834 lines
30 KiB
HTML
834 lines
30 KiB
HTML
<h1 id="awesome-monte-carlo-tree-search-papers.">Awesome Monte Carlo
|
||
Tree Search Papers.</h1>
|
||
<a href="https://github.com/sindresorhus/awesome"><img
|
||
src="https://cdn.rawgit.com/sindresorhus/awesome/d7305f38d29fed78fa85652e3a63e154dd8e8829/media/badge.svg"
|
||
alt="Awesome" /></a> <a href="http://makeapullrequest.com"><img
|
||
src="https://img.shields.io/badge/PRs-welcome-brightgreen.svg?style=flat-square"
|
||
alt="PRs Welcome" /></a><a
|
||
href="https://github.com/benedekrozemberczki/awesome-monte-carlo-tree-search-papers/archive/master.zip"><img
|
||
src="https://img.shields.io/github/repo-size/benedekrozemberczki/awesome-monte-carlo-tree-search-papers.svg"
|
||
alt="repo size" /></a> <img
|
||
src="https://img.shields.io/github/license/benedekrozemberczki/awesome-tree-search-papers.svg?color=blue"
|
||
alt="License" /> <a
|
||
href="https://twitter.com/intent/follow?screen_name=benrozemberczki"><img
|
||
src="https://img.shields.io/twitter/follow/benrozemberczki?style=social&logo=twitter"
|
||
alt="benedekrozemberczki" /></a>
|
||
<p align="center">
|
||
<img width="600" src="tree.png">
|
||
</p>
|
||
<hr />
|
||
<p>A curated list of Monte Carlo tree search papers with implementations
|
||
from the following conferences/journals:</p>
|
||
<ul>
|
||
<li>Machine learning
|
||
<ul>
|
||
<li><a href="https://nips.cc/">NeurIPS</a></li>
|
||
<li><a href="https://icml.cc/">ICML</a></li>
|
||
</ul></li>
|
||
<li>Computer vision
|
||
<ul>
|
||
<li><a href="http://cvpr2019.thecvf.com/">CVPR</a></li>
|
||
<li><a href="http://iccv2019.thecvf.com/">ICCV</a></li>
|
||
</ul></li>
|
||
<li>Natural language processing
|
||
<ul>
|
||
<li><a href="http://www.acl2019.org/EN/index.xhtml">ACL</a></li>
|
||
</ul></li>
|
||
<li>Data
|
||
<ul>
|
||
<li><a href="https://www.kdd.org/">KDD</a></li>
|
||
</ul></li>
|
||
<li>Artificial intelligence
|
||
<ul>
|
||
<li><a href="https://www.aaai.org/">AAAI</a></li>
|
||
<li><a href="https://www.aistats.org/">AISTATS</a></li>
|
||
<li><a href="https://www.ijcai.org/">IJCAI</a></li>
|
||
<li><a href="http://www.auai.org/">UAI</a></li>
|
||
</ul></li>
|
||
<li>Robotics
|
||
<ul>
|
||
<li><a
|
||
href="https://www.journals.elsevier.com/robotics-and-autonomous-systems">RAS</a></li>
|
||
</ul></li>
|
||
<li>Games
|
||
<ul>
|
||
<li><a href="http://www.ieee-cig.org/">CIG</a></li>
|
||
</ul></li>
|
||
</ul>
|
||
<p>Similar collections about <a
|
||
href="https://github.com/benedekrozemberczki/awesome-graph-classification">graph
|
||
classification</a>, <a
|
||
href="https://github.com/benedekrozemberczki/awesome-gradient-boosting-papers">gradient
|
||
boosting</a>, <a
|
||
href="https://github.com/benedekrozemberczki/awesome-decision-tree-papers">classification/regression
|
||
trees</a>, <a
|
||
href="https://github.com/benedekrozemberczki/awesome-fraud-detection-papers">fraud
|
||
detection</a>, and <a
|
||
href="https://github.com/benedekrozemberczki/awesome-community-detection">community
|
||
detection</a> papers with implementations.</p>
|
||
<h2 id="section">2023</h2>
|
||
<ul>
|
||
<li><strong>Symbolic Physics Learner: Discovering governing equations
|
||
via Monte Carlo tree search (ICLR 2023)</strong>
|
||
<ul>
|
||
<li>Fangzheng Sun, Yang Liu, Jian-Xun Wang, Hao Sun</li>
|
||
<li><a href="https://arxiv.org/abs/2205.13134">[Paper]</a></li>
|
||
</ul></li>
|
||
</ul>
|
||
<h2 id="section-1">2022</h2>
|
||
<ul>
|
||
<li><strong>Finding Backdoors to Integer Programs: A Monte Carlo Tree
|
||
Search Framework (AAAI 2022)</strong>
|
||
<ul>
|
||
<li>Elias B. Khalil, Pashootan Vaezipoor, Bistra Dilkina</li>
|
||
<li><a href="https://arxiv.org/abs/2110.08423">[Paper]</a></li>
|
||
</ul></li>
|
||
<li><strong>NSGZero: Efficiently Learning Non-exploitable Policy in
|
||
Large-Scale Network Security Games with Neural Monte Carlo Tree Search
|
||
(AAAI 2022)</strong>
|
||
<ul>
|
||
<li>Wanqi Xue, Bo An, Chai Kiat Yeo</li>
|
||
<li><a href="https://arxiv.org/abs/2201.07224">[Paper]</a></li>
|
||
</ul></li>
|
||
<li><strong>Solving Disjunctive Temporal Networks with Uncertainty under
|
||
Restricted Time-Based Controllability Using Tree Search and Graph Neural
|
||
Networks (AAAI 2022)</strong>
|
||
<ul>
|
||
<li>Kevin Osanlou, Jeremy Frank, Andrei Bursuc, Tristan Cazenave, Eric
|
||
Jacopin, Christophe Guettier, J. Benton</li>
|
||
<li><a
|
||
href="https://ojs.aaai.org/index.php/AAAI/article/view/21224">[Paper]</a></li>
