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.

翻译：模仿学习是训练游戏智能体的有效方法，也是高效游戏生产的关键。然而，泛化能力——即在相关但未见过的情境中表现良好的能力——对于游戏AI而言仍是一个尚未解决的挑战。对模仿学习智能体而言，泛化尤为困难，因为这要求算法在训练分布之外采取有意义的动作。本文提出针对该挑战的解决方案。受监督学习中数据增强成功经验的启发，我们对训练数据进行增强，使数据集中的状态与动作分布更贴近真实的状态-动作分布。本研究评估了多种结合并应用观察数据增强方法，以提升模仿学习智能体泛化能力的效果，并在多个3D环境中提供了这些增强方法的性能基准。结果表明，数据增强是改进模仿学习智能体泛化能力的一种有前景的框架。