Open ThisIsIsaac opened 5 years ago
Looks like I came up with a script in my Atari repo that can do this, but I can't remember where I got the details (must have scoured through lots of DQN papers). I'm not going to do it myself, but if you want to submit a PR that adds the computation and plotting of this score to test.py
then I'd be happy to accept it.
The scores for some games are different from the ones from the DQN paper:
beam_rider:
Enduro
Qbert
Pong
Space invaders:
Do you remember which papers you got these numbers from?
Unfortunately not. Maybe you can email one of the authors of Rainbow to see if they can give you a list of the human rewards and also confirm the score calculation?
Although they apparently got the human rewards from the original paper, you can check this paper for human rewards and evaluation.
The Rainbow DQN paper uses human-expert normalized scores, so I am not sure how to evaluate the training results against the original paper. Do you know what values were used for human expert scores?
I found snippets of the values used from papers here and there, but not sure if we can use the same number and how we can compute a single normalized value for all Atari games:![image](https://user-images.githubusercontent.com/49523965/62829153-56abd800-bc32-11e9-8169-0857eb958cf4.png)