dopamine icon indicating copy to clipboard operation
dopamine copied to clipboard

Published 20 hours ago • verified publisher icon google

Incredibly high score for Defender

Open cathera opened this issue 6 years ago • 3 comments

Has anyone tried running Defender with dopamine? I noticed that baselines of Defender are not provided so I was trying to run one, but the scores are incredibly high. Here are the reference scores in Rainbow: image And this is what I get with C51: image

cathera avatar May 16 '19 16:05 cathera

I had the same problem... By the way, I found there is no Surround environment in OpenAI gym. How can I reproduce the results of IQN and C51 on this environment?

LinZichuan avatar May 16 '19 16:05 LinZichuan

Hello, I think this is due to a bug in the underlying ALE library. The reward are multiplied by 100 without reason compared to the true score of the actual game. See mgbellemare/Arcade-Learning-Environment#262 for more details.

marintoro avatar May 20 '19 12:05 marintoro

Hello, I think this is due to a bug in the underlying ALE library. The reward are multiplied by 100 without reason compared to the true score of the actual game. See mgbellemare/Arcade-Learning-Environment#262 for more details.

Hi, thanks for the information! I wonder how all previous works got their results though.....

cathera avatar May 20 '19 22:05 cathera