Requisite resource levels: The project must have adequate resources to compete at the frontier of AGI development, including whatever mix of computational resources, intellectual labor, and closed insights are required to produce a 1+ year lead over less cautious competing projects.
Relative to the...
We introduce a method for learning physics-based soccer juggling skills via deep reinforcement learning. Innovations include a layer-wise mixture-of-experts neural network policy for efficient learning, a control graph for authoring the many skills and their transitions, and an adaptive random walk curriculum on the control graph.
Recently, we saw a surge of Deep Learning methods that were tailored to tabular data but still underperformed compared to Gradient Boosting on small-sized datasets. We suggest "Hopular", a novel Deep Learning architecture for medium- and small-sized datasets, where each layer is equipped with continuous modern Hopfield networks.