This is not the latest version of this item. The latest version can be found here.
Monte Carlo Tree Search in Continuous Spaces Using Voronoi Optimistic Optimization with Regret Bounds
Name
64fd9a5e014484f531552e56342e522de21b.pdf
Description
Accepted version
Size
7.59 MB
Format
Adobe PDF
Checksum (MD5)
75d79d0059b6741ddd159c52dede98a7
Author(s)
Kim, Beomjoon
Lee, Kyungjae
Lim, Sungbin
Kaelbling, Leslie
Lozano-Perez, Tomas
Journal
Proceedings of the AAAI Conference on Artificial Intelligence
Publisher
Association for the Advancement of Artificial Intelligence (AAAI)
Version
Author's final manuscript
Abstract
Many important applications, including robotics, data-center management, and process control, require planning action sequences in domains with continuous state and action spaces and discontinuous objective functions. Monte Carlo tree search (MCTS) is an effective strategy for planning in discrete action spaces. We provide a novel MCTS algorithm (voot) for deterministic environments with continuous action spaces, which, in turn, is based on a novel black-box function-optimization algorithm (voo) to efficiently sample actions. The voo algorithm uses Voronoi partitioning to guide sampling, and is particularly efficient in high-dimensional spaces. The voot algorithm has an instance of voo at each node in the tree. We provide regret bounds for both algorithms and demonstrate their empirical effectiveness in several high-dimensional problems including two difficult robotics planning problems.
Terms of Use
Creative Commons Attribution-Noncommercial-Share Alike
Persistent DSpace Link
DOI of Published Version
10.1609/AAAI.V34I06.6546
