We propose an inverse reinforcement learning (IRL) approach using Deep Q-Networks to extract the rewards in problems with large state spaces. We evaluate the performance of this approach in a simulation-based autonomous driving scenario. Our results resemble the intuitive relation between the reward function and readings of distance sensors mounted at different poses on the car. We also show that, after a few learning rounds, our simulated agent generates collision-free motions and performs human-like lane change behaviour.
@article{arxiv.1612.03653,
title = {Learning to Drive using Inverse Reinforcement Learning and Deep Q-Networks},
author = {Sahand Sharifzadeh and Ioannis Chiotellis and Rudolph Triebel and Daniel Cremers},
journal= {arXiv preprint arXiv:1612.03653},
year = {2017}
}
Comments
NIPS workshop on Deep Learning for Action and Interaction, 2016