Fixing RuntimeError simple_dqn_torch_2020.py

[ker2x]

On my (windows 10, Cuda 11) platform i get an error and found this fix. Here is the error : Traceback (most recent call last): File "C:/Users/kerde/Documents/python/qlearning/main.py", line 133, in action = agent.choose_action(observation) File "C:/Users/kerde/Documents/python/qlearning/main.py", line 84, in choose_action actions = self.Q_eval.forward(state) File "C:/Users/kerde/Documents/python/qlearning/main.py", line 40, in forward x = F.relu(self.fc1(state)) File "C:\Users\kerde\miniconda3\envs\qlearning\lib\site-packages\torch\nn\modules\module.py", line 727, in _call_impl result = self.forward(*input, **kwargs) File "C:\Users\kerde\miniconda3\envs\qlearning\lib\site-packages\torch\nn\modules\linear.py", line 93, in forward return F.linear(input, self.weight, self.bias) File "C:\Users\kerde\miniconda3\envs\qlearning\lib\site-packages\torch\nn\functional.py", line 1690, in linear ret = torch.addmm(bias, input, weight.t()) RuntimeError: expected scalar type Float but found Double