If you're working on OpenAI's Breakout-v4 environment:
To train: python baby-a3c.py --env Breakout-v4
To test: python baby-a3c.py --env Breakout-v4 --test True
To render: python baby-a3c.py --env Breakout-v4 --render True
About
Make things as simple as possible, but not simpler.
Frustrated by the number of deep RL implementations that are clunky and opaque? In this repo, I've stripped a high-performance A3C model down to its bare essentials. Everything you'll need is contained in 180 lines...
If you are trying to learn deep RL, the code is compact, readable, and commented
If you want quick results, I've included pretrained models
If something goes wrong, there's not a mountain of code to debug
If you want to try something new, this is a simple and strong baseline
I recently ported this code to Python 3.6 / PyTorch 0.4. If you want
to run on Python 2.7 / PyTorch 0.2, then look at one of my earlier
commits to this repo (there are different pretrained models as well)