Triple-GAIL: A Multi-Modal Imitation Learning Framework with Generative Adversarial Nets

TL;DR

Triple-GAIL is a novel multi-modal imitation learning framework that enhances generative adversarial imitation learning by jointly learning skill selection and imitation from diverse data sources, improving performance on complex real-world tasks.

Contribution

It introduces an auxiliary skill selector into GAIL, enabling joint learning from multiple data modalities with theoretical convergence guarantees.

Findings

Outperforms state-of-the-art methods on driver and game datasets.

Effectively captures multi-modal behaviors close to demonstrators.

Demonstrates improved scalability for real-world autonomous systems.

Abstract

Generative adversarial imitation learning (GAIL) has shown promising results by taking advantage of generative adversarial nets, especially in the field of robot learning. However, the requirement of isolated single modal demonstrations limits the scalability of the approach to real world scenarios such as autonomous vehicles' demand for a proper understanding of human drivers' behavior. In this paper, we propose a novel multi-modal GAIL framework, named Triple-GAIL, that is able to learn skill selection and imitation jointly from both expert demonstrations and continuously generated experiences with data augmentation purpose by introducing an auxiliary skill selector. We provide theoretical guarantees on the convergence to optima for both of the generator and the selector respectively. Experiments on real driver trajectories and real-time strategy game datasets demonstrate that Triple-GAIL can better fit multi-modal behaviors close to the demonstrators and outperforms state-of-the-art methods.