the python sample of rl learning regarding jetracer is not able to converge, the training was token over 200k steps. While the jetbot case is good.
The jetracer example was not completely done, and will be removed from the next release
hi, thanks for the reply. but can you provide more detail about the issue, is it related to the Environment or the PhysiX? from the source code, that is the key different between jetbot and jetracer.
there were no specific issues, it was just our of our scope to work on the training for Jetracer at the moment