Chenjia Bai

Have you find the hyper-parameters to reproduce the result in Adroit?

Hi, Algolzw @Algolzw . I also have some problem about the right test data. If I set the test data to be e.g., `TEST_DATA = 'datasets/lspig_val.h5'`, then I have error...

Thanks for your reply. Another quick question is why the dice score seems also high even before traning (i.e., 0.7~0.8)?

I meet the same problem when I use mujco150, the error is ``` >>> import gym >>> env = gym.make("FetchPush-v1") >>> obs = env.reset() >>> env.render() libGL error: unable to...

I use Ubuntu 16.04, Anaconda python 3.6.1, mujoco-py 1.50.1.56 , gym 0.10.5 , Nvidia driver 410.73 and CUDA 10. I can `import mujoco_py` and run `env.step(action)` successfully, but I cannot...