Towards Explaining Monte-Carlo Tree Search by Using Its Enhancements
This addresses the need for explainable search in AI, though it appears incremental as it builds on existing MCTS enhancements without introducing a new method.
The paper tackles the problem of explaining intelligent search techniques by proposing to use Monte-Carlo Tree Search (MCTS) enhancements to provide higher-quality, knowledge-free explanations, and presents a proof-of-concept demonstrating their advantages.
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.