|
||
</ul></li>
|
||
<li><strong>Qubit Routing Using Graph Neural Network Aided Monte Carlo
|
||
Tree Search (AAAI 2022)</strong>
|
||
<ul>
|
||
<li>Animesh Sinha, Utkarsh Azad, Harjinder Singh</li>
|
||
<li><a href="https://arxiv.org/abs/2104.01992">[Paper]</a></li>
|
||
</ul></li>
|
||
<li><strong>Split Moves for Monte-Carlo Tree Search (AAAI 2022)</strong>
|
||
<ul>
|
||
<li>Jakub Kowalski, Maksymilian Mika, Wojciech Pawlik, Jakub Sutowicz,
|
||
Marek Szykula, Mark H. M. Winands</li>
|
||
<li><a href="https://arxiv.org/abs/2112.07761">[Paper]</a></li>
|
||
</ul></li>
|
||
<li><strong>Procrastinated Tree Search: Black-Box Optimization with
|
||
Delayed%2C Noisy and Multi-Fidelity Feedback (AAAI 2022)</strong>
|
||
<ul>
|
||
<li>Junxiong Wang, Debabrota Basu, Immanuel Trummer</li>
|
||
<li><a href="https://arxiv.org/abs/2110.07232">[Paper]</a></li>
|
||
</ul></li>
|
||
<li><strong>Enabling Arbitrary Translation Objectives with Adaptive Tree
|
||
Search (ICLR 2022)</strong>
|
||
<ul>
|
||
<li>Wang Ling, Wojciech Stokowiec, Domenic Donato, Chris Dyer, Lei Yu,
|
||
Laurent Sartran, Austin Matthews</li>
|
||
<li><a
|
||
href="https://en.x-mol.com/paper/article/1496885785571840000">[Paper]</a></li>
|
||
</ul></li>
|
||
<li><strong>What’s Wrong with Deep Learning in Tree Search for
|
||
Combinatorial Optimization (ICLR 2022)</strong>
|
||
<ul>
|
||
<li>Maximili1an Böther, Otto Kißig, Martin Taraz, Sarel Cohen, Karen
|
||
Seidel, Tobias Friedrich</li>
|
||
<li><a href="https://arxiv.org/abs/2201.10494">[Paper]</a></li>
|
||
</ul></li>
|
||
<li><strong>Anytime Capacity Expansion in Medical Residency Match by
|
||
Monte Carlo Tree Search (IJCAI 2022)</strong>
|
||
<ul>
|
||
<li>Kenshi Abe, Junpei Komiyama, Atsushi Iwasaki</li>
|
||
<li><a href="https://www.ijcai.org/proceedings/2022/1">[Paper]</a></li>
|
||
</ul></li>
|
||
<li><strong>Fast and Accurate User Cold-Start Learning Using Monte Carlo
|
||
Tree Search (RECSYS 2022)</strong>
|
||
<ul>
|
||
<li>Dilina Chandika Rajapakse, Douglas Leith</li>
|
||
<li><a
|
||
href="https://www.scss.tcd.ie/Doug.Leith/pubs/recsys22-35.pdf">[Paper]</a></li>
|
||
</ul></li>
|
||
</ul>
|
||
<h2 id="section-2">2021</h2>
|
||
<ul>
|
||
<li><strong>Learning to Stop: Dynamic Simulation Monte-Carlo Tree Search
|
||
(AAAI 2021)</strong>
|
||
<ul>
|
||
<li>Li-Cheng Lan, Ti-Rong Wu, I-Chen Wu, Cho-Jui Hsieh</li>
|
||
<li><a href="https://arxiv.org/abs/2012.07910">[Paper]</a></li>
|
||
</ul></li>
|
||
<li><strong>Dec-SGTS: Decentralized Sub-Goal Tree Search for Multi-Agent
|
||
Coordination (AAAI 2021)</strong>
|
||
<ul>
|
||
<li>Minglong Li, Zhongxuan Cai, Wenjing Yang, Lixia Wu, Yinghui Xu, Ji
|
||
Wang</li>
|
||
<li><a
|
||
href="https://ojs.aaai.org/index.php/AAAI/article/view/17345">[Paper]</a></li>
|
||
</ul></li>
|
||
<li><strong>Improved POMDP Tree Search Planning with Prioritized Action
|
||
Branching (AAAI 2021)</strong>
|
||
<ul>
|
||
<li>John Mern, Anil Yildiz, Lawrence Bush, Tapan Mukerji, Mykel J.
|
||
Kochenderfer</li>
|
||
<li><a href="https://arxiv.org/abs/2010.03599">[Paper]</a></li>
|
||
</ul></li>
|
||
<li><strong>Dynamic Automaton-Guided Reward Shaping for Monte Carlo Tree
|
||
Search (AAAI 2021)</strong>
|
||
<ul>
|
||
<li>Alvaro Velasquez, Brett Bissey, Lior Barak, Andre Beckus, Ismail
|
||
Alkhouri, Daniel Melcer, George K. Atia</li>
|
||
<li><a
|
||
href="https://ojs.aaai.org/index.php/AAAI/article/view/17427">[Paper]</a></li>
|
||
</ul></li>
|
||
<li><strong>Single Player Monte-Carlo Tree Search Based on the
|
||
Plackett-Luce Model (AAAI 2021)</strong>
|
||
<ul>
|
||
<li>Felix Mohr, Viktor Bengs, Eyke Hüllermeier</li>
|
||
<li><a
|
||
href="https://ojs.aaai.org/index.php/AAAI/article/view/17468">[Paper]</a></li>
|
||
</ul></li>
|
||
<li><strong>Learning to Pack: A Data-Driven Tree Search Algorithm for
|
||
Large-Scale 3D Bin Packing Problem (CIKM 2021)</strong>
|
||
<ul>
|
||
<li>Qianwen Zhu, Xihan Li, Zihan Zhang, Zhixing Luo, Xialiang Tong,
|
||
Mingxuan Yuan, Jia Zeng</li>
|
||
<li><a
|
||
href="https://dl.acm.org/doi/abs/10.1145/3459637.3481933">[Paper]</a></li>
|
||
</ul></li>
|
||
<li><strong>Practical Massively Parallel Monte-Carlo Tree Search Applied
|
||
to Molecular Design (ICLR 2021)</strong>
|
||
<ul>
|
||
<li>Xiufeng Yang, Tanuj Kr Aasawat, Kazuki Yoshizoe</li>
|
||
<li><a href="https://arxiv.org/abs/2006.10504">[Paper]</a></li>
|
||
</ul></li>
|
||
