GAN-MPC: Training Model Predictive Controllers with Parameterized Cost Functions using Demonstrations from Non-identical Experts

1 code implementation • 30 May 2023 • Returaj Burnwal, Anirban Santara, Nirav P. Bhatt, Balaraman Ravindran, Gaurav Aggarwal

We propose a novel approach that uses a generative adversarial network (GAN) to minimize the Jensen-Shannon divergence between the state-trajectory distributions of the demonstrator and the imitator.

Generative Adversarial Network Imitation Learning +1