# An Efficient Dynamic Sampling Policy For Monte Carlo Tree Search

arXiv: https://arxiv.org/abs/2204.12043 · HTML: https://mlsanity.com/paper/2204.12043/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Builds on 6 of its 23 references that are in the map.
- First posted on arXiv 26 Apr 2022.

## Builds on (most cited first, 6 of 6)

- [Monte Carlo Tree Search: A Review of Recent Modifications and Applications](https://mlsanity.com/paper/2103.04931/) (2021)
- [Simple Bayesian Algorithms for Best Arm Identification](https://mlsanity.com/paper/1602.08448/) (2016)
- [Monte-Carlo Tree Search by Best Arm Identification](https://mlsanity.com/paper/1706.02986/) (2017)
- [Ranking and Selection as Stochastic Control](https://mlsanity.com/paper/1710.02619/) (2017)
- [An Optimal Computing Budget Allocation Tree Policy for Monte Carlo Tree Search](https://mlsanity.com/paper/2009.12407/) (2020)
- [Ranking and Selection: A New Sequential Bayesian Procedure for Use with Common Random Numbers](https://mlsanity.com/paper/1410.6782/) (2014)

## Built on by (most cited first, 1 of 1)

- [Streaming Looking Ahead with Token-level Self-reward](https://mlsanity.com/paper/2503.00029/) (2025)

## Abstract (arXiv)

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.