Imitation with Neural Density Models

Kuno Kim
Kuno Kim
Akshat Jindal
Akshat Jindal
Yanan Sui
Yanan Sui
Cited by: 0|Bibtex|Views27
Other Links: arxiv.org

Abstract:

We propose a new framework for Imitation Learning (IL) via density estimation of the expert's occupancy measure followed by Maximum Occupancy Entropy Reinforcement Learning (RL) using the density as a reward. Our approach maximizes a non-adversarial model-free RL objective that provably lower bounds reverse Kullback-Leibler divergence b...More

Code:

Data:

Full Text
Your rating :
0

 

Tags
Comments