-
Notifications
You must be signed in to change notification settings - Fork 0
Open
Description
I am trying to understand the way you generated the timeseries.
For example HalfCheetah-v3 has 25 dimensions. I am assuming the last two are done and reward. The first 17 is the observation space and from 17 to 23 is the action space. Am I right? Your observation space does not include the robot’s x-coordinate.
Metadata
Metadata
Assignees
Labels
No labels