stonyhu

``` class MDNRNN(nn.Module): def __init__(self, z_size, n_hidden=256, n_gaussians=5, n_layers=1): super(MDNRNN, self).__init__() self.z_size = z_size self.n_hidden = n_hidden self.n_gaussians = n_gaussians self.n_layers = n_layers self.lstm = nn.LSTM(z_size, n_hidden, n_layers, batch_first=True) **self.fc1...

A mistake in policy gradient for cliff walking REINFORCE

1

Hi author, your code is just wonderful and it help me a lot on building deep reinforcement learning system for my project. But I found a mistake in the following...