# The N-Tuple Bandit Evolutionary Algorithm for Automatic Game Improvement

## TL;DR

This paper introduces the N-Tuple Bandit Evolutionary Algorithm, a novel method for automatic game improvement that uses AI agent observations to estimate game quality, demonstrating robustness and human preference over existing methods.

## Contribution

The paper presents a new evolutionary algorithm combining model-based fitness estimation with bandit strategies, tailored for AI-assisted game design without game-specific tuning.

## Key findings

- The N-Tuple Bandit Algorithm outperforms Random Mutation Hill Climber and Biased Mutation in robustness.
- Initial experiments show the algorithm effectively optimizes a Space Battle game variant.
- Human players prefer games evolved by the N-Tuple algorithm.

## Abstract

This paper describes a new evolutionary algorithm that is especially well suited to AI-Assisted Game Design. The approach adopted in this paper is to use observations of AI agents playing the game to estimate the game's quality. Some of best agents for this purpose are General Video Game AI agents, since they can be deployed directly on a new game without game-specific tuning; these agents tend to be based on stochastic algorithms which give robust but noisy results and tend to be expensive to run. This motivates the main contribution of the paper: the development of the novel N-Tuple Bandit Evolutionary Algorithm, where a model is used to estimate the fitness of unsampled points and a bandit approach is used to balance exploration and exploitation of the search space. Initial results on optimising a Space Battle game variant suggest that the algorithm offers far more robust results than the Random Mutation Hill Climber and a Biased Mutation variant, which are themselves known to offer competitive performance across a range of problems. Subjective observations are also given by human players on the nature of the evolved games, which indicate a preference towards games generated by the N-Tuple algorithm.