feat: CSV加player列+#RESULT汇总 — 训练中直接看胜率进化

PdkFriendServer/Logic/PdkGameMain.cs

@@ -499,7 +499,7 @@ namespace PdkFriendServer.Logic
                                     float s = GamePack.Info.Score[i];
                                     rewards[i] = s > 0 ? 1f : s < 0 ? -1f : 0f;
                                 }
-                                TrainingCollector.FlushGame(_flushGameCounter++, rewards);
+                                TrainingCollector.FlushGame(_flushGameCounter++, rewards, GamePack.Info.OverPos, BotTypes);
                             }
 
                             if (DeskGameDo != null)

PdkFriendServer/Logic/TrainingCollector.cs

@@ -39,19 +39,21 @@ namespace PdkFriendServer.Logic
         /// 游戏结束，输出本轮训练数据到文件。
         /// rewards: 每个玩家的奖励 (1=赢, 0=第二, -1=第三)
         /// </summary>
-        public static void FlushGame(int gameId, float[] rewards)
+        public static void FlushGame(int gameId, float[] rewards, int winnerPos, string[] botTypes)
         {
             if (!Enabled || _records.Count == 0) return;
             var path = $"training_data/game_{gameId:D5}.csv";
             System.IO.Directory.CreateDirectory("training_data");
             using var w = new System.IO.StreamWriter(path);
-            w.WriteLine("state,action,reward");
+            w.WriteLine("state,action,reward,player");
             foreach (var r in _records)
             {
                 float reward = r.Player >= 0 && r.Player < rewards.Length ? rewards[r.Player] : 0;
                 var stateStr = string.Join(",", r.State.Select(f => f.ToString("F6")));
-                w.WriteLine($"\"{stateStr}\",{r.Action},{reward:F3}");
+                w.WriteLine($"\"{stateStr}\",{r.Action},{reward:F3},{r.Player}");
             }
+            // 游戏结果摘要 — 方便不中断训练即可评估模型进化
+            w.WriteLine($"#RESULT,winner={winnerPos},bots={string.Join(",", botTypes ?? new[]{"ISMCTS","ISMCTS","ISMCTS"})}");
             _records.Clear();
         }