dingchenghu
dingchenghu
+1. PyTorch == 0.3.1 is not available How to run it on the latest PyTorch?
Hi How do you render the result after training on HalfCheetahDir-v1? Thanks
Hi, I have also tried run_grbal.py (default version) and it seems that it cannot reproduce the original result. Here is the output from the last iteration: ``` ----------------------------------------- | AverageDiscountedReturn...
Thank you! I also tried run_rebal. Looking at AverageReturn, it seems not working either. After some iterations, the loss went to be nan. ``` -------------------------------------- | AverageDiscountedReturn | -24.7 |...
Update: When training with more timesteps (grbal), from 250000 to 1000000, it still doesn't work: ``` ----------------------------------------- | AverageDiscountedReturn | 9.08 | | AverageForwardProgress | 0.374 | | AverageReturn |...
Any updates? @iclavera Thanks!