# Best Agent Identification for General Game Playing

arXiv: https://arxiv.org/abs/2507.00451 · HTML: https://mlsanity.com/paper/2507.00451/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Builds on 14 of its 57 references that are in the map.
- First posted on arXiv 1 Jul 2025.

## Builds on (most cited first, 14 of 14)

- [Atari-5: Distilling the Arcade Learning Environment down to Five Games](https://mlsanity.com/paper/2210.02019/) (2022)
- [Ludii -- The Ludemic General Game System](https://mlsanity.com/paper/1905.05013/) (2019)
- [Deep Reinforcement Learning for General Video Game AI](https://mlsanity.com/paper/1806.02448/) (2018)
- [Best Arm Identification in Generalized Linear Bandits](https://mlsanity.com/paper/1905.08224/) (2019)
- [General Board Game Concepts](https://mlsanity.com/paper/2107.01078/) (2021)
- [Best-Arm Identification in Correlated Multi-Armed Bandits](https://mlsanity.com/paper/2109.04941/) (2021)
- [General Game Heuristic Prediction Based on Ludeme Descriptions](https://mlsanity.com/paper/2105.12846/) (2021)
- [A Continuous Information Gain Measure to Find the Most Discriminatory Problems for AI Benchmarking](https://mlsanity.com/paper/1809.02904/) (2018)
- [Budgeted Multi-Armed Bandits with Asymmetric Confidence Intervals](https://mlsanity.com/paper/2306.07071/) (2023)
- [Measuring Board Game Distance](https://mlsanity.com/paper/2301.03913/) (2023)
- [An Overview of the Ludii General Game System](https://mlsanity.com/paper/1907.00240/) (2019)
- [Enhancements for Real-Time Monte-Carlo Tree Search in General Video Game Playing](https://mlsanity.com/paper/2407.03049/) (2024)
- [Ensemble Decision Systems for General Video Game Playing](https://mlsanity.com/paper/1905.10792/) (2019)
- [Anytime Sequential Halving in Monte-Carlo Tree Search](https://mlsanity.com/paper/2411.07171/) (2024)

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

- [Dynamic Resource Allocation for Ensemble Determinization MCTS](https://mlsanity.com/paper/2607.13007/) (2026)

## Abstract (arXiv)

We present an efficient and generalised procedure to accurately identify the best (or near best) performing algorithm for each sub-task in a multi-problem domain. Our approach treats this as a set of best arm identification problems for multi-armed bandits, where each bandit corresponds to a specific task and each arm corresponds to a specific algorithm or agent. We propose an optimistic selection process based on a chosen confidence interval, that ranks each arm across all bandits in terms of their potential to influence our overall simple regret. We evaluate the performance of our approach on two of the most popular general game playing domains, the General Video Game AI (GVGAI) framework and the Ludii general game playing system, with the goal of selecting a high-performing agent for each game using a limited number of available trials. Compared to previous best arm identification algorithms for multi-armed bandits, our results demonstrate a substantial performance improvement in terms of average simple regret and average probability of error. This novel approach can be used to significantly improve the quality and accuracy of agent evaluation procedures for general game frameworks, as well as other multi-task domains with high algorithm runtimes.