Taehoon

Loss sometimes goes to nan even with the gradient clipping

6

Didn't figure out why yet and any advice for this is welcome!

재밌게 잘 봤습니다 😄

Reproducing results of the paper on Mujoco domain

3

Working on `paper` branch ([link](https://github.com/carpedm20/NAF-tensorflow/tree/paper)). | environment | Best return for 200 steps | | :-: | :-: | | InvertedPendulum-v1 | | | InvertedDoublePendulum-v1 | | | Reacher-v1 |...