Learning to Drive using Inverse Reinforcement Learning and Deep QNetworks
This topic contains 0 replies, has 1 voice, and was last updated by arXiv 1 year, 7 months ago.

Learning to Drive using Inverse Reinforcement Learning and Deep QNetworks
We propose an inverse reinforcement learning (IRL) approach using Deep QNetworks to extract the rewards in problems with large state spaces. We evaluate the performance of this approach in a simulationbased 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 collisionfree motions and performs humanlike lane change behaviour.
Learning to Drive using Inverse Reinforcement Learning and Deep QNetworks
by Sahand Sharifzadeh, Ioannis Chiotellis, Rudolph Triebel, Daniel Cremers
https://arxiv.org/pdf/1612.03653v2.pdf
You must be logged in to reply to this topic.