Commit Graph

20 Commits

Author SHA1 Message Date
zhiyang7 05aa179ba6 新增vanilla模型训练逻辑及开关项 2021-12-10 16:12:50 +08:00
zhiyang7 3300fd9658 添加叫牌相关的评估逻辑 2021-12-10 10:11:44 +08:00
zhiyang7 0df61c62e3 reward调整 2021-12-09 22:07:11 +08:00
zhiyang7 c239085c24 移除根据胜率叫地主逻辑(4人场景下,胜率计算未适配) 2021-12-09 20:02:40 +08:00
zhiyang7 a755ffe719 调整评估相关代码 2021-12-08 17:16:27 +08:00
zhiyang7 ee409846f3 minor fix 2021-12-07 17:44:36 +08:00
zhiyang7 4a55570be6 修复bid模型参数错误 2021-12-07 11:18:44 +08:00
zhiyang7 c7f105d20d 调整激励算法 2021-12-07 10:33:18 +08:00
zhiyang7 cfa9da6b2c 修复炸弹问题 2021-12-06 09:49:47 +08:00
ZaneYork 7bc1e527c3 修复5张以上的炸弹BUG 2021-12-05 19:08:24 +08:00
ZaneYork e017c3724d 参数调整 2021-12-05 13:01:29 +08:00
zhiyang7 56c6ac5130 调整为4人模式输出 2021-12-05 12:20:49 +08:00
zhiyang7 aab93d66c6 改造为4人斗地主 2021-12-05 12:03:30 +08:00
Vincentzyx 9c1c56d91d
Update README.md 2021-09-25 10:57:38 +08:00
Vincentzyx 272c492c0c
Update README.md 2021-09-25 10:57:16 +08:00
Vincentzyx 9b6852d4eb Merge branch 'main' of https://github.com/Vincentzyx/Douzero_Resnet into main 2021-09-07 17:19:35 +08:00
Vincentzyx 3381e96932 Env 2021-09-07 17:19:25 +08:00
Vincentzyx 3fe262b6a6
Create README.md 2021-09-07 16:39:45 +08:00
Vincentzyx e1e727a2f3 Init 2021-09-07 16:38:34 +08:00
Vincentzyx 5fbacd142e Initial commit 2021-09-07 16:37:24 +08:00