On the Convergence Rate of MCTS for the Optimal Value Estimation in Markov Decision Processes

A recent theoretical analysis of a Monte-Carlo tree search (MCTS) method properly modified from the "upper confidence bound applied to trees" (UCT) algorithm established a surprising result, due to a great deal of empirical successes reported from heuristic usage of UCT with relevant adjus...

Full description

Saved in:
Bibliographic Details
Published in:IEEE transactions on automatic control Vol. 70; no. 7; pp. 4788 - 4793
Main Author: Chang, Hyeong Soo
Format: Journal Article
Language:English
Published: New York IEEE 01.07.2025
The Institute of Electrical and Electronics Engineers, Inc. (IEEE)
Subjects:
ISSN:0018-9286, 1558-2523
Online Access:Get full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Abstract A recent theoretical analysis of a Monte-Carlo tree search (MCTS) method properly modified from the "upper confidence bound applied to trees" (UCT) algorithm established a surprising result, due to a great deal of empirical successes reported from heuristic usage of UCT with relevant adjustments for various problem domains in the literature, that its rate of convergence of the expected absolute error to zero is <inline-formula><tex-math notation="LaTeX">O(1/\sqrt{n})</tex-math></inline-formula> in estimating the optimal value at an initial state in a finite-horizon Markov decision process (MDP), where <inline-formula><tex-math notation="LaTeX">n</tex-math></inline-formula> is the number of simulations. We strengthen this dispiriting slow convergence result by arguing within a simpler algorithmic framework in the perspective of MDP, apart from the usual MCTS description, that the simpler strategy, called "upper confidence bound 1" (UCB1) for multiarmed bandit problems, when employed as an instance of MCTS by setting UCB1's arm set to be the policy set of the underlying MDP, has an asymptotically faster convergence-rate of <inline-formula><tex-math notation="LaTeX">O(\ln n / n)</tex-math></inline-formula>. We also point out that the UCT-based MCTS in general has the time and space complexities that depend on the size of the state space in the worst case, which contradicts the original design spirit of MCTS. Unless heuristically used, UCT-based MCTS has yet to have theoretical supports for its applicabilities.
AbstractList A recent theoretical analysis of a Monte-Carlo tree search (MCTS) method properly modified from the “upper confidence bound applied to trees” (UCT) algorithm established a surprising result, due to a great deal of empirical successes reported from heuristic usage of UCT with relevant adjustments for various problem domains in the literature, that its rate of convergence of the expected absolute error to zero is [Formula Omitted] in estimating the optimal value at an initial state in a finite-horizon Markov decision process (MDP), where [Formula Omitted] is the number of simulations. We strengthen this dispiriting slow convergence result by arguing within a simpler algorithmic framework in the perspective of MDP, apart from the usual MCTS description, that the simpler strategy, called “upper confidence bound 1” (UCB1) for multiarmed bandit problems, when employed as an instance of MCTS by setting UCB1’s arm set to be the policy set of the underlying MDP, has an asymptotically faster convergence-rate of [Formula Omitted]. We also point out that the UCT-based MCTS in general has the time and space complexities that depend on the size of the state space in the worst case, which contradicts the original design spirit of MCTS. Unless heuristically used, UCT-based MCTS has yet to have theoretical supports for its applicabilities.
A recent theoretical analysis of a Monte-Carlo tree search (MCTS) method properly modified from the "upper confidence bound applied to trees" (UCT) algorithm established a surprising result, due to a great deal of empirical successes reported from heuristic usage of UCT with relevant adjustments for various problem domains in the literature, that its rate of convergence of the expected absolute error to zero is <inline-formula><tex-math notation="LaTeX">O(1/\sqrt{n})</tex-math></inline-formula> in estimating the optimal value at an initial state in a finite-horizon Markov decision process (MDP), where <inline-formula><tex-math notation="LaTeX">n</tex-math></inline-formula> is the number of simulations. We strengthen this dispiriting slow convergence result by arguing within a simpler algorithmic framework in the perspective of MDP, apart from the usual MCTS description, that the simpler strategy, called "upper confidence bound 1" (UCB1) for multiarmed bandit problems, when employed as an instance of MCTS by setting UCB1's arm set to be the policy set of the underlying MDP, has an asymptotically faster convergence-rate of <inline-formula><tex-math notation="LaTeX">O(\ln n / n)</tex-math></inline-formula>. We also point out that the UCT-based MCTS in general has the time and space complexities that depend on the size of the state space in the worst case, which contradicts the original design spirit of MCTS. Unless heuristically used, UCT-based MCTS has yet to have theoretical supports for its applicabilities.
Author Chang, Hyeong Soo
Author_xml – sequence: 1
  givenname: Hyeong Soo
  orcidid: 0000-0003-3298-0018
  surname: Chang
  fullname: Chang, Hyeong Soo
  email: hschang@sogang.ac.kr
  organization: Department of Computer Science and Engineering, Sogang University, Seoul, South Korea
BookMark eNpNkD1PwzAQhi1UJNrCzsBgiTnFH7Fjj1UoH1KrIihsKHKcM6SUuNhpJf49CWVgOr2n5-50zwgNGt8AQueUTCgl-mo1zSeMMDHhgitFsiM0pEKohAnGB2hICFWJZkqeoFGM6y7KNKVD9LpscPsOOPfNHsIbNBbwo2kBe4cX-eoJOx9-geW2rT_NBr-YzQ7wLPaprX2D6wYvTPjwe3wNto596yF4CzFCPEXHzmwinP3VMXq-ma3yu2S-vL3Pp_PEslS0ickMgEor6qTTpeWuJCUxhNrMOdBK6EraSlJpCdOlLI3TgpW8dCmvFNUc-BhdHvZug__aQWyLtd-FpjtZcMakICSTqqPIgbLBxxjAFdvQfRG-C0qKXmLRSSx6icWfxG7k4jBSA8A_XGWEiIz_ABCRb2c
CODEN IETAA9
Cites_doi 10.1007/978-1-4471-5022-0
10.1287/opre.2021.2239
10.1016/0196-8858(85)90002-8
10.1109/cdc.1995.478953
10.1109/TCIAIG.2012.2186810
10.1007/978-3-540-75538-8_7
10.1002/SERIES1345
10.1007/11871842_29
10.1007/s001860400372
10.1287/opre.1040.0145
10.1007/s10462-022-10228-y
10.1016/j.tcs.2010.12.059
10.1023/A:1013689704352
ContentType Journal Article
Copyright Copyright The Institute of Electrical and Electronics Engineers, Inc. (IEEE) 2025
Copyright_xml – notice: Copyright The Institute of Electrical and Electronics Engineers, Inc. (IEEE) 2025
DBID 97E
RIA
RIE
AAYXX
CITATION
7SC
7SP
7TB
8FD
FR3
JQ2
L7M
L~C
L~D
DOI 10.1109/TAC.2025.3538807
DatabaseName IEEE Xplore (IEEE)
IEEE All-Society Periodicals Package (ASPP) 1998-Present
IEEE Electronic Library (IEL)
CrossRef
Computer and Information Systems Abstracts
Electronics & Communications Abstracts
Mechanical & Transportation Engineering Abstracts
Technology Research Database
Engineering Research Database
ProQuest Computer Science Collection
Advanced Technologies Database with Aerospace
Computer and Information Systems Abstracts – Academic
Computer and Information Systems Abstracts Professional
DatabaseTitle CrossRef
Technology Research Database
Computer and Information Systems Abstracts – Academic
Mechanical & Transportation Engineering Abstracts
Electronics & Communications Abstracts
ProQuest Computer Science Collection
Computer and Information Systems Abstracts
Engineering Research Database
Advanced Technologies Database with Aerospace
Computer and Information Systems Abstracts Professional
DatabaseTitleList Technology Research Database

Database_xml – sequence: 1
  dbid: RIE
  name: IEEE Electronic Library (IEL)
  url: https://ieeexplore.ieee.org/
  sourceTypes: Publisher
DeliveryMethod fulltext_linktorsrc
Discipline Engineering
EISSN 1558-2523
EndPage 4793
ExternalDocumentID 10_1109_TAC_2025_3538807
10870057
Genre orig-research
GroupedDBID -~X
.DC
0R~
29I
3EH
4.4
5GY
5VS
6IK
97E
AAJGR
AARMG
AASAJ
AAWTH
ABAZT
ABQJQ
ABVLG
ACGFO
ACGFS
ACIWK
ACNCT
AENEX
AETIX
AGQYO
AGSQL
AHBIQ
AI.
