google-deepmind / google-deepmind/dm_control
How to change the reset function?
Open
- Dominant language
- Python
- Stars
- 4.7k
- Forks
- 764
- PR merge metrics
- No merged PRs in 30d
Description
I am attempting to change the movement dynamics within the environment, such as enabling the hopper to walk in a different direction. Although I've added additional joints to facilitate lateral movementthe in the XML file. But I've found that the hopper still only moves forward during training with DDPG .
To address this issue, I aim to change the initial position,made the hopper to face left or downwards at the begning.
However, it seems the reset function does not allow manual adjustments.
Could you help me how to do it? Thank you!
Contributor guide
Assessment
This issue has not been assessed yet.