Can I read An Efficient Dynamic Sampling Policy For Monte Carlo Tree Search on EtoBox?

An Efficient Dynamic Sampling Policy For Monte Carlo Tree Search by Zhang, Gongbo; Peng, Yijie; Xu, Yilong is a scholarly article available to read on EtoBox.

What is An Efficient Dynamic Sampling Policy For Monte Carlo Tree Search about?

We consider the popular tree-based search strategy within the framework of reinforcement learning, the Monte Carlo Tree Search (MCTS), in the context of finite-horizon Markov decision process. We propose a dynamic sampling tree policy that efficiently allocates limited computational budget to maximize the probability of correct selection of the best action at the root node of the tree. Experimental results on Tic-Tac-Toe and Gomoku show that the proposed tree policy is more efficient than other competing methods.

Author

Zhang, Gongbo; Peng, Yijie; Xu, Yilong

Published

2022

Language

EN