search

kentsommer / pytorch-value-iteration-networks

Pytorch implementation of Value Iteration Networks (NIPS 2016 best paper)
BSD 3-Clause "New" or "Revised" License
318 stars 62 forks source link

Improved readability of the VIN model, in addition to minor changes #12

Closed shuishida closed 4 years ago

shuishida commented 4 years ago

My main modification is in the forward method of the model where you extract the q_out from the q values, and not repeating q = F.conv2d(...) in two places. I also made minor improvements, such as adding argparse in the dataset creation script and changing .cuda() into .to(device) in test.py.

shuishida commented 4 years ago

In addition to the fixes you suggested, I also refactored the gridworld.py file in the hope to make it more readable and concise.

kentsommer commented 4 years ago

LGTM