Reinforcement Learning
Learn about reinforcement learning and the principle of optimality in the context of video games.
Most discriminative AI examples involve applying a continuous or discrete label to a piece of data. From applying a deep neural network to determine the digit represented by one of the MNIST images or if a CIFAR-10 image contains a horse, the model produces a single output, a prediction with minimal error. In reinforcement learning, we also want to make such point predictions, but over many steps, and to optimize the total error over repeated uses.
Get hands-on with 1400+ tech skills courses.