rlworkgroup / garage

A toolkit for reproducible reinforcement learning research.
MIT License
1.84k stars 309 forks source link

I don't know how to visualize. #2299

Open TriBall3 opened 2 years ago

TriBall3 commented 2 years ago

I want to visualize the arm movement during training, but I'm not sure how to visualize the mujoco environment. I've called the function: env.visualize(),but it doesn't works. Can someone help me? The program I'm running is this: image I changed the program here: image But the program reported an error image

In addition, I also have a question about whether the example of meta-learning is very slow to train. I trained the SAC-Metaworld program for 4 days, but the final success rate is still 0。