Skip to content

Instantly share code, notes, and snippets.

@tambetm

tambetm/Pong-v0.md

Last active October 22, 2016 18:16
Show Gist options
  • Save tambetm/fc6a6e9eb1eebedd79e37b7df409e0a8 to your computer and use it in GitHub Desktop.
Save tambetm/fc6a6e9eb1eebedd79e37b7df409e0a8 to your computer and use it in GitHub Desktop.
Download ZIP
Raw
Pong-v0.md
  1. Install simple_dqn.
  2. Run ./train.sh Pong-v0 --evironment gym.
  3. Check results/Pong-v0.csv for best performing epoch (in my case it was 81).
  4. Run ./test_gym.sh snapshots/Pong-v0_81.pkl (replace 81 with your best epoch).
  5. Optional: run ./upload_gym.sh results/Pong-v0 --api_key <your_key> to upload the results.

The Simple DQN implementation uses network architecture and hyperparameters from DeepMind Nature paper.

Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment