wsy182
/
mjAi
1
0
Fork 0
Code Issues Pull Requests Packages Projects Releases Wiki Activity

Update README.md

main
wsy182 2024-12-02 13:20:57 +08:00
parent 96353480be
commit 4a9f45b2df
1 changed files with 11 additions and 1 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

10
README.md
View File

@ -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_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/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。 - **`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