<li><strong>Convex Regularization in Monte-Carlo Tree Search (ICML
|
||
2021)</strong>
|
||
<ul>
|
||
<li>Tuan Dam, Carlo D’Eramo, Jan Peters, Joni Pajarinen</li>
|
||
<li><a href="https://arxiv.org/abs/2007.00391">[Paper]</a></li>
|
||
</ul></li>
|
||
<li><strong>Combining Tree Search and Action Prediction for
|
||
State-of-the-Art Performance in DouDiZhu (IJCAI 2021)</strong>
|
||
<ul>
|
||
<li>Yunsheng Zhang, Dong Yan, Bei Shi, Haobo Fu, Qiang Fu, Hang Su, Jun
|
||
Zhu, Ning Chen</li>
|
||
<li><a
|
||
href="https://www.ijcai.org/proceedings/2021/470">[Paper]</a></li>
|
||
</ul></li>
|
||
</ul>
|
||
<h2 id="section-3">2020</h2>
|
||
<ul>
|
||
<li><strong>Monte Carlo Tree Search in Continuous Spaces Using Voronoi
|
||
Optimistic Optimization with Regret Bounds (AAAI 2020)</strong>
|
||
<ul>
|
||
<li>Beomjoon Kim, Kyungjae Lee, Sungbin Lim, Leslie Pack Kaelbling,
|
||
Tomás Lozano-Pérez</li>
|
||
<li><a
|
||
href="https://www.aaai.org/Papers/AAAI/2020GB/AAAI-KimB.1282.pdf">[Paper]</a></li>
|
||
</ul></li>
|
||
<li><strong>Neural Architecture Search Using Deep Neural Networks and
|
||
Monte Carlo Tree Search (AAAI 2020)</strong>
|
||
<ul>
|
||
<li>Linnan Wang, Yiyang Zhao, Yuu Jinnai, Yuandong Tian, Rodrigo
|
||
Fonseca</li>
|
||
<li><a href="https://arxiv.org/abs/1805.07440">[Paper]</a></li>
|
||
<li><a
|
||
href="https://github.com/linnanwang/AlphaX-NASBench101">[Code]</a></li>
|
||
</ul></li>
|
||
<li><strong>Monte-Carlo Tree Search in Continuous Action Spaces with
|
||
Value Gradients (AAAI 2020)</strong>
|
||
<ul>
|
||
<li>Jongmin Lee, Wonseok Jeon, Geon-Hyeong Kim, Kee-Eung Kim</li>
|
||
<li><a
|
||
href="https://www.ijcai.org/Proceedings/16/Papers/104.pdf">[Paper]</a></li>
|
||
<li><a href="https://github.com/leekwoon/KR-DL-UCT">[Code]</a></li>
|
||
</ul></li>
|
||
<li><strong>Approximate Inference in Discrete Distributions with Monte
|
||
Carlo Tree Search and Value Functions (AISTATS 2020)</strong>
|
||
<ul>
|
||
<li>Lars Buesing, Nicolas Heess, Theophane Weber</li>
|
||
<li><a href="https://arxiv.org/abs/1910.06862">[Paper]</a></li>
|
||
</ul></li>
|
||
<li><strong>Watch the Unobserved: A Simple Approach to Parallelizing
|
||
Monte Carlo Tree Search (ICLR 2020)</strong>
|
||
<ul>
|
||
<li>Anji Liu, Jianshu Chen, Mingze Yu, Yu Zhai, Xuewen Zhou, Ji Liu</li>
|
||
<li><a
|
||
href="https://openreview.net/forum?id=BJlQtJSKDB">[Paper]</a></li>
|
||
<li><a href="https://github.com/brilee/python_uct">[Code]</a></li>
|
||
</ul></li>
|
||
<li><strong>Information Particle Filter Tree: An Online Algorithm for
|
||
POMDPs with Belief-Based Rewards on Continuous Domains (ICML
|
||
2020)</strong>
|
||
<ul>
|
||
<li>Johannes Fischer, Ömer Sahin Tas</li>
|
||
<li><a
|
||
href="http://proceedings.mlr.press/v119/fischer20a.html">[Paper]</a></li>
|
||
<li><a
|
||
href="https://github.com/johannes-fischer/icml2020_ipft">[Code]</a></li>
|
||
</ul></li>
|
||
<li><strong>Sub-Goal Trees a Framework for Goal-Based Reinforcement
|
||
Learning (ICML 2020)</strong>
|
||
<ul>
|
||
<li>Tom Jurgenson, Or Avner, Edward Groshev, Aviv Tamar</li>
|
||
<li><a href="https://arxiv.org/abs/2002.12361">[Paper]</a></li>
|
||
</ul></li>
|
||
<li><strong>Monte-Carlo Tree Search for Scalable Coalition Formation
|
||
(IJCAI 2020)</strong>
|
||
<ul>
|
||
<li>Feng Wu, Sarvapali D. Ramchurn</li>
|
||
<li><a href="https://www.ijcai.org/Proceedings/2020/57">[Paper]</a></li>
|
||
</ul></li>
|
||
<li><strong>Generalized Mean Estimation in Monte-Carlo Tree Search
|
||
(IJCAI 2020)</strong>
|
||
<ul>
|
||
<li>Tuan Dam, Pascal Klink, Carlo D’Eramo, Jan Peters, Joni
|
||
Pajarinen</li>
|
||
<li><a href="https://arxiv.org/abs/1911.00384">[Paper]</a></li>
|
||
</ul></li>
|
||
<li><strong>Sparse Tree Search Optimality Guarantees in POMDPs with
|
||
Continuous Observation Spaces (IJCAI 2020)</strong>
|
||
<ul>
|
||
<li>Michael H. Lim, Claire Tomlin, Zachary N. Sunberg</li>
|
||
<li><a href="https://arxiv.org/abs/1910.04332">[Paper]</a></li>
|
||
</ul></li>
|
||
<li><strong>Mix and Match: An Optimistic Tree-Search Approach for
|
||
Learning Models from Mixture Distributions (NeurIPS 2020)</strong>
|
||
<ul>
|
||
<li>Matthew Faw, Rajat Sen, Karthikeyan Shanmugam, Constantine
|
||
Caramanis, Sanjay Shakkottai</li>
|
||
<li><a href="https://arxiv.org/abs/1907.10154">[Paper]</a></li>
|
||
</ul></li>
|
||
<li><strong>Extracting Knowledge from Web Text with Monte Carlo Tree
|
||
Search (WWW 2020)</strong>
|
||
<ul>
