Update README.md
parent
96353480be
commit
4a9f45b2df
10
README.md
10
README.md
|
|
@ -206,3 +206,13 @@ TensorBoard 通常会记录和可视化多种训练指标。你提到的这些
|
|||
- **`train/clip_range`**:剪裁范围,反映策略更新的限制。
|
||||
- **`train/clip_fraction`**:被剪裁的比例,反映策略更新的稳定性。
|
||||
- **`train/approx_kl`**:近似 KL 散度,反映策略更新的幅度和稳定性。
|
||||
|
||||
|
||||
|
||||
|
||||
|
||||
## 参考
|
||||
|
||||
https://github.com/mangenotwork/CLI-Sichuan-Mahjong //golang命令行麻将
|
||||
|
||||
https://github.com/lauyikfung/SichuaMahjongAI //SichuaMahjongAI
|
||||
Loading…
Reference in New Issue