Skip to content

S
seminar-breakout
Commit e5f9f83a authored by Yuxin Wu's avatar Yuxin Wu
Browse files
Options

update readme

parent 66db04fe
Hide whitespace changes
Inline Side-by-side
Showing with 6 additions and 5 deletions
examples/A3C-Gym/README.md
View file @ e5f9f83a
...@@ -25,14 +25,15 @@ Some practicical notes: ...@@ -25,14 +25,15 @@ Some practicical notes:
multiprocess Python program to get a cgroup dedicated for the task. multiprocess Python program to get a cgroup dedicated for the task.
3. Training with a significant slower speed (e.g. on CPU) will result in very bad score, probably because of async issues. 3. Training with a significant slower speed (e.g. on CPU) will result in very bad score, probably because of async issues.
### To watch the agent play (need GUI): ### To test a model:
`./train-atari.py --task play --env Breakout-v0 --load Breakout-v0.tfmodel` Download models from [model zoo](https://goo.gl/9yIol2).
### To generate gym submission with a pretrained Atari model: Watch the agent play:
`./train-atari.py --task play --env Breakout-v0 --load Breakout-v0.tfmodel`
1. Download models from [model zoo](https://goo.gl/9yIol2) Generate gym submissions:
2. `./train-atari.py --task gen_submit --load Breakout-v0.tfmodel --env Breakout-v0 --output output_dir` `./train-atari.py --task gen_submit --load Breakout-v0.tfmodel --env Breakout-v0 --output output_dir`
Models are available for the following atari environments (click to watch videos of my agent): Models are available for the following atari environments (click to watch videos of my agent):
......
Markdown is supported
0% or
You are about to add 0 people to the discussion. Proceed with caution.
Finish editing this message first!
Please register or to comment