Outracing champion Gran Turismo drivers with deep reinforcement learning.

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.

A (somewhat) new solution to the variable binding problem.

To perform automatic, unconscious inference, the human brain must solve the binding problem by correctly grouping properties with objects. Temporal binding models like SHRUTI already suggest much of how this might be done in a connectionist and localist way by using temporal synchrony. We propose a set of alternatives to temporal synchrony mechanisms that instead use short signatures. This serves two functions: it allows us to explore an additional biologically plausible alternative, and it allows us to extend and improve the capabilities of these models. These extensions model the human ability to both perform unification and handle multiple instantiations of logical terms. To verify our model's feasibility, we simulate it with a computer system modeling simple, neuron-like computations.