AIBXA
AKJIK
AKQYR
ALLEH
ALMA_UNASSIGNED_HOLDINGS
ASUFR
ATWAV
BEFXN
BFFAM
BGNUA
BKEBE
BPEOZ
CS3
DU5
EBS
EJD
F5P
HZ~
H~9
IAAWW
IBMZZ
ICLAB
IDIHD
IFIPE
IFJZH
IPLJI
JAVBF
LAI
M43
MS~
O9-
OCL
P2P
RIA
RIE
RNS
TAE
TN5
VH1
VJK
~02
AAYXX
CITATION
7SC
7SP
7TB
8FD
FR3
JQ2
L7M
L~C
L~D
ID FETCH-LOGICAL-c245t-a7aee84d1f6f9bc3fb0b0a01c7ffe9859d6cd616c029b6baf952b3bf43d8193e3
IEDL.DBID RIE
ISICitedReferencesCount 0
ISICitedReferencesURI http://www.webofscience.com/api/gateway?GWVersion=2&SrcApp=Summon&SrcAuth=ProQuest&DestLinkType=CitingArticles&DestApp=WOS_CPL&KeyUT=001521488300015&url=https%3A%2F%2Fcvtisr.summon.serialssolutions.com%2F%23%21%2Fsearch%3Fho%3Df%26include.ft.matches%3Dt%26l%3Dnull%26q%3D
ISSN 0018-9286
IngestDate Thu Oct 30 15:48:40 EDT 2025
Sat Nov 29 07:52:45 EST 2025
Wed Aug 27 02:14:29 EDT 2025
IsPeerReviewed true
IsScholarly true
Issue 7
Language English
License https://ieeexplore.ieee.org/Xplorehelp/downloads/license-information/IEEE.html
https://doi.org/10.15223/policy-029
https://doi.org/10.15223/policy-037
LinkModel DirectLink
MergedId FETCHMERGED-LOGICAL-c245t-a7aee84d1f6f9bc3fb0b0a01c7ffe9859d6cd616c029b6baf952b3bf43d8193e3
Notes ObjectType-Article-1
SourceType-Scholarly Journals-1
ObjectType-Feature-2
content type line 14
ORCID 0000-0003-3298-0018
PQID 3226500768
PQPubID 85475
PageCount 6
ParticipantIDs proquest_journals_3226500768
ieee_primary_10870057
crossref_primary_10_1109_TAC_2025_3538807
PublicationCentury 2000
PublicationDate 2025-07-01
PublicationDateYYYYMMDD 2025-07-01
PublicationDate_xml – month: 07
  year: 2025
  text: 2025-07-01
  day: 01
PublicationDecade 2020
PublicationPlace New York
PublicationPlace_xml – name: New York
PublicationTitle IEEE transactions on automatic control
PublicationTitleAbbrev TAC
PublicationYear 2025
Publisher IEEE
The Institute of Electrical and Electronics Engineers, Inc. (IEEE)
Publisher_xml – name: IEEE
– name: The Institute of Electrical and Electronics Engineers, Inc. (IEEE)
References ref13
ref12
ref14
ref11
ref10
ref1
ref8
ref7
ref9
ref4
ref3
ref6
ref5
Bertsekas (ref2) 2022
References_xml – ident: ref7
  doi: 10.1007/978-1-4471-5022-0
– ident: ref13
  doi: 10.1287/opre.2021.2239
– ident: ref11
  doi: 10.1016/0196-8858(85)90002-8
– ident: ref3
  doi: 10.1109/cdc.1995.478953
– ident: ref4
  doi: 10.1109/TCIAIG.2012.2186810
– ident: ref8
  doi: 10.1007/978-3-540-75538-8_7
– ident: ref12
  doi: 10.1002/SERIES1345
– ident: ref10
  doi: 10.1007/11871842_29
– ident: ref9
  doi: 10.1007/s001860400372
– ident: ref6
  doi: 10.1287/opre.1040.0145
– ident: ref14
  doi: 10.1007/s10462-022-10228-y
– volume-title: Lessons from AlphaZero Optimal, Model Predictive, Adaptive Control
  year: 2022
  ident: ref2
– ident: ref5
  doi: 10.1016/j.tcs.2010.12.059
– ident: ref1
  doi: 10.1023/A:1013689704352
SSID ssj0016441
Score 2.4826643
Snippet A recent theoretical analysis of a Monte-Carlo tree search (MCTS) method properly modified from the "upper confidence bound applied to trees" (UCT) algorithm...
A recent theoretical analysis of a Monte-Carlo tree search (MCTS) method properly modified from the “upper confidence bound applied to trees” (UCT) algorithm...
