You signed in with another tab or window. Reload to refresh your session.You signed out in another tab or window. Reload to refresh your session.You switched accounts on another tab or window. Reload to refresh your session.Dismiss alert
I have set up a reinforcement learning environment for the Unitree Go2 using a direct reinforcement learning environment. However, during the training process, the robot's movements appear very stiff, as if its joints are stuck, and the reward values are consistently hovering in the single digits. When I switched the environment to CartPole, the model's reward values increased normally. Can someone help me check the issues in my environment?
reacted with thumbs up emoji reacted with thumbs down emoji reacted with laugh emoji reacted with hooray emoji reacted with confused emoji reacted with heart emoji reacted with rocket emoji reacted with eyes emoji
-
I have set up a reinforcement learning environment for the Unitree Go2 using a direct reinforcement learning environment. However, during the training process, the robot's movements appear very stiff, as if its joints are stuck, and the reward values are consistently hovering in the single digits. When I switched the environment to CartPole, the model's reward values increased normally. Can someone help me check the issues in my environment?
https://github.com/Huisouan/isaac-lab-vqvae/blob/master/source/vqvae/vqvae/tasks/direct/GO2/go2_pmc_env.py
Beta Was this translation helpful? Give feedback.
All reactions