LGAIMLMar 30, 2020

Parallelization of Monte Carlo Tree Search in Continuous Domains

arXiv:2003.13741v16 citations
Originality Incremental advance
AI Analysis

This work addresses the challenge of scaling MCTS to continuous domains for applications like automated vehicle planning, but it is incremental as it builds on prior parallelization strategies.

The paper tackled the problem of parallelizing Monte Carlo Tree Search (MCTS) for continuous domains, extending existing strategies like leaf and root parallelization and proposing selection methods for continuous states, with evaluation on a cooperative multi-agent trajectory planning task for automated vehicles.

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.

Code Implementations1 repo
Foundations

The foundational work for this paper's niche, ranked by how specifically the neighbourhood builds on it — not by global fame.

Your Notes