SourceID proquest
crossref
ieee
SourceType Aggregation Database
Index Database
Publisher
StartPage 4788
SubjectTerms Approximation algorithms
Artificial intelligence
Complexity theory
Computational modeling
Convergence
Data mining
Estimation
Markov decision process (MDP)
Markov processes
Monte-Carlo tree search (MCTS)
multiarmed bandit (MAB)
Search problems
Training
Uncertainty
Upper bound
upper confidence bound 1 (UCB1)
upper confidence bound applied to trees (UCT)
Title On the Convergence Rate of MCTS for the Optimal Value Estimation in Markov Decision Processes
URI https://ieeexplore.ieee.org/document/10870057
https://www.proquest.com/docview/3226500768
Volume 70
WOSCitedRecordID wos001521488300015&url=https%3A%2F%2Fcvtisr.summon.serialssolutions.com%2F%23%21%2Fsearch%3Fho%3Df%26include.ft.matches%3Dt%26l%3Dnull%26q%3D
hasFullText 1
inHoldings 1
isFullTextHit
isPrint
journalDatabaseRights – providerCode: PRVIEE
  databaseName: IEEE Electronic Library (IEL)
  customDbUrl:
  eissn: 1558-2523
  dateEnd: 99991231
  omitProxy: false
  ssIdentifier: ssj0016441
  issn: 0018-9286
  databaseCode: RIE
  dateStart: 19630101
  isFulltext: true
  titleUrlDefault: https://ieeexplore.ieee.org/
  providerName: IEEE
link http://cvtisr.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwlV07T8MwELagYoCBZxGFgjywMKTk4ST2WIVWDNAiKKgLivw4S5UgRU3b34_tpFURYmBKIjlWdJ_v_Dn3QuiaMhUoEqae0pH0CGHEE5LaKAvQxhqaS9W15CEdDOh4zJ7qZHWXCwMALvgMOvbW-fLVVC7srzKj4WZ1GYKxjbbTNKmStdYuA7uxV2bXaHBI1z5Jn92Oupk5CYZxJ4pt7ZP0xx7kmqr8ssRue-kf_PPDDtF-zSNxtwL-CG1BcYz2NqoLnqD3YYENvcOZDSx3OZaAnw21xFONH7PRCzZ81Q0YGrPxaSZ74x8LwL3SPlm88KTANpdnusR3dSseXCcWQNlEr_3eKLv36m4KngxJPPd4ygEoUYFONBMy0sIXPvcDmWoNjMZMJVIlQSL9kIlEcM3iUERCk0gZ1hBBdIoaxbSAM4QD6kPMEp4qzoiSgstQxD6RVHMtaQQtdLOSb_5VFc3I3WHDZ7nBIrdY5DUWLdS08twYV4myhdorRPJarcrcWB_DKK3z8PyP1y7Qrp29Cqhto8Z8toBLtCOX80k5u3Ir5hvcMr8E
linkProvider IEEE
linkToHtml http://cvtisr.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwlV1LS8QwEB58gXrwueL6zMGLh2rapm1ylFVRXFfRVbxIyWMCgnbF3fX3m6RVFPHgqS2kD2Yyky-d-WYA9rgwsWFJERmb6ogxwSKluc-yQOu8oTvUXUu6Ra_HHx7EdUNWD1wYRAzJZ3jgT0Ms3wz02P8qcxbuZpcDGJMwnTGW0Jqu9RU08Et77XidDSf8KypJxWH_qOP2gkl2kGa--knxYxUKbVV--eKwwJwu_vPTlmChQZLkqFb9MkxgtQLz3-oLrsLjVUUcwCMdn1oeWJZIbhy4JANLLjv9W-IQaxhw5RzHi3vYvXweIzkZ-iuvMfJUEc_mGbyT46YZD2moBThswd3pSb9zFjX9FCKdsGwUyUIicmZim1uhdGoVVVTSWBfWouCZMLk2eZxrmgiVK2lFlqhUWZYahxtSTNdgqhpUuA4k5hQzkcvCSMGMVlInKqNMcyut5im2Yf9TvuVrXTajDNsNKkqni9Lromx00YaWl-e3cbUo27D1qZGyMaxh6fyPw5Q-fLjxx227MHvWv-yW3fPexSbM-TfV6bVbMDV6G-M2zOj30dPwbSfMng_3BsJL
openUrl ctx_ver=Z39.88-2004&ctx_enc=info%3Aofi%2Fenc%3AUTF-8&rfr_id=info%3Asid%2Fsummon.serialssolutions.com&rft_val_fmt=info%3Aofi%2Ffmt%3Akev%3Amtx%3Ajournal&rft.genre=article&rft.atitle=On+the+Convergence+Rate+of+MCTS+for+the+Optimal+Value+Estimation+in+Markov+Decision+Processes&rft.jtitle=IEEE+transactions+on+automatic+control&rft.au=Chang%2C+Hyeong+Soo&rft.date=2025-07-01&rft.pub=IEEE&rft.issn=0018-9286&rft.volume=70&rft.issue=7&rft.spage=4788&rft.epage=4793&rft_id=info:doi/10.1109%2FTAC.2025.3538807&rft.externalDocID=10870057
thumbnail_l http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/lc.gif&issn=0018-9286&client=summon
thumbnail_m http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/mc.gif&issn=0018-9286&client=summon
thumbnail_s http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/sc.gif&issn=0018-9286&client=summon