7566fe99a1
feat(PX): 自训练v1.5 P0准备 — NHN模式 + 总分法胜率解析 + 评估管线
...
CB-01: Program.cs 加 --nhn 模式 [NEURAL,ISMCTS,NEURAL]
- 3人跑得快 N插花坐排列
- Rotations 数组补全为4种排列 (IIN/NII/INI/NHN)
- --nhn 参数: 不生成CSV, 直接评估
CB-02: 胜率解析统一总分法
- TrainingCollector 加 ScoreAccumulator/BotWins/BotGames 静态累加器
- GameOver 无条件调用 AccumulateScore (eval + 训练模式均记录)
- stress_summary.txt 输出 #BOT_SCORES: bot=wins/games,wr=XX%,score=YYY
- orchestrator eval 解析改用 #BOT_SCORES 格式, 正则回退逻辑移除
管线: orchestrator eval→stress_summary→总分法解析, 闭环可验证
2026-07-20 15:40:59 +08:00
ebf2a0dc98
fix: N2H2V5独立分支用NeuralBotV5 - 新增NeuralBotV5类 + InitBots映射 + --n2h2v5参数
2026-07-18 11:20:14 +08:00
aa4cbd0a3e
fix: backup before selfplay, never rmtree — crash-safe
...
rmtree(training_data) → mv to training_data_prev
训练成功后再清理backup, 崩了数据不丢
2026-07-13 11:51:17 +08:00
f66f56d0f8
feat: ISMCTS q-value as training label
...
C#: TrainingCollector新增q_value列, IsmctsBot传入winRate
CSV: reward→q_value, ISMCTS状态带真实评估值, Neural填0
Python: 优先取ISMCTS状态+评估值训练, 无q_value的Neural状态跳过
旧CSV格式(reward)自动fallback到Neural-only过滤
信号从'这局谁赢'改为'ISMCTS评估这步有多好'
2026-07-13 11:38:42 +08:00
dc17c0f464
feat: position rotation every 10 games in self-play
...
--mix-rotate: 每10局轮换bot排列
[ISMCTS,ISMCTS,NEURAL] → [NEURAL,ISMCTS,ISMCTS] → [ISMCTS,NEURAL,ISMCTS]
Neural 三个位置都练到, 数据分布平衡
orchestrator改用--mix-rotate替换--mix
2026-07-13 11:28:45 +08:00
4e6ad234da
feat: Neural-only training, experience replay, per-round eval
...
3个训练效率提升:
1. Neural filter: V训练只取player=2数据, 排除ISMCTS状态干扰
旧格式(无player列)自动fallback全量数据
2. 经验回放: 保留最近3轮数据混入当前轮训练, 扩大分布覆盖
存储到 paodekuai-trainer/data/replay_buffer.pkl
3. 每轮eval: 训练后跑200局--eval测胜率, 下降>10%自动回滚
回滚到 model_prev.pt, 防止坏模型污染下轮数据
2026-07-13 11:26:40 +08:00
98ab4414a4
feat: improve V-training loop — weight decay, cosine LR, early stop
...
- Adam weight_decay=1e-5 to prevent overfitting
- CosineAnnealingLR 0.001→1e-5 over 50 epochs
- Early stopping after 10 epochs without improvement
- Epochs: 20→50 max (with early stop typically fewer)
2026-07-13 11:24:42 +08:00
4c1b1c971c
feat: 20k局/轮无限训练 + scan_wins支持存档目录
2026-07-13 08:43:39 +08:00
22acc3b2ca
feat: CSV加player列+#RESULT汇总 — 训练中直接看胜率进化
2026-07-13 08:40:14 +08:00
27d7e28236
fix: 训练编排器 — V训练从头开始 + ONNX外部数据文件复制
2026-07-13 08:14:05 +08:00
