DQN-using-PyTorch-and-ML-Agents
DQN-using-PyTorch-and-ML-Agents copied to clipboard
xkiwilabs
A simple example of how to implement vector based DQN using PyTorch and a ML-Agents environment
Hi, love your implementation, however, i am curious what the variable "train_mode" in env.reset() does? Can you shortly explain what the difference between "train" and "test" mode is regarding the...
You're making it more complicated to test your code by using some "unknown" environment, this is not very helpful.... Sorry ;( Using something like the gym "cartpole" would make it...
As soon as I run the exe the following error appears. > RuntimeError: size mismatch, m1: [1 x 159], m2: [53 x 128] at c:\users\administrator\downloads\new-builder\win-wheel\pytorch\aten\src\thc\generic/THCTensorMathBlas.cu:249
Once i start training, Unity window pops up and i can see the agent moving around at fast speed so everything looks ok. However, after a few seconds this error...
Sorry since this is not an issue however i am not familiar to github interface so i don't know how request something from the developer. This is a great repository...