PPB-MCTS: A novel distributed-memory parallel partial-backpropagation Monte Carlo tree search algorithm
Monte-Carlo Tree Search (MCTS) is an adaptive and heuristic tree-search algorithm designed to uncover sub-optimal actions at each decision-making point. This method progressively constructs a search tree by gathering samples throughout its execution. Predominantly applied within the realm of gaming,...
Uloženo v:
| Vydáno v: | Journal of parallel and distributed computing Ročník 193; s. 104944 |
|---|---|
| Hlavní autoři: | , , |
| Médium: | Journal Article |
| Jazyk: | angličtina |
| Vydáno: |
Elsevier Inc
01.11.2024
|
| Témata: | |
| ISSN: | 0743-7315 |
| On-line přístup: | Získat plný text |
| Tagy: |
Přidat tag
Žádné tagy, Buďte první, kdo vytvoří štítek k tomuto záznamu!
|
| Abstract | Monte-Carlo Tree Search (MCTS) is an adaptive and heuristic tree-search algorithm designed to uncover sub-optimal actions at each decision-making point. This method progressively constructs a search tree by gathering samples throughout its execution. Predominantly applied within the realm of gaming, MCTS has exhibited exceptional achievements. Additionally, it has displayed promising outcomes when employed to solve NP-hard combinatorial optimization problems. MCTS has been adapted for distributed-memory parallel platforms. The primary challenges associated with distributed-memory parallel MCTS are the substantial communication overhead and the necessity to balance the computational load among various processes. In this work, we introduce a novel distributed-memory parallel MCTS algorithm with partial backpropagations, referred to as Parallel Partial-Backpropagation MCTS (PPB-MCTS). Our design approach aims to significantly reduce the communication overhead while maintaining, or even slightly improving, the performance in the context of combinatorial optimization problems. To address the communication overhead challenge, we propose a strategy involving transmitting an additional backpropagation message. This strategy avoids attaching an information table to the communication messages exchanged by the processes, thus reducing the communication overhead. Furthermore, this approach contributes to enhancing the decision-making accuracy during the selection phase. The load balancing issue is also effectively addressed by implementing a shared transposition table among the parallel processes. Furthermore, we introduce two primary methods for managing duplicate states within distributed-memory parallel MCTS, drawing upon techniques utilized in addressing duplicate states within sequential MCTS. Duplicate states can transform the conventional search tree into a Directed Acyclic Graph (DAG). To evaluate the performance of our proposed parallel algorithm, we conduct an extensive series of experiments on solving instances of the Job-Shop Scheduling Problem (JSSP) and the Weighted Set-Cover Problem (WSCP). These problems are recognized for their complexity and classified as NP-hard combinatorial optimization problems with considerable relevance within industrial applications. The experiments are performed on a cluster of computers with many cores. The empirical results highlight the enhanced scalability of our algorithm compared to that of the existing distributed-memory parallel MCTS algorithms. As the number of processes increases, our algorithm demonstrates increased rollout efficiency while maintaining an improved load balance across processes.
•A distributed-memory parallel Monte Carlo Tree Search algorithm is proposed.•The algorithm is scalable and efficient.•The algorithm is used to solve several Job-Shop Scheduling Problem instances. |
|---|---|
| AbstractList | Monte-Carlo Tree Search (MCTS) is an adaptive and heuristic tree-search algorithm designed to uncover sub-optimal actions at each decision-making point. This method progressively constructs a search tree by gathering samples throughout its execution. Predominantly applied within the realm of gaming, MCTS has exhibited exceptional achievements. Additionally, it has displayed promising outcomes when employed to solve NP-hard combinatorial optimization problems. MCTS has been adapted for distributed-memory parallel platforms. The primary challenges associated with distributed-memory parallel MCTS are the substantial communication overhead and the necessity to balance the computational load among various processes. In this work, we introduce a novel distributed-memory parallel MCTS algorithm with partial backpropagations, referred to as Parallel Partial-Backpropagation MCTS (PPB-MCTS). Our design approach aims to significantly reduce the communication overhead while maintaining, or even slightly improving, the performance in the context of combinatorial optimization problems. To address the communication overhead challenge, we propose a strategy involving transmitting an additional backpropagation message. This strategy avoids attaching an information table to the communication messages exchanged by the processes, thus reducing the communication overhead. Furthermore, this approach contributes to enhancing the decision-making accuracy during the selection phase. The load balancing issue is also effectively addressed by implementing a shared transposition table among the parallel processes. Furthermore, we introduce two primary methods for managing duplicate states within distributed-memory parallel MCTS, drawing upon techniques utilized in addressing duplicate states within sequential MCTS. Duplicate states can transform the conventional search tree into a Directed Acyclic Graph (DAG). To evaluate the performance of our proposed parallel algorithm, we conduct an extensive series of experiments on solving instances of the Job-Shop Scheduling Problem (JSSP) and the Weighted Set-Cover Problem (WSCP). These problems are recognized for their complexity and classified as NP-hard combinatorial optimization problems with considerable relevance within industrial applications. The experiments are performed on a cluster of computers with many cores. The empirical results highlight the enhanced scalability of our algorithm compared to that of the existing distributed-memory parallel MCTS algorithms. As the number of processes increases, our algorithm demonstrates increased rollout efficiency while maintaining an improved load balance across processes.
