search

denisyarats / drq

DrQ: Data regularized Q
https://sites.google.com/view/data-regularized-q
MIT License
407 stars 52 forks source link

How to run code without augmentation? #19

Closed zhihanyang2022 closed 3 years ago

zhihanyang2022 commented 3 years ago

Hi, thanks for sharing the code! I'm interested in applying DrQ to a dm_control domain, and I see from the README that I can readily do that using the following command:

python train.py env=cartpole_swingup

However, is there a way to turn off augmentation (e.g., via command line options)? I'd like to compare the performance with and without augmentation.

denisyarats commented 3 years ago

There is a command line option for this, feel free to add one.

Generally, you just need to turn off this: https://github.com/denisyarats/drq/blob/master/replay_buffer.py#L64