dikke
Results
2
issues of
dikke
Hello On your `4.imagination-augmented agent.ipynb`, you specify the distil loss function as the following: `distil_loss = 0.01 * (F.softmax(logit).detach() * F.log_softmax(distil_logit)).sum(1).mean()` Don't you forget the minus sign in front of...
Hello I am amazed by your work. I am wondering if you tested the Sokoban's game on the standard RL method (Q learning, A2C, ec), and wondering if you have...