•A distributed-memory parallel Monte Carlo Tree Search algorithm is proposed.•The algorithm is scalable and efficient.•The algorithm is used to solve several Job-Shop Scheduling Problem instances. |
| ArticleNumber | 104944 |
| Author | Grosu, Daniel Naderzadeh, Yashar Chinnam, Ratna Babu |
| Author_xml | – sequence: 1 givenname: Yashar surname: Naderzadeh fullname: Naderzadeh, Yashar organization: Department of Computer Science, Wayne State University, 5057 Woodward Ave., Detroit, 48202, MI, USA – sequence: 2 givenname: Daniel orcidid: 0000-0003-2340-5433 surname: Grosu fullname: Grosu, Daniel email: dgrosu@wayne.edu organization: Department of Computer Science, Wayne State University, 5057 Woodward Ave., Detroit, 48202, MI, USA – sequence: 3 givenname: Ratna Babu orcidid: 0000-0003-0980-1544 surname: Chinnam fullname: Chinnam, Ratna Babu organization: Department of Industrial and Systems Engineering, Wayne State University, 4815 Fourth Street, Detroit, 48202, MI, USA |
| BookMark | eNp9kE1uwjAQRr2gUoH2Al35AqF27MRJ1Q1F_ZNARSpdW449AadJHDkuErdvgK66YDWjGb3RN2-CRq1rAaE7SmaU0PS-mlWd0bOYxHwY8JzzERoTwVkkGE2u0aTvK0IoTUQ2Rtv1-ilaLTafD3iOW7eHGhvbB2-LnwAmaqBx_oA75VVdD7uhCVbVUaH0d-ddp7YqWNfilWsD4IXytcPBA-AelNc7rOqt8zbsmht0Vaq6h9u_OkVfL8-bxVu0_Hh9X8yXkWaEhIjnhsU01ukpt-DCZEabvFCMmRiUTlVaaJ2XaUFjlXCuBc9LxkRJgWUiSdgUZee72ru-91BKbcMpY_DK1pISeZQkK3mUJI-S5FnSgMb_0M7bRvnDZejxDMHw1N6Cl7220Gow1oMO0jh7Cf8Fi6SFrQ |
| CitedBy_id | crossref_primary_10_3390_e27010035 crossref_primary_10_1016_j_enconman_2025_120173 crossref_primary_10_1109_LRA_2025_3586517 |
| Cites_doi | 10.1177/0278364918755924 10.1109/ACCESS.2020.3029868 10.1016/0377-2217(93)90182-M 10.1038/nature16961 10.1109/TG.2020.3048331 10.1109/TCIAIG.2014.2346997 10.1103/PhysRevE.71.036113 10.1007/s10514-024-10156-6 10.1016/0004-3702(85)90084-0 10.1145/2093548.2093574 10.1109/JAS.2016.7471613 10.1109/TCIAIG.2012.2186810 10.1109/JAS.2019.1911540 10.1287/opre.8.2.219 10.1016/j.knosys.2011.11.014 10.1561/2200000038 |
| ContentType | Journal Article |
| Copyright | 2024 Elsevier Inc. |
| Copyright_xml | – notice: 2024 Elsevier Inc. |
| DBID | AAYXX CITATION |
| DOI | 10.1016/j.jpdc.2024.104944 |
| DatabaseName | CrossRef |
| DatabaseTitle | CrossRef |
| DatabaseTitleList | |
| DeliveryMethod | fulltext_linktorsrc |
| Discipline | Computer Science |
| ExternalDocumentID | 10_1016_j_jpdc_2024_104944 S0743731524001084 |
| GroupedDBID | --K --M -~X .~1 0R~ 0SF 1B1 1~. 1~5 29L 4.4 457 4G. 5GY 5VS 7-5 71M 8P~ 9JN AACTN AAEDT AAEDW AAIKJ AAKOC AALRI AAOAW AAQFI AAQXK AAXUO AAYFN ABBOA ABEFU ABFNM ABFSI ABJNI ABMAC ABTAH ABXDB ACDAQ ACGFS ACNNM ACRLP ACZNC ADBBV ADEZE ADFGL ADHUB ADJOM ADMUD ADTZH ADVLN AEBSH AECPX AEKER AENEX AFKWA AFTJW AGHFR AGUBO AGYEJ AHHHB AHJVU AHZHX AIALX AIEXJ AIKHN AITUG AJOXV AKRWK ALMA_UNASSIGNED_HOLDINGS AMFUW AMRAJ AOUOD ASPBG AVWKF AXJTR AZFZN BJAXD BKOJK BLXMC CAG COF CS3 DM4 DU5 E.L EBS EFBJH EJD EO8 EO9 EP2 EP3 F5P FDB FEDTE FGOYB FIRID FNPLU FYGXN G-2 G-Q G8K GBLVA GBOLZ HLZ HVGLF HZ~ H~9 IHE J1W JJJVA K-O KOM LG5 LG9 LY7 M41 MO0 N9A O-L O9- OAUVE OZT P-8 P-9 P2P PC. Q38 R2- RIG ROL RPZ SBC SDF SDG SDP SES SET SEW SPC SPCBC SST SSV SSZ T5K TN5 TWZ WUQ XJT XOL XPP ZMT ZU3 ZY4 ~G- ~G0 9DU AATTM AAXKI AAYWO AAYXX ABDPE ABWVN ACLOT ACRPL ACVFH ADCNI ADNMO AEIPS AEUPX AFJKZ AFPUW AGQPQ AIGII AIIUN AKBMS AKYEP ANKPU APXCP CITATION EFKBS EFLBG ~HD |
| ID | FETCH-LOGICAL-c300t-49d3212c604944747d8dcd9ba33d2eac6a6bcc9f6b12a544c749f337f1e387553 |
| ISICitedReferencesCount | 3 |
| ISICitedReferencesURI | http://www.webofscience.com/api/gateway?GWVersion=2&SrcApp=Summon&SrcAuth=ProQuest&DestLinkType=CitingArticles&DestApp=WOS_CPL&KeyUT=001263563400001&url=https%3A%2F%2Fcvtisr.summon.serialssolutions.com%2F%23%21%2Fsearch%3Fho%3Df%26include.ft.matches%3Dt%26l%3Dnull%26q%3D |
| ISSN | 0743-7315 |
| IngestDate | Sat Nov 29 05:29:19 EST 2025 Tue Nov 18 21:02:46 EST 2025 Sat Aug 24 15:42:07 EDT 2024 |
