Towards Explaining Monte-Carlo Tree Search by Using Its Enhancements
Fuente:
arXiv
Saved in:
| Main Authors: | , , , , |
|---|---|
| Format: | Preprint |
| Published: |
2025
|
| Subjects: | |
| Online Access: | |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866916795497054208 |
|---|---|
| author | Kowalski, Jakub Winands, Mark H. M. Wiśniewski, Maksymilian Reda, Stanisław Wilbik, Anna |
| author_facet | Kowalski, Jakub Winands, Mark H. M. Wiśniewski, Maksymilian Reda, Stanisław Wilbik, Anna |
| contents | 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. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2506_13223 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | Towards Explaining Monte-Carlo Tree Search by Using Its Enhancements Kowalski, Jakub Winands, Mark H. M. Wiśniewski, Maksymilian Reda, Stanisław Wilbik, Anna Artificial Intelligence 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. |
| title | Towards Explaining Monte-Carlo Tree Search by Using Its Enhancements |
| topic | Artificial Intelligence |
| url | https://arxiv.org/abs/2506.13223 |