增加L0训练阶段的MCTS部分

2025-07-23 07:04:10 +08:00
parent 88bed2a1ef
commit 4410defbe5
23 changed files with 5205 additions and 0 deletions
--- a/l0_config.json
+++ b/l0_config.json
@@ -0,0 +1,47 @@
+{
+  "board_height": 3,
+  "board_width": 3,
+  "base_seed": 42,
+  "max_moves_per_game": 100,
+  
+  "mcts_c_param": 1.414,
+  "max_simulation_depth": 80,
+  "batch_size": null,
+  "device": "auto",
+  
+  "cache_size": 100000,
+  "data_dir": "data/l0_production",
+  "log_dir": "logs/l0_production",
+  "checkpoint_dir": "checkpoints/l0_production",
+  
+  "stages": [
+    {
+      "description": "初始探索阶段 - 快速生成基础数据",
+      "num_batches": 10,
+      "games_per_batch": 50,
+      "simulations_per_move": 100
+    },
+    {
+      "description": "深度搜索阶段 - 中等质量数据",
+      "num_batches": 20,
+      "games_per_batch": 75,
+      "simulations_per_move": 200
+    },
+    {
+      "description": "精细优化阶段 - 高质量数据",
+      "num_batches": 30,
+      "games_per_batch": 100,
+      "simulations_per_move": 300
+    },
+    {
+      "description": "最终收集阶段 - 顶级质量数据",
+      "num_batches": 20,
+      "games_per_batch": 150,
+      "simulations_per_move": 500
+    }
+  ],
+  
+  "checkpoint_interval": 3,
+  "quality_check_interval": 5,
+  "verbose": true
+}