Ray Sun

@IcarusWizard @NonsansWD How did you know that the train_ratio should be 1024 for atari100k, instead of 256 as set by configs.yaml for "atari100k"? https://github.com/danijar/dreamerv3/blob/251910d04c9f38dd9dc385775bb0d6efa0e57a95/dreamerv3/configs.yaml#L211-L216 I wonder if the old version...

@George614 I think I figured out the issue. The task config should be "atari100k_pong" instead of "atari_pong". #173 I am leaving the train_ratio as 256 as set by the atari100k...

@danijar Thanks so much for replying. I see, so the results reported in the paper are the final training scores after 400,000 steps? I noticed that script=train does not report...

@danijar Thanks for sharing that detail. Can you share what version of ale-py should be used to run the latest version of DreamerV3? The requirements.txt file does not specify package...

Here is a thread summarizing the major changes to DreamerV3: https://x.com/danijarh/status/1782820513401958441 However, I am not sure if there is another source that describes more details or if @danijar can elaborate...

@LYK-love Thanks so much for the reply! Could you please share the exact command you ran to execute the script? Also, did you make any code changes (e.g. for logging,...

I think I figured out my issue. I was using ale-py==0.10.1. If I downgrade my ale-py package version to 0.9.0, I am able to reproduce the Atari100k Pong results for...

> Do you know what change in atari.py might have impacted performance? I noticed the old version of atari.py uses gym and the atari-py 0.2.6 package instead of using the...

@danijar Yes, the results in my table are averaged over 5 seeds (0-4). You can see the individual results for each seed here: https://docs.google.com/spreadsheets/d/1AuCd1b-numwhQ8bZ0kNoC9UKVJ-dDnO4Wg93TENvVmc/edit?usp=sharing

@realwenlongwang I haven't tried ale-py 0.11.0 yet