Fuwei Li

I have the same concern. Have you figured it out?

The environment I use is Python 3.5. You can switch to Python3.5 and try. You can also use env.py as the environment. It is much easier and does not depend...

Since you are using the env.py as the environment, the prey policy should be implemented outside the environment by yourself. This is a little different from the modified gym environment...

Would you please delete the env folder and try our env.py implementation. You can refer [this repository ](https://github.com/livey/scalable_maddpg_clever_prey).

I can not remember the details of the code now. But, the traditional SBL is a good start to see whether the sparse signal is recoverable.

Delete the env.py file in the main directory.

> Thank you for the excellent work. > > I'm doing an experiment on Depth Network. To this end, I would like to add GT of Pose instead of Posenetwork....

> @livey Hi, may I ask which dataset you are using for the GT-pose experiment? Thanks a lot! I used the DDAD dataset.

> @VitorGuizilini-TRI @livey Hi, Thanks a lot for the information. According to the discussion in [https://github.com/TRI-ML/DDAD/issues/29](url), it seems the GT-pose in DDAD dataset is also not well. @VitorGuizilini-TRI was there...