Interpretable Generative Adversarial Imitation Learning

arXiv:2402.10310v1 Announce Type: new
Abstract: Imitation learning methods have demonstrated considerable success in teaching autonomous systems complex tasks through expert demonstrations. However, a limitation of these methods is their lack of interpretability, particularly in understanding the specific task the learning agent aims to accomplish. In this paper, we propose a novel imitation learning method that combines Signal Temporal Logic (STL) inference and control synthesis, enabling the explicit representation of the task as an STL formula. This approach not only provides …

abstract adversarial agent arxiv autonomous autonomous systems cs.lg cs.sy eess.sy expert generative imitation learning interpretability novel paper success systems tasks teaching through type understanding