Bryan

Any reason why the new PR was necessary? It seems to be the exact same code as the original with the comment deleted and the linter is still complaining here...

Is there any progress on this?

Thanks for the reply—actually, I ended up realizing I'm looking for parallelized sampling, not parallelized consumption.

It's unclear to me how parallel sampling is implemented here without vectorized environments, i.e., like https://stable-baselines.readthedocs.io/en/master/guide/vec_envs.html. Can you explain the approach?

Also — I noticed that you created this issue in the past https://github.com/ray-project/ray/issues/5278 and I'm curious what adjustments were key in this implementation to get PPO with LSTMs to work

Thanks for the detailed answer, appreciate it! It makes sense to me to use sample factory then. I'll give it a shot soon 👍 A few details I forgot to...

Hi, Thanks for the documentation. After reading through I'm still confused on the dynamic of batch_T / batch_size / replay_ratio. In specific, I'm trying to recreate the training loop [here](https://github.com/hill-a/stable-baselines/blob/master/stable_baselines/td3/td3.py#L276):...

Are there any updates / ETA on this issue? Are there any rlpyt-specific blockers for the implementation?

+1 The lack of automatic scroll for large outputs is a big pain point compared to standard jupyter.

Thanks for the great work! am also interested in the sampling code, would be really useful! (btw for those who really need it, I think you could [load it into...