carpedm20 / carpedm20/SPIRAL-tensorflow
Incorrectly converged samples at early stage
Open
- Dominant language
- Python
- Stars
- 117
- Forks
- 22
- PR merge metrics
- No merged PRs in 30d
Description
When I run this project under simple_mnist or mnist env, I always get Incorrectly converged samples at early stage as showed in README,and can not generate correct numbers when training step grows, it looks still randomly generated after 10k policy steps. what do you think the possible reasons of this problem? thank you very much!
Contributor guide
No contributing guide indexed for this repository
Assessment
This issue has not been assessed yet.