Dillon Sandhu

icon indicating an email [email protected]

icon location Durham, NC icon location Grad Student at Duke with an interest in Reinforcement Learning

Results 2 comments of Dillon Sandhu

Can't train using GPU? The torch version for this environment is '1.10.0cpu', that is, CPU one.

Which Cuda version do you have? Updating pytorch may work for you.

The model does not converge for breakout

Did the reward stay zero the entire time, or did it occasionally get some reward? I have it working on cartpole, but not on Atari. That said, it still gets...