|
||
<li>Guiliang Liu, Xu Li, Jiakang Wang, Mingming Sun, Ping Li</li>
|
||
<li><a
|
||
href="https://dl.acm.org/doi/abs/10.1145/3366423.3380010">[Paper]</a></li>
|
||
</ul></li>
|
||
</ul>
|
||
<h2 id="section-4">2019</h2>
|
||
<ul>
|
||
<li><strong>ACE: An Actor Ensemble Algorithm for Continuous Control with
|
||
Tree Search (AAAI 2019)</strong>
|
||
<ul>
|
||
<li>Shangtong Zhang, Hengshuai Yao</li>
|
||
<li><a href="https://arxiv.org/abs/1811.02696">[Paper]</a></li>
|
||
<li><a href="https://github.com/ShangtongZhang/DeepRL">[Code]</a></li>
|
||
</ul></li>
|
||
<li><strong>A Monte Carlo Tree Search Player for Birds of a Feather
|
||
Solitaire (AAAI 2019)</strong>
|
||
<ul>
|
||
<li>Christian Roberson, Katarina Sperduto</li>
|
||
<li><a
|
||
href="https://aaai.org/ojs/index.php/AAAI/article/view/5036">[Paper]</a></li>
|
||
<li><a
|
||
href="http://cs.gettysburg.edu/~tneller/puzzles/boaf/">[Code]</a></li>
|
||
</ul></li>
|
||
<li><strong>Vine Copula Structure Learning via Monte Carlo Tree Search
|
||
(AISTATS 2019)</strong>
|
||
<ul>
|
||
<li>Bo Chang, Shenyi Pan, Harry Joe</li>
|
||
<li><a
|
||
href="http://proceedings.mlr.press/v89/chang19a/chang19a.pdf">[Paper]</a></li>
|
||
<li><a href="https://github.com/changebo/Vine_MCTS">[Code]</a></li>
|
||
</ul></li>
|
||
<li><strong>Noisy Blackbox Optimization using Multi-fidelity Queries: A
|
||
Tree Search Approach (AISTATS 2019)</strong>
|
||
<ul>
|
||
<li>Rajat Sen, Kirthevasan Kandasamy, Sanjay Shakkottai</li>
|
||
<li><a href="https://arxiv.org/abs/1810.10482">[Paper]</a></li>
|
||
<li><a href="https://github.com/rajatsen91/MFTREE_DET">[Code]</a></li>
|
||
</ul></li>
|
||
<li><strong>Reinforcement Learning Based Monte Carlo Tree Search for
|
||
Temporal Path Discovery (ICDM 2019)</strong>
|
||
<ul>
|
||
<li>Pengfei Ding, Guanfeng Liu, Pengpeng Zhao, An Liu, Zhixu Li, Kai
|
||
Zheng</li>
|
||
<li><a
|
||
href="https://zheng-kai.com/paper/icdm_2019_b.pdf">[Paper]</a></li>
|
||
</ul></li>
|
||
<li><strong>Monte Carlo Tree Search for Policy Optimization (IJCAI
|
||
2019)</strong>
|
||
<ul>
|
||
<li>Xiaobai Ma, Katherine Rose Driggs-Campbell, Zongzhang Zhang, Mykel
|
||
J. Kochenderfer</li>
|
||
<li><a
|
||
href="https://www.ijcai.org/proceedings/2019/0432.pdf">[Paper]</a></li>
|
||
</ul></li>
|
||
<li><strong>Subgoal-Based Temporal Abstraction in Monte-Carlo Tree
|
||
Search (IJCAI 2019)</strong>
|
||
<ul>
|
||
<li>Thomas Gabor, Jan Peter, Thomy Phan, Christian Meyer, Claudia
|
||
Linnhoff-Popien</li>
|
||
<li><a
|
||
href="https://www.ijcai.org/proceedings/2019/0772.pdf">[Paper]</a></li>
|
||
<li><a href="https://github.com/jnptr/subgoal-mcts">[Code]</a></li>
|
||
</ul></li>
|
||
<li><strong>Automated Machine Learning with Monte-Carlo Tree Search
|
||
(IJCAI 2019)</strong>
|
||
<ul>
|
||
<li>Herilalaina Rakotoarison, Marc Schoenauer, Michèle Sebag</li>
|
||
<li><a
|
||
href="https://www.ijcai.org/proceedings/2019/0457.pdf">[Paper]</a></li>
|
||
<li><a href="https://github.com/herilalaina/mosaic_ml">[Code]</a></li>
|
||
</ul></li>
|
||
<li><strong>Multiple Policy Value Monte Carlo Tree Search (IJCAI
|
||
2019)</strong>
|
||
<ul>
|
||
<li>Li-Cheng Lan, Wei Li, Ting-Han Wei, I-Chen Wu</li>
|
||
<li><a
|
||
href="https://www.ijcai.org/proceedings/2019/0653.pdf">[Paper]</a></li>
|
||
</ul></li>
|
||
<li><strong>Learning Compositional Neural Programs with Recursive Tree
|
||
Search and Planning (NeurIPS 2019)</strong>
|
||
<ul>
|
||
<li>Thomas Pierrot, Guillaume Ligner, Scott E. Reed, Olivier Sigaud,
|
||
Nicolas Perrin, Alexandre Laterre, David Kas, Karim Beguir, Nando de
|
||
Freitas</li>
|
||
<li><a href="https://arxiv.org/abs/1905.12941">[Paper]</a></li>
|
||
</ul></li>
|
||
</ul>
|
||
<h2 id="section-5">2018</h2>
|
||
<ul>
|
||
<li><strong>Monte Carlo Methods for the Game Kingdomino (CIG
|
||
2018)</strong>
|
||
<ul>
|
||
<li>Magnus Gedda, Mikael Z. Lagerkvist, Martin Butler</li>
|
||
<li><a href="https://arxiv.org/abs/1807.04458">[Paper]</a></li>
|
||
<li><a href="https://github.com/mgedda/kdom-ai">[Code]</a></li>
|
||
<li><a href="https://github.com/mratin/kdom">[Game Server]</a></li>
|
||
</ul></li>
|
||
<li><strong>Reset-free Trial-and-Error Learning for Robot Damage
|
||
Recovery (RAS 2018)</strong>
|
||
<ul>
|
||
<li>Konstantinos Chatzilygeroudis, Vassilis Vassiliades, Jean-Baptiste
|
||
Mouret</li>
|
||
<li><a href="https://arxiv.org/pdf/1610.04213.pdf">[Paper]</a></li>
|
||
<li><a
|
||
