Improving Generalization in Game Agents with Data Augmentation in Imitation Learning

arXiv:2309.12815v3 Announce Type: replace
Abstract: 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 …

abstract agents arxiv augmentation challenge cs.lg data game however imitation learning improving playing production training type unsolved