Rishabh Agarwal
Rishabh Agarwal
Hmm .. I'm also not sure what could be causing the issue but we have used `Asterix/1` for some of our recent ICLR/NeurIPS papers and it does seem to replicate...
Yes, the dataset is composed of (s, a, r, s') tuples like the way you indicated (you can visualize the data in a colab/jupyter notebook). For a Pytorch version of...
So, the evaluation is done every iteration in `dopamine` [here](https://github.com/google/dopamine/blob/master/dopamine/discrete_domains/run_experiment.py#L450). Also, if you launched the code in the repository, the evaluation results should be logged in your tensorboard logs as...
@Altriaex was this issue resolved?
@psc might answer more details .. but Dopamine supports openAI gym environments too and there is data logging code in the repo (look in the baselines directory) that can be...
Yes, I can release the raw results and I would try to do so by the end of this week. Which results do you specifically need?
I think you meant the CQL paper? Actually, I can send you these results directly over email now (as I have them stored as zipped panda dataframes) -- can you...
@GoingMyWay Yes, I'll post the raw results on github by next month. In the meantime, you can send me an email and I can send you some of those results...
> Any ideas what could be the cause of this? My hunch is that in each of the checkpoint files, there are `stack size` (typically 4) elements near the end...
That's correct, it's not possible to load the entire dataset into memory. So, the way the dataset is stored is in 50 files of size 1M each corresponding to replay...