Approximate Inverse Reinforcement Learning from Vision-based Imitation Learning
Keuntaek Lee, Bogdan Vlahov, Jason Gibson, James M. Rehg, Evangelos A. Theodorou
Abstract
In this work, we present a method for obtaining an implicit objective function for vision-based navigation. The proposed methodology relies on Imitation Learning, Model Predictive Control (MPC), and an interpretation technique used in Deep Neural Networks. We use Imitation Learning as a means to do Inverse Reinforcement Learning in order to create an approximate cost function generator for a visual navigation challenge. The resulting cost function, the costmap, is used in conjunction with MPC for real-time control and outperforms other state-of-the-art costmap generators in novel environments. The proposed process allows for simple training and robustness to out-of-sample data. We apply our method to the task of vision-based autonomous driving in multiple real and simulated environments and show its generalizability. Supplementary video: https://youtu.be/WyJfT5lc0aQ
BibTeX
@inproceedings{icra2021_approximateinver,
title = {Approximate Inverse Reinforcement Learning from Vision-based Imitation Learning},
author = {Keuntaek Lee and Bogdan Vlahov and Jason Gibson and James M. Rehg and Evangelos A. Theodorou},
booktitle = {ICRA 2021},
year = {2021}
}