Dyna-AIL : Adversarial Imitation Learning by Planning

• Saxena, Vaibhav*; Sivanandan, Srinivasan; Mathur, Pulkit
• Accepted abstract
• [PDF] [Slides] [Join poster session]
  Poster session from 15:00 to 16:00 EAT and from 20:45 to 21:45 EAT
  Obtain the zoom password from ICLR

Abstract

Adversarial methods for imitation learning have been shown to perform well on various control tasks. However, they require a large number of environment interactions for convergence. In this paper, we propose an end-to-end differentiable adversarial imitation learning algorithm in a Dyna-like framework for switching between model-based planning and model-free learning from expert data. Our results on both discrete and continuous environments show that our approach of using model-based planning along with model-free learning converges to an optimal policy with fewer number of environment interactions in comparison to state-of-the-art imitation learning methods.