Parallelization of Monte Carlo Tree Search in Continuous Domains
Published in
arXiv.org(2020)External Links:
TL
TL;DR
This work builds upon existing parallelization strategies and extends them to continuous domains and examines the resulting parallelized continuous MCTS using a challenging cooperative multi-agent system trajectory planning task in the domain of automated vehicles.
Abstract
Monte Carlo Tree Search (MCTS) has proven to be capable of solving challenging tasks in domains such as Go, chess and Atari. Previous research has developed parallel versions of MCTS, exploiting today's multiprocessing architectures. These studies focused on versions of MCTS for the discrete case. Our work builds upon existing parallelization strategies and extends them to continuous domains. In particular, leaf parallelization and root parallelization are studied and two final selection strategies that are required to handle continuous states in root parallelization are proposed. The evaluation of the resulting parallelized continuous MCTS is conducted using a challenging cooperative multi-agent system trajectory planning task in the domain of automated vehicles.
References25 items
1
Mastering Atari, Go, chess and shogi by planning with a learned model
2
Watch the Unobserved: A Simple Approach to Parallelizing Monte Carlo Tree Search
3
Decentralized Cooperative Planning for Automated Vehicles with Continuous Monte Carlo Tree Search
4
A0C: Alpha Zero in Continuous Action Space
5