The N-Tuple Bandit Evolutionary Algorithm for Game Agent Optimisation
This addresses optimization challenges in game agent design, but it is incremental as it builds on existing evolutionary and bandit methods.
The paper tackles noisy and expensive discrete optimization problems by introducing the N-Tuple Bandit Evolutionary Algorithm (NTBEA), which models parameter combinations to approximate fitness and evaluation counts, and results show it significantly outperforms grid search and an estimation of distribution algorithm in game-based hyper-parameter optimization.
This paper describes the N-Tuple Bandit Evolutionary Algorithm (NTBEA), an optimisation algorithm developed for noisy and expensive discrete (combinatorial) optimisation problems. The algorithm is applied to two game-based hyper-parameter optimisation problems. The N-Tuple system directly models the statistics, approximating the fitness and number of evaluations of each modelled combination of parameters. The model is simple, efficient and informative. Results show that the NTBEA significantly outperforms grid search and an estimation of distribution algorithm.