Continuous Monte Carlo Graph Search
Loading...
Access rights
openAccess
Journal Title
Journal ISSN
Volume Title
A4 Artikkeli konferenssijulkaisussa
This publication is imported from Aalto University research portal.
View publication in the Research portal
View/Open full text file from the Research portal
Other link related to publication
View publication in the Research portal
View/Open full text file from the Research portal
Other link related to publication
Date
2024
Major/Subject
Mcode
Degree programme
Language
en
Pages
10
Series
Abstract
Online planning is crucial for high performance in many complex sequential decision-making tasks. Monte Carlo Tree Search (MCTS) employs a principled mechanism for trading off exploration for exploitation for efficient online planning, and it outperforms comparison methods in many discrete decision-making domains such as Go, Chess, and Shogi. Subsequently, extensions of MCTS to continuous domains have been developed. However, the inherent high branching factor and the resulting explosion of the search tree size are limiting the existing methods. To address this problem, we propose Continuous Monte Carlo Graph Search (CMCGS), an extension of MCTS to online planning in environments with continuous state and action spaces. CMCGS takes advantage of the insight that, during planning, sharing the same action policy between several states can yield high performance. To implement this idea, at each time step, CMCGS clusters similar states into a limited number of stochastic action bandit nodes, which produce a layered directed graph instead of an MCTS search tree. Experimental evaluation shows that CMCGS outperforms comparable planning methods in several complex continuous DeepMind Control Suite benchmarks and 2D navigation and exploration tasks with limited sample budgets. Furthermore, CMCGS can be scaled up through parallelization, and it outperforms the Cross-Entropy Method (CEM) in continuous control with learned dynamics models.Description
Publisher Copyright: © 2024 International Foundation for Autonomous Agents and Multiagent Systems.
Keywords
Continuous Control, MCTS, Model-Based Reinforcement Learning, Online Planning, Planning, Reinforcement Learning
Other note
Citation
Kujanpää, K, Kannala, J, Babadi, A, Ilin, A, Zhao, Y & Pajarinen, J 2024, Continuous Monte Carlo Graph Search . in AAMAS '24: Proceedings of the 23rd International Conference on Autonomous Agents and Multiagent Systems . ACM, pp. 1047-1056, International Conference on Autonomous Agents and Multiagent Systems, Auckland, New Zealand, 06/05/2024 . https://doi.org/10.5555/3635637.3662960
