masterdezign

I am trying to figure it out now. My problem is: if a neural network with fully connected layers is represented as ``` network :: (Reifies s W) => =>...

I am using the matrix-matrix multiplication `()` from [accelerate-blas](https://hackage.haskell.org/package/accelerate-blas) package as a basis of a linear layer: ``` linear :: (Reifies s W, Numeric e) => BVar s (Acc (Matrix...

I would really love to try, but I am really, really afraid of getting a [result similar to this one](https://ajknapp.github.io/2018/08/14/notomatic-differentiation.html). Are there any limitations that you are aware of?

> so what is the point of using hardtanh activation? To approximate sign gradients in the backward pass

Have you installed `build-essential` package? Verify the version of your `gcc`. I was able to install the environment with `gcc (Ubuntu 7.5.0-3ubuntu1~18.04) 7.5.0`.

See also how this problem is solved in [hasktorch](https://github.com/hasktorch/hasktorch).

Hi @mtnusf97, I am working on #201 so I may add several types of recurrent networks to SAC.

Thanks for the references. I will check them out and come back.

Just a quick update: I plan to do this by the end of 2023 when I have some free time. Currently I have three higher priority projects.

Status update: 1. I've checked the resources that you provided, thanks a lot. I find the [code](https://github.com/zhihanyang2022/off-policy-continuous-control) to be nicely written and quite easy to understand. 2. I managed to...