href="https://github.com/resibots/chatzilygeroudis_2018_rte">[Code]</a></li>
|
||
<li><a href="https://github.com/resibots/mcts">[MCTS C++
|
||
Library]</a></li>
|
||
</ul></li>
|
||
<li><strong>Memory-Augmented Monte Carlo Tree Search (AAAI
|
||
2018)</strong>
|
||
<ul>
|
||
<li>Chenjun Xiao, Jincheng Mei, Martin Müller</li>
|
||
<li><a
|
||
href="https://aaai.org/ocs/index.php/AAAI/AAAI18/paper/view/17139">[Paper]</a></li>
|
||
</ul></li>
|
||
<li><strong>Feedback-Based Tree Search for Reinforcement Learning (ICML
|
||
2018)</strong>
|
||
<ul>
|
||
<li>Daniel R. Jiang, Emmanuel Ekwedike, Han Liu</li>
|
||
<li><a href="https://arxiv.org/abs/1805.05935">[Paper]</a></li>
|
||
</ul></li>
|
||
<li><strong>Extended Increasing Cost Tree Search for Non-Unit Cost
|
||
Domains (IJCAI 2018)</strong>
|
||
<ul>
|
||
<li>Thayne T. Walker, Nathan R. Sturtevant, Ariel Felner</li>
|
||
<li><a href="https://www.ijcai.org/proceedings/2018/74">[Paper]</a></li>
|
||
</ul></li>
|
||
<li><strong>Three-Head Neural Network Architecture for Monte Carlo Tree
|
||
Search (IJCAI 2018)</strong>
|
||
<ul>
|
||
<li>Chao Gao, Martin Müller, Ryan Hayward</li>
|
||
<li><a
|
||
href="https://www.ijcai.org/proceedings/2018/523">[Paper]</a></li>
|
||
</ul></li>
|
||
<li><strong>Bidding in Periodic Double Auctions Using Heuristics and
|
||
Dynamic Monte Carlo Tree Search (IJCAI 2018)</strong>
|
||
<ul>
|
||
<li>Moinul Morshed Porag Chowdhury, Christopher Kiekintveld, Son Tran,
|
||
William Yeoh</li>
|
||
<li><a href="https://www.ijcai.org/proceedings/2018/23">[Paper]</a></li>
|
||
</ul></li>
|
||
<li><strong>Combinatorial Optimization with Graph Convolutional Networks
|
||
and Guided Tree Search (NIPS 2018)</strong>
|
||
<ul>
|
||
<li>Zhuwen Li, Qifeng Chen, Vladlen Koltun</li>
|
||
<li><a href="https://arxiv.org/abs/1810.10659">[Paper]</a></li>
|
||
</ul></li>
|
||
<li><strong>M-Walk: Learning to Walk over Graphs using Monte Carlo Tree
|
||
Search (NIPS 2018)</strong>
|
||
<ul>
|
||
<li>Yelong Shen, Jianshu Chen, Po-Sen Huang, Yuqing Guo, Jianfeng
|
||
Gao</li>
|
||
<li><a href="https://arxiv.org/abs/1802.04394">[Paper]</a></li>
|
||
</ul></li>
|
||
<li><strong>Single-Agent Policy Tree Search With Guarantees (NIPS
|
||
2018)</strong>
|
||
<ul>
|
||
<li>Laurent Orseau, Levi Lelis, Tor Lattimore, Theophane Weber</li>
|
||
<li><a href="https://arxiv.org/abs/1811.10928">[Paper]</a></li>
|
||
</ul></li>
|
||
<li><strong>Monte-Carlo Tree Search for Constrained POMDPs (NIPS
|
||
2018)</strong>
|
||
<ul>
|
||
<li>Jongmin Lee, Geon-hyeong Kim, Pascal Poupart, Kee-Eung Kim</li>
|
||
<li><a
|
||
href="https://cs.uwaterloo.ca/~ppoupart/publications/constrained-pomdps/mcts-constrained-pomdps-paper.pdf">[Paper]</a></li>
|
||
</ul></li>
|
||
</ul>
|
||
<h2 id="section-6">2017</h2>
|
||
<ul>
|
||
<li><strong>An Analysis of Monte Carlo Tree Search (AAAI 2017)</strong>
|
||
<ul>
|
||
<li>Steven James, George Dimitri Konidaris, Benjamin Rosman</li>
|
||
<li><a
|
||
href="https://aaai.org/ocs/index.php/AAAI/AAAI17/paper/view/14886">[Paper]</a></li>
|
||
</ul></li>
|
||
<li><strong>Beyond Monte Carlo Tree Search: Playing Go with Deep
|
||
Alternative Neural Network and Long-Term Evaluation (AAAI 2017)</strong>
|
||
<ul>
|
||
<li>Jinzhuo Wang, Wenmin Wang, Ronggang Wang, Wen Gao</li>
|
||
<li><a href="https://arxiv.org/abs/1706.04052">[Paper]</a></li>
|
||
</ul></li>
|
||
<li><strong>Designing Better Playlists with Monte Carlo Tree Search
|
||
(AAAI 2017)</strong>
|
||
<ul>
|
||
<li>Elad Liebman, Piyush Khandelwal, Maytal Saar-Tsechansky, Peter
|
||
Stone</li>
|
||
<li><a
|
||
href="https://www.cs.utexas.edu/~pstone/Papers/bib2html-links/IAAI2017-eladlieb.pdf">[Paper]</a></li>
|
||
</ul></li>
|
||
<li><strong>Learning in POMDPs with Monte Carlo Tree Search (ICML
|
||
2017)</strong>
|
||
<ul>
|
||
<li>Sammie Katt, Frans A. Oliehoek, Christopher Amato</li>
|
||
<li><a href="https://arxiv.org/abs/1806.05631">[Paper]</a></li>
|
||
</ul></li>
|
||
<li><strong>Learning to Run Heuristics in Tree Search (IJCAI
|
||
2017)</strong>
|
||
<ul>
|
||
<li>Elias B. Khalil, Bistra Dilkina, George L. Nemhauser, Shabbir Ahmed,
|
||
Yufen Shao</li>
|
||
<li><a href="https://www.ijcai.org/proceedings/2017/92">[Paper]</a></li>
|
||
</ul></li>
|
||
<li><strong>Estimating the Size of Search Trees by Sampling with Domain
|
||
Knowledge (IJCAI 2017)</strong>
|
||
<ul>
|
||
<li>Gleb Belov, Samuel Esler, Dylan Fernando, Pierre Le Bodic, George L.
