Triple-GAIL: A Multi-Modal Imitation Learning Framework with Generative Adversarial Nets
This addresses the need for scalable imitation learning in real-world scenarios like autonomous vehicles by handling multi-modal behaviors, though it is incremental as it builds on existing GAIL methods.
The paper tackles the problem of limited scalability in imitation learning due to single-modal demonstrations by proposing Triple-GAIL, a multi-modal framework that jointly learns skill selection and imitation from expert data and generated experiences, achieving better fit to multi-modal behaviors and outperforming state-of-the-art methods in experiments on driver trajectories and game datasets.
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.