Towards Explaining Monte-Carlo Tree Search by Using Its Enhancements

2025/06/16 by Jakub Kowalski, Kowalski, Jakub, Mark H. M. Winands +6
Computer Science · Economics, Econometrics and Finance · #Artificial Intelligence (cs.AI) #Artificial Intelligence in Games #FOS: Computer and information sciences #Sports Analytics and Performance #Time Series Analysis and Forecasting

paper · pdf · doi:10.48550/arxiv.2506.13223

openalex publication_date 2025/06/16 · openalex created_date 2025/10/13 · openalex updated_date 2026/07/28

Abstract

Typically, research on Explainable Artificial Intelligence (XAI) focuses on black-box models within the context of a general policy in a known, specific domain. This paper advocates for the need for knowledge-agnostic explainability applied to the subfield of XAI called Explainable Search, which focuses on explaining the choices made by intelligent search techniques. It proposes Monte-Carlo Tree Search (MCTS) enhancements as a solution to obtaining additional data and providing higher-quality explanations while remaining knowledge-free, and analyzes the most popular enhancements in terms of the specific types of explainability they introduce. So far, no other research has considered the explainability of MCTS enhancements. We present a proof-of-concept that demonstrates the advantages of utilizing enhancements.

Citations

• Combining LLMs with Logic-Based Framework to Explain MCTS
• Interpretable Contrastive Monte Carlo Tree Search Reasoning
• Enabling MCTS Explainability for Sequential Planning Through Computation Tree Logic
• Proof Number Based Monte-Carlo Tree Search
• General Game Heuristic Prediction Based on Ludeme Descriptions
• Explainable Artificial Intelligence (XAI): Concepts, Taxonomies, Opportunities and Challenges toward Responsible AI
• Ludii -- The Ludemic General Game System
• A Survey of Methods for Explaining Black Box Models

Related

• Unveiling Interesting Insights: Monte Carlo Tree Search for Knowledge Discovery
• Combining LLMs with Logic-Based Framework to Explain MCTS
• Interpretable Contrastive Monte Carlo Tree Search Reasoning
• McXai: Local model-agnostic explanation as two games
• Amplifying Exploration in Monte-Carlo Tree Search by Focusing on the Unknown