|
||
Nemhauser</li>
|
||
<li><a href="https://www.ijcai.org/proceedings/2017/67">[Paper]</a></li>
|
||
</ul></li>
|
||
<li><strong>A Monte Carlo Tree Search Approach to Active Malware
|
||
Analysis (IJCAI 2017)</strong>
|
||
<ul>
|
||
<li>Riccardo Sartea, Alessandro Farinelli</li>
|
||
<li><a
|
||
href="https://www.ijcai.org/proceedings/2017/535">[Paper]</a></li>
|
||
</ul></li>
|
||
<li><strong>Monte-Carlo Tree Search by Best Arm Identification (NIPS
|
||
2017)</strong>
|
||
<ul>
|
||
<li>Emilie Kaufmann, Wouter M. Koolen</li>
|
||
<li><a href="https://arxiv.org/abs/1706.02986">[Paper]</a></li>
|
||
</ul></li>
|
||
<li><strong>Thinking Fast and Slow with Deep Learning and Tree Search
|
||
(NIPS 2017)</strong>
|
||
<ul>
|
||
<li>Thomas Anthony, Zheng Tian, David Barber</li>
|
||
<li><a href="https://arxiv.org/abs/1705.08439">[Paper]</a></li>
|
||
</ul></li>
|
||
<li><strong>Monte-Carlo Tree Search using Batch Value of Perfect
|
||
Information (UAI 2017)</strong>
|
||
<ul>
|
||
<li>Shahaf S. Shperberg, Solomon Eyal Shimony, Ariel Felner</li>
|
||
<li><a
|
||
href="http://auai.org/uai2017/proceedings/papers/37.pdf">[Paper]</a></li>
|
||
</ul></li>
|
||
</ul>
|
||
<h2 id="section-7">2016</h2>
|
||
<ul>
|
||
<li><strong>Using Domain Knowledge to Improve Monte-Carlo Tree Search
|
||
Performance in Parameterized Poker Squares (AAAI 2016)</strong>
|
||
<ul>
|
||
<li>Robert Arrington, Clay Langley, Steven Bogaerts</li>
|
||
<li><a
|
||
href="https://www.aaai.org/ocs/index.php/AAAI/AAAI16/paper/view/11809">[Paper]</a></li>
|
||
</ul></li>
|
||
<li><strong>Monte Carlo Tree Search for Multi-Robot Task Allocation
|
||
(AAAI 2016)</strong>
|
||
<ul>
|
||
<li>Bilal Kartal, Ernesto Nunes, Julio Godoy, Maria L. Gini</li>
|
||
<li><a
|
||
href="https://www.aaai.org/ocs/index.php/AAAI/AAAI16/paper/view/12154">[Paper]</a></li>
|
||
</ul></li>
|
||
<li><strong>Large Scale Hard Sample Mining with Monte Carlo Tree Search
|
||
(CVPR 2016)</strong>
|
||
<ul>
|
||
<li>Olivier Canévet, François Fleuret</li>
|
||
<li><a
|
||
href="https://www.idiap.ch/~fleuret/papers/canevet-fleuret-cvpr2016.pdf">[Paper]</a></li>
|
||
</ul></li>
|
||
<li><strong>On the Analysis of Complex Backup Strategies in Monte Carlo
|
||
Tree Search (ICML 2016)</strong>
|
||
<ul>
|
||
<li>Piyush Khandelwal, Elad Liebman, Scott Niekum, Peter Stone</li>
|
||
<li><a
|
||
href="https://www.cs.utexas.edu/~eladlieb/ICML2016.pdf">[Paper]</a></li>
|
||
</ul></li>
|
||
<li><strong>Deep Learning for Reward Design to Improve Monte Carlo Tree
|
||
Search in ATARI Games (IJCAI 2016)</strong>
|
||
<ul>
|
||
<li>Xiaoxiao Guo, Satinder P. Singh, Richard L. Lewis, Honglak Lee</li>
|
||
<li><a href="https://arxiv.org/abs/1604.07095">[Paper]</a></li>
|
||
</ul></li>
|
||
<li><strong>Monte Carlo Tree Search in Continuous Action Spaces with
|
||
Execution Uncertainty (IJCAI 2016)</strong>
|
||
<ul>
|
||
<li>Timothy Yee, Viliam Lisý, Michael H. Bowling</li>
|
||
<li><a
|
||
href="https://www.ijcai.org/Proceedings/16/Papers/104.pdf">[Paper]</a></li>
|
||
</ul></li>
|
||
<li><strong>Learning Predictive State Representations via Monte-Carlo
|
||
Tree Search (IJCAI 2016)</strong>
|
||
<ul>
|
||
<li>Yunlong Liu, Hexing Zhu, Yifeng Zeng, Zongxiong Dai</li>
|
||
<li><a
|
||
href="https://pdfs.semanticscholar.org/8056/df11094fc96d76826403f8b339dc14aa821f.pdf">[Paper]</a></li>
|
||
</ul></li>
|
||
</ul>
|
||
<h2 id="section-8">2015</h2>
|
||
<ul>
|
||
<li><strong>Efficient Globally Optimal Consensus Maximisation with Tree
|
||
Search (CVPR 2015)</strong>
|
||
<ul>
|
||
<li>Tat-Jun Chin, Pulak Purkait, Anders P. Eriksson, David Suter</li>
|
||
<li><a
|
||
href="https://zpascal.net/cvpr2015/Chin_Efficient_Globally_Optimal_2015_CVPR_paper.pdf">[Paper]</a></li>
|
||
</ul></li>
|
||
<li><strong>Interplanetary Trajectory Planning with Monte Carlo Tree
|
||
Search (IJCAI 2015)</strong>
|
||
<ul>
|
||
<li>Daniel Hennes, Dario Izzo</li>
|
||
<li><a
|
||
href="https://pdfs.semanticscholar.org/ce42/53ca1c5b16e96cdbefae75649cd2588f42f3.pdf">[Paper]</a></li>
|
||
</ul></li>
|
||
</ul>
|
||
<h2 id="section-9">2014</h2>
|
||
<ul>
|
||
<li><strong>State Aggregation in Monte Carlo Tree Search (AAAI
|
||
2014)</strong>
|
||
<ul>
|
||
