Imitation with Neural Density Models

Kuno Kim · Akshat Jindal · Yang Song · Jiaming Song · Yanan Sui · Stefano Ermon

Keywords: [ Reinforcement Learning and Planning ]


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 KullbackÔÇôLeibler divergence between occupancy measures of the expert and imitator. We present a practical IL algorithm, Neural Density Imitation (NDI), which obtains state-of-the-art demonstration efficiency on benchmark control tasks.

Chat is not available.