drq

drq copied to clipboard

walker_stand critic loss explosion

1

Hi, thank you for quality code. but I wonder why walker_stand task critic loss is too high(up to 1e+3) in my experiment. In my case, I used your `conda.yaml` and...

seolhokim

The current implementation of `drq` does not support **channels last** input since `view` has constraints on the input size and stride (https://pytorch.org/docs/stable/generated/torch.Tensor.view.html): ``` Cannot view a tensor with shape torch.Size([1,...

chunyuan-w

About Replay Buffer Sample function

1

In your code, why the data sampled from the replay buffer obs and obs_aug is the same? What's the purpose? I can't understand. Waiting for your answer~

ergo-zyh