Generation and Evaluation of Exploration Terms for Monte Carlo Tree Search
- 1 May 2026
- journal article
- research article
- Published by SAGE Publications in ICGA Journal: The Journal of the Computer Games Community
- Vol. 48 (2) , 62-76
Abstract
Monte Carlo Tree Search (MCTS) has shown good results for many difficult problems. We propose to automatically generate mathematical expressions that are used as exploration terms for MCTS algorithms, and we evaluate the resulting expressions in the game of Go. We use a systematic generation of small exploration terms. This is in contrast to our initial conference paper, which used Monte Carlo Search to generate exploration terms for Sequential Halving Using Scores (SHUSS). In this journal paper, we extend the work to automatically design three exploration terms: the exploration term near the leaves of Prior Upper Confidence for Trees (PUCT), the exploration term at the root of PUCT and the SHUSS exploration term. All three resulting exploration terms improve upon standard PUCT in the game of Go.Keywords
This publication has 34 references indexed in Scilit:
- Nested Qubit Routing2026
- Quantum Circuit Design using a Progressive Widening Enhanced Monte Carlo Tree SearchAdvanced Quantum Technologies, 2025
- Monte Carlo Search Algorithms Discovering Monte Carlo Tree Search Exploration Terms2025
- Batch Monte Carlo Tree Search2023
- Sequential Halving Using Scores2022
- Evolving Game-Specific UCB Alternatives for General Video Game Playing2017
- Sequential Halving for Partially Observable GamesCommunications in Computer and Information Science, 2016
- Minimizing Simple and Cumulative Regret in Monte-Carlo Tree Search2014
- Efficient Selectivity and Backup Operators in Monte-Carlo Tree Search2007
- Bandit Based Monte-Carlo Planning2006