Improving Generalization in Game Agents with Data Augmentation in Imitation Learning
This addresses a key challenge in game production by enhancing agent adaptability to unseen scenarios, though it is incremental as it adapts existing supervised learning techniques.
The paper tackles the problem of poor generalization in imitation learning agents for game AI by applying data augmentation to training data, demonstrating improved performance across several 3D environments.
Imitation learning is an effective approach for training game-playing agents and, consequently, for efficient game production. However, generalization - the ability to perform well in related but unseen scenarios - is an essential requirement that remains an unsolved challenge for game AI. Generalization is difficult for imitation learning agents because it requires the algorithm to take meaningful actions outside of the training distribution. In this paper we propose a solution to this challenge. Inspired by the success of data augmentation in supervised learning, we augment the training data so the distribution of states and actions in the dataset better represents the real state-action distribution. This study evaluates methods for combining and applying data augmentations to observations, to improve generalization of imitation learning agents. It also provides a performance benchmark of these augmentations across several 3D environments. These results demonstrate that data augmentation is a promising framework for improving generalization in imitation learning agents.