| IsPeerReviewed | true |
| IsScholarly | true |
| Keywords | Parallel algorithms Job shop scheduling Monte Carlo tree search |
| Language | English |
| LinkModel | OpenURL |
| MergedId | FETCHMERGED-LOGICAL-c300t-49d3212c604944747d8dcd9ba33d2eac6a6bcc9f6b12a544c749f337f1e387553 |
| ORCID | 0000-0003-0980-1544 0000-0003-2340-5433 |
| ParticipantIDs | crossref_citationtrail_10_1016_j_jpdc_2024_104944 crossref_primary_10_1016_j_jpdc_2024_104944 elsevier_sciencedirect_doi_10_1016_j_jpdc_2024_104944 |
| PublicationCentury | 2000 |
| PublicationDate | November 2024 2024-11-00 |
| PublicationDateYYYYMMDD | 2024-11-01 |
| PublicationDate_xml | – month: 11 year: 2024 text: November 2024 |
| PublicationDecade | 2020 |
| PublicationTitle | Journal of parallel and distributed computing |
| PublicationYear | 2024 |
| Publisher | Elsevier Inc |
| Publisher_xml | – name: Elsevier Inc |
| References | Gao, Cao, Zhang, Chen, Han, Pan (br0260) 2019; 6 Munos (br0360) 2014; 7 Enzenberger, Müller (br0300) 2009 Scheide, Best, Hollinger (br0120) 2021 Zhang, Song, Cao, Zhang, Tan, Chi (br0410) 2020; 33 Skrynnik, Andreychuk, Yakovlev, Panov (br0090) 2024; vol. 38 Yoshizoe, Kishimoto, Kaneko, Yoshimoto, Ishikawa (br0140) 2011; vol. 2 Graf, Lorenz, Platzner, Schaefers (br0160) 2011 Cazenave, Jouandeau (br0290) 2007 Kocsis, Szepesvári (br0010) 2006 Han, Yang (br0420) 2020; 8 Kurzer, Hörtnagl, Zöllner (br0280) 2020 Schaefers, Platzner (br0170) 2014; 7 Holcomb, Porter, Ault, Mao, Wang (br0230) 2018 Yang, Aasawat, Yoshizoe (br0150) 2020 Romein, Plaat, Bal, Schaeffer (br0180) 1999, 1999 Gelly, Kocsis, Schoenauer, Sebag, Silver, Szepesvári, Teytaud (br0240) 2012; 55 Enzenberger, Müller (br0130) 2010 Steinmetz, Gini (br0060) 2020; 13 Guo, Singh, Lewis, Lee (br0030) 2016 Kishimoto, Schaeffer (br0350) 2002 Chaslot, Winands, van Den Herik (br0050) 2008 Williamson, Shmoys (br0380) 2011 Manne (br0270) 1960; 8 Korf (br0340) 1985; 27 Runarsson, Schoenauer, Sebag (br0310) 2012 Lin, Tseng (br0330) 2024; 48 Lawrence (br0390) 1984 Taillard (br0400) 1993; 64 Mirsoleimani, van den Herik, Plaat, Vermaseren (br0080) 2018; vol. 2 Silver, Huang, Maddison, Guez, Sifre, Van Den Driessche, Schrittwieser, Antonoglou, Panneershelvam, Lanctot (br0020) 2016; 529 Czech, Korus, Kersting (br0200) 2021; vol. 31 Best, Fitch (br0110) 2016 Browne, Powley, Whitehouse, Lucas, Cowling, Rohlfshagen, Tavener, Perez, Samothrakis, Colton (br0040) 2012; 4 Segal (br0070) 2010 Wang, Zhang, Zheng, Wang, Yuan, Dai, Zhang, Yang (br0220) 2016; 3 Batagelj, Brandes (br0430) 2005; 71 Kan (br0250) 2012 Sutton, Barto (br0370) 2018 Saqlain, Ali, Lee (br0320) 2022 Saffidine, Cazenave, Méhat (br0210) 2012; 34 Leurent, Maillard (br0190) 2020 Best, Cliff, Patten, Mettu, Fitch (br0100) 2019; 38 Silver (10.1016/j.jpdc.2024.104944_br0020) 2016; 529 Gao (10.1016/j.jpdc.2024.104944_br0260) 2019; 6 Czech (10.1016/j.jpdc.2024.104944_br0200) 2021; vol. 31 Kishimoto (10.1016/j.jpdc.2024.104944_br0350) 2002 Lin (10.1016/j.jpdc.2024.104944_br0330) 2024; 48 Munos (10.1016/j.jpdc.2024.104944_br0360) 2014; 7 Best (10.1016/j.jpdc.2024.104944_br0100) 2019; 38 Leurent (10.1016/j.jpdc.2024.104944_br0190) 2020 Runarsson (10.1016/j.jpdc.2024.104944_br0310) 2012 Wang (10.1016/j.jpdc.2024.104944_br0220) 2016; 3 Enzenberger (10.1016/j.jpdc.2024.104944_br0300) 2009 Guo (10.1016/j.jpdc.2024.104944_br0030) Yoshizoe (10.1016/j.jpdc.2024.104944_br0140) 2011; vol. 2 Taillard (10.1016/j.jpdc.2024.104944_br0400) 1993; 64 Williamson (10.1016/j.jpdc.2024.104944_br0380) 2011 Saqlain (10.1016/j.jpdc.2024.104944_br0320) 2022 Zhang (10.1016/j.jpdc.2024.104944_br0410) 2020; 33 Segal (10.1016/j.jpdc.2024.104944_br0070) 2010 Enzenberger (10.1016/j.jpdc.2024.104944_br0130) 2010 Sutton (10.1016/j.jpdc.2024.104944_br0370) 2018 Browne (10.1016/j.jpdc.2024.104944_br0040) 2012; 