End-to-End Driving in a Realistic Racing Game with Deep Reinforcement Learning

We address the problem of autonomous race car driving. Using a recent rally game (WRC6) with realistic physics and graphics we train an Asynchronous Actor Critic (A3C) in an end-to-end fashion and propose an improved reward function to learn faster. The network is trained simultaneously on three ver...

Full description

Saved in:
Bibliographic Details
Main Authors: Perot, Etienne, Jaritz, Maximilian, Toromanoff, Marin, De Charette, Raoul
Format: Conference Proceeding
Language:English
Subjects:
Automobiles
Computer architecture
Games
Learning (artificial intelligence)
Physics
Roads
Training
Online Access:Request full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary:We address the problem of autonomous race car driving. Using a recent rally game (WRC6) with realistic physics and graphics we train an Asynchronous Actor Critic (A3C) in an end-to-end fashion and propose an improved reward function to learn faster. The network is trained simultaneously on three very different tracks (snow, mountain, and coast) with various road structures, graphics and physics. Despite the more complex environments the trained agent learns significant features and exhibits good performance while driving in a more stable way than existing end-to-end approaches.
ISSN:2160-7516
DOI:10.1109/CVPRW.2017.64