Replies: 1 comment
-
It depends on the reward function and the training time (time steps of episodes). Without more details about how you are doing the training is impossible to guess what is going wrong. |
Beta Was this translation helpful? Give feedback.
0 replies
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
-
i've tried [python learn.py # task: single drone hover at z == 1.0] so many times but it seems the rl doesn't work when the action is set to be [rpm]. it is easy to have success when turn action to [1_d_rpm]
Beta Was this translation helpful? Give feedback.
All reactions