4 Schaefers (10.1016/j.jpdc.2024.104944_br0170) 2014; 7 Kan (10.1016/j.jpdc.2024.104944_br0250) 2012 Skrynnik (10.1016/j.jpdc.2024.104944_br0090) 2024; vol. 38 Korf (10.1016/j.jpdc.2024.104944_br0340) 1985; 27 Lawrence (10.1016/j.jpdc.2024.104944_br0390) 1984 Holcomb (10.1016/j.jpdc.2024.104944_br0230) 2018 Manne (10.1016/j.jpdc.2024.104944_br0270) 1960; 8 Cazenave (10.1016/j.jpdc.2024.104944_br0290) 2007 Kocsis (10.1016/j.jpdc.2024.104944_br0010) 2006 Steinmetz (10.1016/j.jpdc.2024.104944_br0060) 2020; 13 Yang (10.1016/j.jpdc.2024.104944_br0150) Mirsoleimani (10.1016/j.jpdc.2024.104944_br0080) 2018; vol. 2 Saffidine (10.1016/j.jpdc.2024.104944_br0210) 2012; 34 Romein (10.1016/j.jpdc.2024.104944_br0180) 1999 Chaslot (10.1016/j.jpdc.2024.104944_br0050) 2008 Graf (10.1016/j.jpdc.2024.104944_br0160) 2011 Han (10.1016/j.jpdc.2024.104944_br0420) 2020; 8 Best (10.1016/j.jpdc.2024.104944_br0110) 2016 Scheide (10.1016/j.jpdc.2024.104944_br0120) 2021 Kurzer (10.1016/j.jpdc.2024.104944_br0280) Batagelj (10.1016/j.jpdc.2024.104944_br0430) 2005; 71 Gelly (10.1016/j.jpdc.2024.104944_br0240) 2012; 55 |
| References_xml | – volume: 64 start-page: 278 year: 1993 end-page: 285 ident: br0400 article-title: Benchmarks for basic scheduling problems publication-title: Eur. J. Oper. Res. – volume: 33 start-page: 1621 year: 2020 end-page: 1632 ident: br0410 article-title: Learning to dispatch for job shop scheduling via deep reinforcement learning publication-title: Adv. Neural Inf. Process. Syst. – volume: 27 start-page: 97 year: 1985 end-page: 109 ident: br0340 article-title: Depth-first iterative-deepening: an optimal admissible tree search publication-title: Artif. Intell. – year: 2018 ident: br0370 article-title: Reinforcement Learning: An Introduction – start-page: 14 year: 2010 end-page: 20 ident: br0130 article-title: A lock-free multithreaded Monte-Carlo tree search algorithm publication-title: Proc. of the 12th International Conference Advances in Computer Games (ACG 2009) – start-page: 67 year: 2018 end-page: 71 ident: br0230 article-title: Overview on deepmind and its alphago zero ai publication-title: Proc. of the International Conference on Big Data and Education (ICBDE 2018) – volume: 4 start-page: 1 year: 2012 end-page: 43 ident: br0040 article-title: A survey of Monte Carlo tree search methods publication-title: IEEE Trans. Comput. Intell. AI Games – volume: vol. 2 start-page: 589 year: 2018 end-page: 598 ident: br0080 article-title: A lock-free algorithm for parallel mcts publication-title: Proc. of the 10th International Conference on Agents and Artificial Intelligence (ICAART 2018) – start-page: 365 year: 2011 end-page: 376 ident: br0160 article-title: Parallel Monte-Carlo tree search for hpc systems publication-title: Proc. of the 17th International European Conference on Parallel Processing (Euro-Par 2011), vol. 2 – volume: 7 start-page: 361 year: 2014 end-page: 374 ident: br0170 article-title: Distributed Monte Carlo tree search: a novel technique and its application to computer go publication-title: IEEE Trans. Comput. Intell. AI Games – start-page: 14 year: 2009 end-page: 20 ident: br0300 article-title: A lock-free multithreaded Monte-Carlo tree search algorithm publication-title: Proc. of the 12th International Conference on Advances in Computer Games (ACG 2009) – volume: vol. 2 start-page: 180 year: 2011 end-page: 187 ident: br0140 article-title: Scalable distributed Monte-Carlo tree search publication-title: Proc. of the International Symposium on Combinatorial Search (SoCS 2011) – volume: 34 start-page: 26 year: 2012 end-page: 33 ident: br0210 article-title: Ucd: upper confidence bound for rooted directed acyclic graphs publication-title: Knowl.-Based Syst. – start-page: 1 year: 2022 end-page: 24 ident: br0320 article-title: A Monte-Carlo tree search algorithm for the flexible job-shop scheduling in manufacturing systems publication-title: Flex. Serv. Manuf. J. – year: 2020 ident: br0150 article-title: Practical massively parallel Monte-Carlo tree search applied to molecular design – volume: 71 year: 2005 ident: br0430 article-title: Efficient generation of large random networks publication-title: Phys. Rev. E – start-page: 165 year: 2007 end-page: 174 ident: br0290 article-title: On the parallelization of uct publication-title: Proc. of the Computer Games Workshop (CGW 2007) – start-page: 282 year: 2006 end-page: 293 ident: br0010 article-title: Bandit based Monte-Carlo planning publication-title: Proc. of the 17th European Conference on Machine Learning (ECML 2006) – start-page: 577 year: 2020 end-page: 592 ident: br0190 article-title: Monte-Carlo graph search: the value of merging similar states publication-title: Proc. of the 12th Asian Conference on Machine Learning (ACML 2020) – start-page: 323 year: 2002 end-page: 330 ident: br0350 article-title: Distributed game-tree search using transposition table driven work scheduling publication-title: Proc of the 31st International Conference on Parallel Processing (ICPP 2002) – year: 2020 ident: br0280 article-title: Parallelization of Monte Carlo tree search in continuous domains – start-page: 725 year: 1999, 1999 end-page: 731 ident: br0180 article-title: Transposition table driven work scheduling in distributed search publication-title: Proc. of the 16th National Conference on Artificial Intelligence (AAAI – volume: 38 start-page: 316 year: 2019 end-page: 337 ident: br0100 article-title: Dec-mcts: decentralized planning for multi-robot active perception publication-title: Int. J. Robot. Res. – volume: vol. 31 start-page: 103 year: 2021 end-page: 111 ident: br0200 article-title: Improving alphazero using Monte-Carlo graph search publication-title: Proc. of the 31st International Conference on Automated Planning and Scheduling (ICAPS 2021) – volume: 8 start-page: 186474 year: 2020 end-page: 186495 ident: br0420 article-title: Research on adaptive job shop scheduling problems based on dueling double dqn publication-title: IEEE Access – volume: 6 start-page: 904 year: 2019 end-page: 916 ident: br0260 article-title: A review on swarm intelligence and evolutionary algorithms for solving flexible job shop scheduling problems publication-title: IEEE/CAA J. Autom. Sin. – volume: 7 start-page: 1 year: 2014 end-page: 129 ident: br0360 article-title: From bandits to Monte-Carlo tree search: the optimistic principle applied to optimization and planning publication-title: Found. Trends Mach. Learn. – year: 2016 ident: br0110 article-title: Probabilistic maximum set cover with path constraints for informative path planning publication-title: Proc. of the Australasian Conference on Robotics and Automation – year: 2012 ident: br0250 article-title: Machine Scheduling Problems: Classification, Complexity and Computations – year: 2011 ident: br0380 article-title: The Design of Approximation Algorithms – volume: 3 start-page: 113 year: 2016 end-page: 120 ident: br0220 article-title: Where does alphago go: from church-Turing thesis to alphago thesis and beyond publication-title: IEEE/CAA J. Autom. Sin. – start-page: 36 year: 2010 end-page: 47 ident: br0070 article-title: On the scalability of parallel uct publication-title: Proc. of the 7th International Conference on Computers and Games (CG 2010) – year: 2016 ident: br0030 article-title: Deep learning for reward design to improve Monte Carlo tree search in atari games – volume: vol. 38 start-page: 17531 year: 2024 end-page: 17540 ident: br0090 article-title: Decentralized Monte Carlo tree search for partially observable multi-agent pathfinding publication-title: Proc. of the AAAI Conference on Artificial Intelligence – year: 1984 ident: br0390 article-title: Resouce Constrained Project Scheduling: An Experimental Investigation of Heuristic Scheduling Techniques (Supplement), Graduate School of Industrial Administration – volume: 48 start-page: 1 year: 2024 end-page: 22 ident: br0330 article-title: Maximal coverage problems with routing constraints using cross-entropy Monte Carlo tree search publication-title: Auton. Robots – volume: 529 start-page: 484 year: 2016 end-page: 489 ident: br0020 article-title: Mastering the game of go with deep neural networks and tree search publication-title: Nature – start-page: 160 year: 2012 end-page: 174 ident: br0310 article-title: Pilot, rollout and Monte Carlo tree search methods for job shop scheduling publication-title: Proc. of the 6th International Conference on Learning and Intelligent Optimization (LION 6) – start-page: 4837 year: 2021 end-page: 4843 ident: br0120 article-title: Behavior tree learning for robotic task planning through Monte Carlo dag search over a formal grammar publication-title: Proc. of the IEEE International Conference on Robotics and Automation (ICRA) – volume: 13 start-page: 315 year: 2020 end-page: 320 ident: br0060 article-title: More trees or larger trees: parallelizing Monte Carlo tree search publication-title: IEEE Trans. Games – volume: 55 start-page: 106 year: 2012 end-page: 113 ident: br0240 article-title: The grand challenge of computer go: Monte Carlo tree search and extensions publication-title: Commun. ACM – start-page: 60 year: 2008 end-page: 71 ident: br0050 article-title: Parallel Monte-Carlo tree search publication-title: Proc. of the 6th International Conference on Computers and Games (CG 2008) – volume: 8 start-page: 219 year: 1960 end-page: 223 ident: br0270 article-title: On the job-shop scheduling problem publication-title: Oper. Res. – start-page: 165 year: 2007 ident: 10.1016/j.jpdc.2024.104944_br0290 article-title: On the parallelization of uct – start-page: 577 year: 2020 ident: 10.1016/j.jpdc.2024.104944_br0190 article-title: Monte-Carlo graph search: the value of merging similar states – start-page: 60 year: 2008 ident: 10.1016/j.jpdc.2024.104944_br0050 article-title: Parallel Monte-Carlo tree search – volume: 38 start-page: 316 year: 2019 ident: 10.1016/j.jpdc.2024.104944_br0100 article-title: Dec-mcts: decentralized planning for multi-robot active perception publication-title: Int. J. Robot. Res. doi: 10.1177/0278364918755924 – start-page: 14 year: 2010 ident: 10.1016/j.jpdc.2024.104944_br0130 article-title: A lock-free multithreaded Monte-Carlo tree search algorithm – volume: 8 start-page: 186474 year: 2020 ident: 10.1016/j.jpdc.2024.104944_br0420 article-title: Research on adaptive job shop scheduling problems based on dueling double dqn publication-title: IEEE Access doi: 10.1109/ACCESS.2020.3029868 – start-page: 282 year: 2006 ident: 10.1016/j.jpdc.2024.104944_br0010 article-title: Bandit based Monte-Carlo planning – start-page: 4837 year: 2021 ident: 10.1016/j.jpdc.2024.104944_br0120 article-title: Behavior tree learning for robotic task planning through Monte Carlo dag search over a formal grammar – volume: vol. 2 start-page: 589 year: 2018 ident: 10.1016/j.jpdc.2024.104944_br0080 article-title: A lock-free algorithm for parallel mcts – volume: 64 start-page: 278 year: 1993 ident: 10.1016/j.jpdc.2024.104944_br0400 article-title: Benchmarks for basic scheduling problems publication-title: Eur. J. Oper. Res. doi: 10.1016/0377-2217(93)90182-M – start-page: 725 year: 1999 ident: 10.1016/j.jpdc.2024.104944_br0180 article-title: Transposition table driven work scheduling in distributed search – start-page: 323 year: 2002 ident: 10.1016/j.jpdc.2024.104944_br0350 article-title: Distributed game-tree search using transposition table driven work scheduling – ident: 10.1016/j.jpdc.2024.104944_br0030 – volume: 33 start-page: 1621 year: 2020 ident: 10.1016/j.jpdc.2024.104944_br0410 article-title: Learning to dispatch for job shop scheduling via deep reinforcement learning publication-title: Adv. Neural Inf. Process. Syst. – year: 2012 ident: 10.1016/j.jpdc.2024.104944_br0250 – year: 1984 ident: 10.1016/j.jpdc.2024.104944_br0390 – volume: 529 start-page: 484 year: 2016 ident: 10.1016/j.jpdc.2024.104944_br0020 article-title: Mastering the game of go with deep neural networks and tree search publication-title: Nature doi: 10.1038/nature16961 – volume: 13 start-page: 315 year: 2020 ident: 10.1016/j.jpdc.2024.104944_br0060 article-title: More trees or larger trees: parallelizing Monte Carlo tree search publication-title: IEEE Trans. Games doi: 10.1109/TG.2020.3048331 – start-page: 67 year: 2018 ident: 10.1016/j.jpdc.2024.104944_br0230 article-title: Overview on deepmind and its alphago zero ai – start-page: 1 year: 2022 ident: 10.1016/j.jpdc.2024.104944_br0320 article-title: A Monte-Carlo tree search algorithm for the flexible job-shop scheduling in manufacturing systems publication-title: Flex. Serv. Manuf. J. – year: 2018 ident: 10.1016/j.jpdc.2024.104944_br0370 – volume: 7 start-page: 361 year: 2014 ident: 10.1016/j.jpdc.2024.104944_br0170 article-title: Distributed Monte Carlo tree search: a novel technique and its application to computer go publication-title: IEEE Trans. Comput. Intell. AI Games doi: 10.1109/TCIAIG.2014.2346997 – year: 2016 ident: 10.1016/j.jpdc.2024.104944_br0110 article-title: Probabilistic maximum set cover with path constraints for informative path planning – start-page: 365 year: 2011 ident: 10.1016/j.jpdc.2024.104944_br0160 article-title: Parallel Monte-Carlo tree search for hpc systems – ident: 10.1016/j.jpdc.2024.104944_br0280 – volume: 71 year: 2005 ident: 10.1016/j.jpdc.2024.104944_br0430 article-title: Efficient generation of large random networks publication-title: Phys. Rev. E doi: 10.1103/PhysRevE.71.036113 – year: 2011 ident: 10.1016/j.jpdc.2024.104944_br0380 – volume: 48 start-page: 1 year: 2024 ident: 10.1016/j.jpdc.2024.104944_br0330 article-title: Maximal coverage problems with routing constraints using cross-entropy Monte Carlo tree search publication-title: Auton. Robots doi: 10.1007/s10514-024-10156-6 – volume: 27 start-page: 97 year: 1985 ident: 10.1016/j.jpdc.2024.104944_br0340 article-title: Depth-first iterative-deepening: an optimal admissible tree search publication-title: Artif. Intell. doi: 10.1016/0004-3702(85)90084-0 – start-page: 36 year: 2010 ident: 10.1016/j.jpdc.2024.104944_br0070 article-title: On the scalability of parallel uct – start-page: 160 year: 2012 ident: 10.1016/j.jpdc.2024.104944_br0310 article-title: Pilot, rollout and Monte Carlo tree search methods for job shop scheduling – volume: 55 start-page: 106 year: 2012 ident: 10.1016/j.jpdc.2024.104944_br0240 article-title: The grand challenge of computer go: Monte Carlo tree search and extensions publication-title: Commun. ACM doi: 10.1145/2093548.2093574 – volume: vol. 2 start-page: 180 year: 2011 ident: 10.1016/j.jpdc.2024.104944_br0140 article-title: Scalable distributed Monte-Carlo tree search – volume: 3 start-page: 113 year: 2016 ident: 10.1016/j.jpdc.2024.104944_br0220 article-title: Where does alphago go: from church-Turing thesis to alphago thesis and beyond publication-title: IEEE/CAA J. Autom. Sin. doi: 10.1109/JAS.2016.7471613 – volume: 4 start-page: 1 year: 2012 ident: 10.1016/j.jpdc.2024.104944_br0040 article-title: A survey of Monte Carlo tree search methods publication-title: IEEE Trans. Comput. Intell. AI Games doi: 10.1109/TCIAIG.2012.2186810 – volume: 6 start-page: 904 year: 2019 ident: 10.1016/j.jpdc.2024.104944_br0260 article-title: A review on swarm intelligence and evolutionary algorithms for solving flexible job shop scheduling problems publication-title: IEEE/CAA J. Autom. Sin. doi: 10.1109/JAS.2019.1911540 – start-page: 14 year: 2009 ident: 10.1016/j.jpdc.2024.104944_br0300 article-title: A lock-free multithreaded Monte-Carlo tree search algorithm – volume: vol. 38 start-page: 17531 year: 2024 ident: 10.1016/j.jpdc.2024.104944_br0090 article-title: Decentralized Monte Carlo tree search for partially observable multi-agent pathfinding – ident: 10.1016/j.jpdc.2024.104944_br0150 – volume: vol. 31 start-page: 103 year: 2021 ident: 10.1016/j.jpdc.2024.104944_br0200 article-title: Improving alphazero using Monte-Carlo graph search – volume: 8 start-page: 219 year: 1960 ident: 10.1016/j.jpdc.2024.104944_br0270 article-title: On the job-shop scheduling problem publication-title: Oper. Res. doi: 10.1287/opre.8.2.219 – volume: 34 start-page: 26 year: 2012 ident: 10.1016/j.jpdc.2024.104944_br0210 article-title: Ucd: upper confidence bound for rooted directed acyclic graphs publication-title: Knowl.-Based Syst. doi: 10.1016/j.knosys.2011.11.014 – volume: 7 start-page: 1 year: 2014 ident: 10.1016/j.jpdc.2024.104944_br0360 article-title: From bandits to Monte-Carlo tree search: the optimistic principle applied to optimization and planning publication-title: Found. Trends Mach. Learn. doi: 10.1561/2200000038 |
| SSID | ssj0011578 |
| Score | 2.4162195 |
| Snippet | Monte-Carlo Tree Search (MCTS) is an adaptive and heuristic tree-search algorithm designed to uncover sub-optimal actions at each decision-making point. This... |
| SourceID | crossref elsevier |
| SourceType | Enrichment Source Index Database Publisher |
| StartPage | 104944 |
| SubjectTerms | Job shop scheduling Monte Carlo tree search Parallel algorithms |
| Title | PPB-MCTS: A novel distributed-memory parallel partial-backpropagation Monte Carlo tree search algorithm |
| URI | https://dx.doi.org/10.1016/j.jpdc.2024.104944 |
| Volume | 193 |
| WOSCitedRecordID | wos001263563400001&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: PRVESC databaseName: Elsevier SD Freedom Collection Journals 2021 issn: 0743-7315 databaseCode: AIEXJ dateStart: 19950101 customDbUrl: isFulltext: true dateEnd: 99991231 titleUrlDefault: https://www.sciencedirect.com omitProxy: false ssIdentifier: ssj0011578 providerName: Elsevier |
| link | http://cvtisr.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwtV1Lb9swDBaydodd9h7a7gEddgtc2JZkW72lRfcCWgRbBmQnQ5bkNpnrBKkTdPsR-82jLMvOuqZYD7sIhmLTjvmBouiPJEJvVcBjHmXMo0FGYYMiA4_HRHqh1FyB-0wTJutmE_HpaTIe82Gv98vlwqyKuCyTqys-_6-qhjlQtkmdvYO6W6EwAcegdBhB7TD-k-KHw0Pv5Gj0xeacl7OVrj_D2M5WWnkXhlv7o29qfhcF_DY3MkThZUJ-B3MKBsZi4sTUrTKEkGJm6Oi63wRIRHE2W0yq84sNfm0r2ITk125cs9eXlVsqTQDasKh_wlCHdr6Jy3PRUoXfw-q97HLgOxbCpCwthj-LqhT9Q5Et1yMXIW1S-DoDZ8qjxsSmc7bWmJM1exqY8jX0RlNvow7T_elcmVKUId3vTv6zrva19a5lITqC2zQ1MlIjI7Uy7qHtMGYcrOT24OPx-FP7XSpgdm13T96kYVnG4PUnudnVWXNfRo_Rw0Y_eGDx8gT1dPkUPXI9PXBj4p-hMwefAzzANXjw3-DBTsd4A3hwDR5cgwcb8GALHtyC5zn6-u54dPTBa5pxeJL4fuVRrgi4OTKq_xpsQlWipOKZIESFsHpHIsqk5HmUBaFglMqY8pyQOA80gT0xIy_QVjkr9Y5h05EoSxjMJYxmvuJ-rv1cKqZZHuSc7KLAvbdUNpXqTcOUIt2ssV3Ub6-Z2zott57NnDrSxtO0HmQK6Lrlur073eUletDB_hXaqhZL_Rrdl6tqcrl400DrN5PQoJ4 |
| linkProvider | Elsevier |
| 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=PPB-MCTS%3A+A+novel+distributed-memory+parallel+partial-backpropagation+Monte+Carlo+tree+search+algorithm&rft.jtitle=Journal+of+parallel+and+distributed+computing&rft.au=Naderzadeh%2C+Yashar&rft.au=Grosu%2C+Daniel&rft.au=Chinnam%2C+Ratna+Babu&rft.date=2024-11-01&rft.issn=0743-7315&rft.volume=193&rft.spage=104944&rft_id=info:doi/10.1016%2Fj.jpdc.2024.104944&rft.externalDBID=n%2Fa&rft.externalDocID=10_1016_j_jpdc_2024_104944 |
| thumbnail_l | http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/lc.gif&issn=0743-7315&client=summon |
| thumbnail_m | http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/mc.gif&issn=0743-7315&client=summon |
| thumbnail_s | http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/sc.gif&issn=0743-7315&client=summon |