Data Augmentation for Learning to Play in Text-Based Games

Data Augmentation for Learning to Play in Text-Based Games

Jinhyeon Kim, Kee-Eung Kim

Proceedings of the Thirty-First International Joint Conference on Artificial Intelligence
Main Track. Pages 3143-3149. https://doi.org/10.24963/ijcai.2022/436

Improving generalization in text-based games serves as a useful stepping-stone towards reinforcement learning (RL) agents with generic linguistic ability. Data augmentation for generalization in RL has shown to be very successful in classic control and visual tasks, but there is no prior work for text-based games. We propose Transition-Matching Permutation, a novel data augmentation technique for text-based games, where we identify phrase permutations that match as many transitions in the trajectory data. We show that applying this technique results in state-of-the-art performance in the Cooking Game benchmark suite for text-based games.
Keywords:
Machine Learning: Reinforcement Learning
Machine Learning: Deep Reinforcement Learning
Natural Language Processing: Other
Planning and Scheduling: POMDPs