@COMMENT This file was generated by bib2html.pl version 0.90
@COMMENT written by Patrick Riley
@COMMENT This file came from Peter Stone's publication pages at
@COMMENT http://www.cs.utexas.edu/~pstone/papers
@article{nature22,
author="Peter R.\ Wurman and Samuel Barrett and Kenta Kawamoto and James MacGlashan and Kaushik Subramanian and Thomas J.\ Walsh and Roberto Capobianco and Alisa Devlic and Franziska Eckert and Florian Fuchs and Leilani Gilpin and Varun Kompella and Piyush Khandelwal and HaoChih Lin and Patrick MacAlpine and Declan Oller and Craig Sherstan and Takuma Seno and Michael D.\ Thomure and Houmehr Aghabozorgi and Leon Barrett and Rory Douglas and Dion Whitehead and Peter Duerr and Peter Stone and Michael Spranger and and Hiroaki Kitano",
title="Outracing Champion Gran Turismo Drivers with Deep Reinforcement Learning",
journal="Nature",
year={2022},month="Feb.",day="10",
pages="223--28",
volume="62",
issue="7896",
doi={10.1038/s41586-021-04357-7},
abstract="Many potential applications of artificial intelligence
involve making real-time decisions in physical systems
while interacting with humans. Automobile racing
represents an extreme example of these conditions; drivers
must execute complex tactical manoeuvres to pass or block
opponents while operating their vehicles at their traction
limits1. Racing simulations, such as the PlayStation game
Gran Turismo, faithfully reproduce the non-linear control
challenges of real race cars while also encapsulating the
complex multi-agent interactions. Here we describe how we
trained agents for Gran Turismo that can compete with the
world's best e-sports drivers. We combine
state-of-the-art, model-free, deep reinforcement learning
algorithms with mixed-scenario training to learn an
integrated control policy that combines exceptional speed
with impressive tactics. In addition, we construct a
reward function that enables the agent to be competitive
while adhering to racing's important, but under-specified,
sportsmanship rules. We demonstrate the capabilities of
our agent, Gran Turismo Sophy, by winning a head-to-head
competition against four of the world's best Gran Turismo
drivers. By describing how we trained championship-level
racers, we demonstrate the possibilities and challenges of
using these techniques to control complex dynamical
systems in domains where agents must respect imprecisely
defined human norms.",
wwwnote={Available from Nature website.
project webpage},
}