]},"counts_by_year":[],"updated_date":"2026-06-30T13:55:48.251075","created_date":"2025-10-10T00:00:00"}