search

amiralansary / rl-medical

Deep Reinforcement Learning (DRL) agents applied to medical images
Apache License 2.0
177 stars 69 forks source link

Documenting of code, and minor code changes #6

Closed crypdick closed 6 years ago

crypdick commented 6 years ago

I read your code line-by-line and added documentation. Hopefully I interpreted everything correctly!

I made some minor edits to play_one_episode. I commented out some unused definitions, and ran the files through a PEP8 linter to clean up the style. I am pretty confident everything should work, but I can't test whether I broke anything without training data.

Finally, I deleted the Atari code at the end of expreplay.py

amiralansary commented 6 years ago

I just added some test data and a pre-trained model. I hope this ease testing any new changes. Thanks!

crypdick commented 6 years ago

Ok, I carefully merged your changes and tested that everything works with your sample data. You can review my changes side-by-side here. The most aggressive change is deleting 2 unused Class definitions.

crypdick commented 6 years ago

e236882 fixes an error due to a train=False kwarg being renamed to task=False in a recent commit

amiralansary commented 6 years ago

I checked the changes and did few test, it seems to be working fine too. The changes are merged now. Thank you for the contribution here! :)