Dual Monte Carlo Tree Search

03/21/2021
by   Prashank Kadam, et al.
4

AlphaZero, using a combination of Deep Neural Networks and Monte Carlo Tree Search (MCTS), has successfully trained reinforcement learning agents in a tabula-rasa way. The neural MCTS algorithm has been successful in finding near-optimal strategies for games through self-play. However, the AlphaZero algorithm has a significant drawback; it takes a long time to converge and requires high computational power due to complex neural networks for solving games like Chess, Go, Shogi, etc. Owing to this, it is very difficult to pursue neural MCTS research without cutting-edge hardware, which is a roadblock for many aspiring neural MCTS researchers. In this paper, we propose a new neural MCTS algorithm, called Dual MCTS, which helps overcome these drawbacks. Dual MCTS uses two different search trees, a single deep neural network, and a new update technique for the search trees using a combination of the PUCB, a sliding-window, and the epsilon-greedy algorithm. This technique is applicable to any MCTS based algorithm to reduce the number of updates to the tree. We show that Dual MCTS performs better than one of the most widely used neural MCTS algorithms, AlphaZero, for various symmetric and asymmetric games.

READ FULL TEXT

page 1

page 2

page 3

page 4

research
04/30/2023

Nearly Optimal Steiner Trees using Graph Neural Network Assisted Monte Carlo Tree Search

Graph neural networks are useful for learning problems, as well as for c...
research
03/16/2023

Proof Number Based Monte-Carlo Tree Search

This paper proposes a new game search algorithm, PN-MCTS, that combines ...
research
05/22/2023

Know your Enemy: Investigating Monte-Carlo Tree Search with Opponent Models in Pommerman

In combination with Reinforcement Learning, Monte-Carlo Tree Search has ...
research
05/23/2018

Monte Carlo Tree Search for Asymmetric Trees

We present an extension of Monte Carlo Tree Search (MCTS) that strongly ...
research
05/06/2020

Learning, transferring, and recommending performance knowledge with Monte Carlo tree search and neural networks

Making changes to a program to optimize its performance is an unscalable...
research
02/05/2020

Toward Optimal FDM Toolpath Planning with Monte Carlo Tree Search

The most widely used methods for toolpath planning in fused deposition 3...
research
04/20/2017

Monte Carlo Tree Search with Sampled Information Relaxation Dual Bounds

Monte Carlo Tree Search (MCTS), most famously used in game-play artifici...

Please sign up or login with your details

Forgot password? Click here to reset