Stephen James

Hi, Thanks for the question. I'll need a little more information to be able to help. Please post a minimal reproducible example. Thanks!

Hi Shane. What action more are you using? I've trained dense-reward policies with RLBench without issue, so it's likely an issue with your algorithm/reward.

Thanks for raising. How soon after launching the dataset_generation does the error appear?

Hi Basab, Thansk for the offer to contribute. There is some discussion ongoing (#356) to get PyRep compatible with the most recent version of CoppeliaSim. Once the new version comes...

As I just realise you already commented in #356 :smile:

Happy to support transferring PyRep over to use ZMQ as the backend once the new CoppleiaSim version comes out. I don't have much time these days to write, but I...

Just a note that the biggest hurdle last time I looked at upgrading pyrep ~2 years ago, was the new IK system within CoppeliaSim, which required non-trivial changes to make...

Hi all. I have an update on this. Thanks to the incredible work that @Coppelia and others have done in V4.6, it is now much easier for me to upgrade...

Just an FYI that I started the work on the upgrade to 4.6 on the weekend. I expect to have a beta version (which does not include IK) by end...

Ah, turns out I don't actually need the Gaussian posterior, but instead a deterministic one. So this isn't a problem for me anymore. But I guess it still handy for...