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 a question about action normalization in Mujoco envs ("Reacher-v2","Walker2d-v3","Ant-v3","HalfCheetah-v3","Hopper-v3" , "Humanoid-v3"):
1- When applying an action to a Mujoco env using "env.step(action)", should "action" be normalized ?
2- If yes, what are the range of action that could be applied to each Mujoco env (i.e., [-1, 1]) ?
The text was updated successfully, but these errors were encountered:
Hello,
I have a question about action normalization in Mujoco envs ("Reacher-v2","Walker2d-v3","Ant-v3","HalfCheetah-v3","Hopper-v3" , "Humanoid-v3"):
1- When applying an action to a Mujoco env using "env.step(action)", should "action" be normalized ?
2- If yes, what are the range of action that could be applied to each Mujoco env (i.e., [-1, 1]) ?
The text was updated successfully, but these errors were encountered: