New issue
Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.
By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.
Already on GitHub? Sign in to your account
Replicate Prioritized Experience Replay's reported performance improvements #278
Comments
I asked the author via email and confirmed
|
I compared "Double DQN tuned prioritized lr/4" vs "proportional" in the paper. They seem to use 500,000 frames instead of 108,000 frames for evaluation (B.2.3 of http://arxiv.org/abs/1511.05952), so trying 500,000 frames may fill the gap. |
Tested 7 games: Breakout, Space Invaders, Seaquest, Asterix, Beam Rider, Qbert. Results: Breakout: 🆗 @muupan suggested that it appears that the evaluations used in the paper permitted longer episodes during evaluations, potentially explaining our slightly worse performance in 2 domains. |
Missing details
The text was updated successfully, but these errors were encountered: