Internet Archive Scholar

Training Champion-level Race Car Drivers Using Deep Reinforcement Learning [post]

Peter Wurman, Samuel Barrett, Kenta Kawamoto, James MacGlashan, Kaushik Subramanian, Thomas Walsh, Roberto Capobianco, Alisa Devlic, Franziska Eckert, Florian Fuchs, Leilani Gilpin, Varun Kompella (+15 others)
2021 unpublished

Preserved Fulltext

fulltext thumbnail
Web Archive Capture PDF (1.3 MB)
https://web.archive.org/web/20210814193418/https://assets.researchsquare.com/files/rs-795954/v1_covered.pdf?c=1628786678

A copy of this work was available on the public web and has been preserved in the Wayback Machine. The capture dates from 2021; you can also visit the original URL. The file type is application/pdf.

Many potential applications of artificial intelligence involve making real-time decisions in physical systems. Automobile racing represents an extreme case of real-time decision making in close proximity to other highly-skilled drivers while near the limits of vehicular control. Racing simulations, such as the PlayStation game Gran Turismo, faithfully reproduce the nonlinear control challenges of real race cars while also encapsulating the complex multi-agent interactions. We attack, and solve
more » ... or the first time, the simulated racing challenge using model-free deep reinforcement learning. We introduce a novel reinforcement learning algorithm and enhance the learning process with mixed scenario training to encourage the agent to incorporate racing tactics into an integrated control policy. In addition, we construct a reward function that enables the agent to adhere to the sport's under-specified racing etiquette rules. We demonstrate the capabilities of our agent, GT Sophy, by winning two of three races against four of the world's best Gran Turismo drivers and being competitive in the overall team score. By showing that these techniques can be successfully used to train championship-level race car drivers, we open up the possibility of their use in other complex dynamical systems and real-world applications.
doi:10.21203/rs.3.rs-795954/v1 fatcat:gz76zvzax5bvnnyuqfnac3rzyq
Open Access
Citation

Peter Wurman, Samuel Barrett, Kenta Kawamoto, James MacGlashan, Kaushik Subramanian, Thomas Walsh, Roberto Capobianco, Alisa Devlic, Franziska Eckert, Florian Fuchs, Leilani Gilpin, Varun Kompella, Piyush Khandelwal, HaoChih Lin, Patrick MacAlpine, Declan Oller, Craig Sherstan, Takuma Seno, Michael Thomure, Houmehr Aghabozorgi, Leon Barrett, Rory Douglas, Dion Whitehead, Peter Dürr, Peter Stone, Michael Spranger, Hiroaki Kitano. "Training Champion-level Race Car Drivers Using Deep Reinforcement Learning." (2021)