End-to-End Differentiable Adversarial Imitation Learning

Nir Baram, Oron Anschel, Itai Caspi, Shie Mannor

Abstract: Generative Adversarial Networks (GANs) have been successfully applied to the problem of <em>policy imitation</em> in a model-free setup. However, the computation graph of GANs, that include a stoch...