<li>Jesse Hostetler, Alan Fern, Tom Dietterich</li>
|
||
<li><a
|
||
href="https://www.aaai.org/ocs/index.php/AAAI/AAAI14/paper/download/8439/8712">[Paper]</a></li>
|
||
</ul></li>
|
||
<li><strong>Deep Learning for Real-Time Atari Game Play Using Offline
|
||
Monte-Carlo Tree Search Planning (NIPS 2014)</strong>
|
||
<ul>
|
||
<li>Xiaoxiao Guo, Satinder P. Singh, Honglak Lee, Richard L. Lewis,
|
||
Xiaoshi Wang</li>
|
||
<li><a
|
||
href="https://web.eecs.umich.edu/~baveja/Papers/UCTtoCNNsAtariGames-FinalVersion.pdf">[Paper]</a></li>
|
||
</ul></li>
|
||
<li><strong>Learning Partial Policies to Speedup MDP Tree Search (UAI
|
||
2014)</strong>
|
||
<ul>
|
||
<li>Jervis Pinto, Alan Fern</li>
|
||
<li><a
|
||
href="http://www.jmlr.org/papers/volume18/15-251/15-251.pdf">[Paper]</a></li>
|
||
</ul></li>
|
||
</ul>
|
||
<h2 id="section-10">2013</h2>
|
||
<ul>
|
||
<li><strong>Monte Carlo Tree Search for Scheduling Activity Recognition
|
||
(ICCV 2013)</strong>
|
||
<ul>
|
||
<li>Mohamed R. Amer, Sinisa Todorovic, Alan Fern, Song-Chun Zhu</li>
|
||
<li><a
|
||
href="http://citeseerx.ist.psu.edu/viewdoc/download?doi=10.1.1.405.5916&rep=rep1&type=pdf">[Paper]</a></li>
|
||
</ul></li>
|
||
<li><strong>Convergence of Monte Carlo Tree Search in Simultaneous Move
|
||
Games (NIPS 2013)</strong>
|
||
<ul>
|
||
<li>Viliam Lisý, Vojtech Kovarík, Marc Lanctot, Branislav Bosanský</li>
|
||
<li><a
|
||
href="https://papers.nips.cc/paper/5145-convergence-of-monte-carlo-tree-search-in-simultaneous-move-games">[Paper]</a></li>
|
||
</ul></li>
|
||
<li><strong>Bayesian Mixture Modelling and Inference based Thompson
|
||
Sampling in Monte-Carlo Tree Search (NIPS 2013)</strong>
|
||
<ul>
|
||
<li>Aijun Bai, Feng Wu, Xiaoping Chen</li>
|
||
<li><a
|
||
href="https://papers.nips.cc/paper/5111-bayesian-mixture-modelling-and-inference-based-thompson-sampling-in-monte-carlo-tree-search">[Paper]</a></li>
|
||
</ul></li>
|
||
</ul>
|
||
<h2 id="section-11">2012</h2>
|
||
<ul>
|
||
<li><strong>Generalized Monte-Carlo Tree Search Extensions for General
|
||
Game Playing (AAAI 2012)</strong>
|
||
<ul>
|
||
<li>Hilmar Finnsson</li>
|
||
<li><a
|
||
href="https://www.aaai.org/ocs/index.php/AAAI/AAAI12/paper/viewFile/4935/5300">[Paper]</a></li>
|
||
</ul></li>
|
||
</ul>
|
||
<h2 id="section-12">2011</h2>
|
||
<ul>
|
||
<li><strong>A Local Monte Carlo Tree Search Approach in Deterministic
|
||
Planning (AAAI 2011)</strong>
|
||
<ul>
|
||
<li>Fan Xie, Hootan Nakhost, Martin Müller</li>
|
||
<li><a
|
||
href="http://citeseerx.ist.psu.edu/viewdoc/download?doi=10.1.1.699.3833&rep=rep1&type=pdf">[Paper]</a></li>
|
||
</ul></li>
|
||
<li><strong>Real-Time Solving of Quantified CSPs Based on Monte-Carlo
|
||
Game Tree Search (IJCAI 2011)</strong>
|
||
<ul>
|
||
<li>Satomi Baba, Yongjoon Joe, Atsushi Iwasaki, Makoto Yokoo</li>
|
||
<li><a
|
||
href="https://www.ijcai.org/Proceedings/11/Papers/116.pdf">[Paper]</a></li>
|
||
</ul></li>
|
||
<li><strong>Nested Rollout Policy Adaptation for Monte Carlo Tree Search
|
||
(IJCAI 2011)</strong>
|
||
<ul>
|
||
<li>Christopher D. Rosin</li>
|
||
<li><a
|
||
href="https://www.ijcai.org/Proceedings/11/Papers/115.pdf">[Paper]</a></li>
|
||
</ul></li>
|
||
<li><strong>Variance Reduction in Monte-Carlo Tree Search (NIPS
|
||
2011)</strong>
|
||
<ul>
|
||
<li>Joel Veness, Marc Lanctot, Michael H. Bowling</li>
|
||
<li><a
|
||
href="https://papers.nips.cc/paper/4288-variance-reduction-in-monte-carlo-tree-search">[Paper]</a></li>
|
||
</ul></li>
|
||
<li><strong>Learning Is Planning: Near Bayes-Optimal Reinforcement
|
||
Learning via Monte-Carlo Tree Search (UAI 2011)</strong>
|
||
<ul>
|
||
<li>John Asmuth, Michael L. Littman</li>
|
||
<li><a href="https://arxiv.org/abs/1202.3699">[Paper]</a></li>
|
||
</ul></li>
|
||
</ul>
|
||
<h2 id="section-13">2010</h2>
|
||
<ul>
|
||
<li><strong>Understanding the Success of Perfect Information Monte Carlo
|
||
Sampling in Game Tree Search (AAAI 2010)</strong>
|
||
<ul>
|
||
<li>Jeffrey Richard Long, Nathan R. Sturtevant, Michael Buro, Timothy
|
||
Furtak</li>
|
||
<li><a
|
||
href="https://pdfs.semanticscholar.org/011e/2c79575721764c127e210c9d8105a6305e70.pdf">[Paper]</a></li>
|
||
</ul></li>
|
||
<li><strong>Bayesian Inference in Monte-Carlo Tree Search (UAI
