AMP training problem
Open
- Dominant language
- Python
- Stars
- 381
- Forks
- 35
- PR merge metrics
- No merged PRs in 30d
Description
您好，如果我设置 amp_reward_coef = 0是不是就相当于不用amp纯粹的靠强化学习，这样可以跨过地形吗，感谢回复
Contributor guide
No contributing guide indexed for this repository
Research direction
Trace amp_reward_coef through the Python training configuration and reward calculation, then compare the AMP and reinforcement-learning paths. Confirm what setting it to 0 changes and whether terrain crossing remains supported; document the result and any relevant limitations in the issue or project documentation.
Written by the indexing model from the issue text.
Assessment
- Tech stack
- python
- Domain
- machine-learning, robotics
- Issue type
- Documentation
- Difficulty
- 2/5
- Estimated time
- 1-3 hours
- Activity status
- Stale
- Clarity
- Needs clarification
- Newbie friendliness
- 25/100