Interpretable Imitation Learning via Generative Adversarial STL Inference and Control

TL;DR

This paper introduces an interpretable imitation learning framework that uses STL inference and GAN-inspired training to explicitly represent tasks, enhancing understanding and adaptability of autonomous systems.

Contribution

It combines STL inference with GAN-based training to produce interpretable task representations and adaptable policies in imitation learning.

Findings

Effective task representation via STL formulas

Improved policy interpretability and adaptability

Successful simulation results demonstrating practicality

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 a clear understanding of the task but also supports the integration of human knowledge and allows for adaptation to out-of-distribution scenarios by manually adjusting the STL formulas and fine-tuning the policy. We employ a Generative Adversarial Network (GAN)-inspired approach to train both the inference and policy networks, effectively narrowing the gap between expert and learned policies. The efficiency of our algorithm is demonstrated through simulations, showcasing its practical applicability and adaptability.