|
||
2010)</strong>
|
||
<ul>
|
||
<li>Gerald Tesauro, V. T. Rajan, Richard Segal</li>
|
||
<li><a href="https://arxiv.org/abs/1203.3519">[Paper]</a></li>
|
||
</ul></li>
|
||
</ul>
|
||
<h2 id="section-14">2009</h2>
|
||
<ul>
|
||
<li><strong>Monte Carlo Tree Search Techniques in the Game of Kriegspiel
|
||
(IJCAI 2009)</strong>
|
||
<ul>
|
||
<li>Paolo Ciancarini, Gian Piero Favini</li>
|
||
<li><a
|
||
href="https://www.aaai.org/ocs/index.php/IJCAI/IJCAI-09/paper/viewFile/396/693">[Paper]</a></li>
|
||
</ul></li>
|
||
<li><strong>Bootstrapping from Game Tree Search (NIPS 2009)</strong>
|
||
<ul>
|
||
<li>Joel Veness, David Silver, William T. B. Uther, Alan Blair</li>
|
||
<li><a
|
||
href="https://papers.nips.cc/paper/3722-bootstrapping-from-game-tree-search">[Paper]</a></li>
|
||
</ul></li>
|
||
</ul>
|
||
<h2 id="section-15">2008</h2>
|
||
<ul>
|
||
<li><strong>Direct Mining of Discriminative and Essential Frequent
|
||
Patterns via Model-Based Search Tree (KDD 2008)</strong>
|
||
<ul>
|
||
<li>Wei Fan, Kun Zhang, Hong Cheng, Jing Gao, Xifeng Yan, Jiawei Han,
|
||
Philip S. Yu, Olivier Verscheure</li>
|
||
<li><a
|
||
href="http://www1.se.cuhk.edu.hk/~hcheng/paper/kdd08mbt.pdf">[Paper]</a></li>
|
||
</ul></li>
|
||
</ul>
|
||
<h2 id="section-16">2007</h2>
|
||
<ul>
|
||
<li><strong>Bandit Algorithms for Tree Search (UAI 2007)</strong>
|
||
<ul>
|
||
<li>Pierre-Arnaud Coquelin, Rémi Munos</li>
|
||
<li><a href="https://arxiv.org/pdf/1408.2028.pdf">[Paper]</a></li>
|
||
</ul></li>
|
||
</ul>
|
||
<h2 id="section-17">2006</h2>
|
||
<ul>
|
||
<li><strong>Properties of Forward Pruning in Game-Tree Search (AAAI
|
||
2006)</strong>
|
||
<ul>
|
||
<li>Yew Jin Lim, Wee Sun Lee</li>
|
||
<li><a
|
||
href="https://dl.acm.org/citation.cfm?id=1597351">[Paper]</a></li>
|
||
</ul></li>
|
||
<li><strong>Graph Branch Algorithm: An Optimum Tree Search Method for
|
||
Scored Dependency Graph with Arc Co-Occurrence Constraints (ACL
|
||
2006)</strong>
|
||
<ul>
|
||
<li>Hideki Hirakawa</li>
|
||
<li><a
|
||
href="https://www.aclweb.org/anthology/P06-2047/">[Paper]</a></li>
|
||
</ul></li>
|
||
</ul>
|
||
<h2 id="section-18">2005</h2>
|
||
<ul>
|
||
<li><strong>Game-Tree Search with Combinatorially Large Belief States
|
||
(IJCAI 2005)</strong>
|
||
<ul>
|
||
<li>Austin Parker, Dana S. Nau, V. S. Subrahmanian</li>
|
||
<li><a
|
||
href="https://www.ijcai.org/Proceedings/05/Papers/0878.pdf">[Paper]</a></li>
|
||
</ul></li>
|
||
</ul>
|
||
<h2 id="section-19">2003</h2>
|
||
<ul>
|
||
<li><strong>Solving Finite Domain Constraint Hierarchies by Local
|
||
Consistency and Tree Search (IJCAI 2003)</strong>
|
||
<ul>
|
||
<li>Stefano Bistarelli, Philippe Codognet, Kin Chuen Hui, Jimmy Ho-Man
|
||
Lee</li>
|
||
<li><a
|
||
href="https://www.ijcai.org/Proceedings/03/Papers/200.pdf">[Paper]</a></li>
|
||
</ul></li>
|
||
</ul>
|
||
<h2 id="section-20">2001</h2>
|
||
<ul>
|
||
<li><strong>Incomplete Tree Search using Adaptive Probing (IJCAI
|
||
2001)</strong>
|
||
<ul>
|
||
<li>Wheeler Ruml</li>
|
||
<li><a
|
||
href="https://dash.harvard.edu/bitstream/handle/1/23017275/tr-02-01.pdf?sequence%3D1">[Paper]</a></li>
|
||
</ul></li>
|
||
</ul>
|
||
<h2 id="section-21">1998</h2>
|
||
<ul>
|
||
<li><strong>KnightCap: A Chess Programm That Learns by Combining TD with
|
||
Game-Tree Search (ICML 1998)</strong>
|
||
<ul>
|
||
<li>Jonathan Baxter, Andrew Tridgell, Lex Weaver</li>
|
||
<li><a href="https://arxiv.org/abs/cs/9901002">[Paper]</a></li>
|
||
</ul></li>
|
||
</ul>
|
||
<h2 id="section-22">1988</h2>
|
||
<ul>
|
||
<li><strong>A Tree Search Algorithm for Target Detection in Image
|
||
Sequences (CVPR 1988)</strong>
|
||
<ul>
|
||
<li>Steven D. Blostein, Thomas S. Huang</li>
|
||
<li><a
|
||
href="https://ieeexplore.ieee.org/document/196309">[Paper]</a></li>
|
||
</ul></li>
|
||
</ul>
|
||
<hr />
|
||
<p><strong>License</strong></p>
|
||
<ul>
|
||
<li><a
|
||
href="https://github.com/benedekrozemberczki/awesome-monte-carlo-tree-search-papers/blob/master/LICENSE">CC0
|
||
Universal</a></li>
|
||
</ul>
|
||
<hr />
|
||
<p><a
|
||
href="https://github.com/benedekrozemberczki/awesome-monte-carlo-tree-search-papers">montecarlotreesearchpapers.md
|
||
Github</a></p>
|