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 limits. 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.

Related Publications

Dynamic Sparse Training for Deep Reinforcement Learning

IJCAI, 2022
Ghada Sokar, Elena Mocanu, Decebal Constantin Mocanu, Mykola Pechenizkiy, Peter Stone

Deep reinforcement learning (DRL) agents are trained through trial-and-error interactions with the environment. This leads to a long training time for dense neural networks to achieve good performance. Hence, prohibitive computation and memory resources are consumed. Recentl…

Planetary Environment Prediction Using Generative Modeling

AIAA SciTech Forum, 2022
Shrijit Singh*, Shreyansh Daftry*, Roberto Capobianco

Planetary rovers have a limited sensory horizon and operate in environments where limited information about the surrounding terrain is available. The rough and unknown nature of the terrain in planetary environments potentially leads to scenarios where the rover gets stuckan…

Logic Tensor Networks

Artificial Intelligence, 2022
Samy Badreddine, Artur d'Avila Garcez*, Luciano Serafini*, Michael Spranger

Attempts at combining logic and neural networks into neurosymbolic approaches have been on the increase in recent years. In a neurosymbolic system, symbolic knowledge assists deep learning, which typically uses a sub-symbolic distributed representation, to learn and reason a…

SEE ALL

HOME
Publications
Outracing Champion Gran Turismo Drivers with Deep Reinforcement Learning

JOIN US

Shape the Future of AI with Sony AI

We want to hear from those of you who have a strong desire
to shape the future of AI.

LEARN MORE