1 Matching Annotations
  1. Apr 2019
  2. karpathy.github.io karpathy.github.io
    Deep Reinforcement Learning: Pong from Pixels
    1
    1. Chris17 11 Apr 2019
      the neurons in the hidden layer (which have their weights arranged along the rows of W1) can detect various game scenarios (e.g. the ball is in the top, and our paddle is in the middle), and the weights in W2 can then decide if in each case we should be going UP or DOWN

      Any ablation experiments? ;)

    Visit annotations in context

    Annotators

    URL

    karpathy.github.io/2016/05/31/rl/