People who code: we want your input. Take the Survey

New answers tagged


Consider a two-dimensional convolution layer with 3x3 kernels. The 2d inputs of this layer can be seen as a particular graph with each pixel being a graph node, that is connected to 8 of his neighbors: The 3x3 kernels of the convolutional layer not only process the information about neighborhood relation between pixels, but also about their relative ...


Bootstrapped estimate is biased because it based on $V(s_{t+1})$ which is usually a biased estimate by some estimator such as neural network. I don't think this statement is totally correct in the context of the paper. Quoting the paper: Taking $\gamma < 1$ introduces bias into the policy gradient estimate, regardless of the value function’s accuracy. ...

Top 50 recent answers are included