Hierarchical Monte Carlo Tree Search for Latent Skill Planning

被引：0
作者：
Pei, Yue [1 ]
机构：
[1] Univ Pittsburgh, Pittsburgh, PA 15213 USA
来源：
2023 2ND ASIA CONFERENCE ON ALGORITHMS, COMPUTING AND MACHINE LEARNING, CACML 2023 | 2023年
关键词：
deep reinforcement learning; monte carlo tree search; REINFORCEMENT; GO;
D O I：
10.1145/3590003.3590005
中图分类号：
TP18 [人工智能理论];
学科分类号：
081104 ; 0812 ; 0835 ; 1405 ;
摘要：
Monte Carlo Tree Search (MCTS) continues to confront the issue of exponential complexity growth in certain tasks when the planning horizon is excessively long, causing the trajectory's past to grow exponentially. Our study presents Hierarchical MCTS Latent Skill Planner, an algorithm based on skill discovery that automatically identifies skills based on intrinsic rewards and integrates them with MCTS, enabling efficient decision-making at a higher level. In the grid world maze domain, we found that latent skill search outperformed the standard MCTS approach that do not contain skills in terms of efficiency and performance.
引用
收藏
页码：6 / 12
页数：7
相关论文
共 50 条
[41]   Monte Carlo Tree Search for Network Planning for Next Generation Mobile Communication Networks [J].
Shen, Linzhi ;
Wang, Shaowei .
2021 IEEE GLOBAL COMMUNICATIONS CONFERENCE (GLOBECOM), 2021,
[42]   Accelerating Cooperative Planning for Automated Vehicles with Learned Heuristics and Monte Carlo Tree Search [J].
Kurzer, Karl ;
Fechner, Marcus ;
Zoellner, J. Marius .
2020 IEEE INTELLIGENT VEHICLES SYMPOSIUM (IV), 2020, :1726-1733
[43]   Epistemic Multi-agent Planning Using Monte-Carlo Tree Search [J].
Reifsteck, Daniel ;
Engesser, Thorsten ;
Mattmueller, Robert ;
Nebel, Bernhard .
ADVANCES IN ARTIFICIAL INTELLIGENCE, KI 2019, 2019, 11793 :277-289
[44]   AlphaTruss: Monte Carlo Tree Search for Optimal Truss Layout Design [J].
Luo, Ruifeng ;
Wang, Yifan ;
Xiao, Weifang ;
Zhao, Xianzhong .
BUILDINGS, 2022, 12 (05)
[45]   Monte Carlo tree search control scheme for multibody dynamics applications [J].
Tang, Yixuan ;
Orzechowski, Grzegorz ;
Prokop, Ales ;
Mikkola, Aki .
NONLINEAR DYNAMICS, 2024, 112 (10) :8363-8391
[46]   Monte Carlo tree search for dynamic shortest-path interdiction [J].
Bochkarev, Alexey A. ;
Smith, J. Cole .
NETWORKS, 2024, 84 (04) :398-419
[47]   Single-player Monte-Carlo tree search for SameGame [J].
Schadd, Maarten P. D. ;
Winands, Mark H. M. ;
Tak, Mandy J. W. ;
Uiterwijk, Jos W. H. M. .
KNOWLEDGE-BASED SYSTEMS, 2012, 34 :3-11
[48]   A Timetable Rescheduling Approach for Railway based on Monte Carlo Tree Search [J].
Wang, Rongsheng ;
Zhou, Min ;
Li, Yidong ;
Zhang, Qi ;
Dong, Hairong .
2019 IEEE INTELLIGENT TRANSPORTATION SYSTEMS CONFERENCE (ITSC), 2019, :3738-3743
[49]   Enhancing Bayesian Network Structural Learning with Monte Carlo Tree Search [J].
Laborda, Jorge D. ;
Torrijos, Pablo ;
Puerta, Jose M. ;
Gamez, Jose A. .
INFORMATION PROCESSING AND MANAGEMENT OF UNCERTAINTY IN KNOWLEDGE-BASED SYSTEMS, IPMU 2024, VOL 1, 2024, 1174 :403-414
[50]   Monte Carlo Tree Search for Bayesian Reinforcement Learning [J].
Vien, Ngo Anh ;
Ertel, Wolfgang .
2012 11TH INTERNATIONAL CONFERENCE ON MACHINE LEARNING AND APPLICATIONS (ICMLA 2012), VOL 1, 2012, :138-143
12345