env代码小调整

env.py

@@ -36,9 +36,14 @@ class PartitionMazeEnv(gym.Env):
         self.trans_energy_factor = params['trans_energy_factor']
         self.battery_energy_capacity = params['battery_energy_capacity']
 
+        ##############################
+        # 可能需要手动修改的超参数
+        ##############################
+        self.CUT_NUM = 4    # 横切一半，竖切一半
+        self.BASE_LINE = 3500.0     # 基准时间，通过greedy或者蒙特卡洛计算出来
+
         self.phase = 0    # 阶段控制，0：区域划分阶段，1：迷宫初始化阶段，2：走迷宫阶段
         self.partition_step = 0      # 区域划分阶段步数，范围 0~4
-        self.CUT_NUM = 6    # 横切一半，竖切一半
         self.partition_values = np.zeros(
             self.CUT_NUM, dtype=np.float32)  # 存储 c₁, c₂, r₁, r₂
 
@@ -61,7 +66,6 @@ class PartitionMazeEnv(gym.Env):
 
         # 路径规划阶段相关变量
         self.MAX_STEPS = 50         # 迷宫走法步数上限
-        self.BASE_LINE = 3500.0     # 基准时间，通过greedy或者蒙特卡洛计算出来
         self.step_count = 0
         self.rectangles = {}
         self.car_pos = [(self.H / 2, self.W / 2) for _ in range(self.num_cars)]

human_action.py

@@ -5,7 +5,7 @@ env = PartitionMazeEnv()
 state = env.reset()
 print(state)
 
-action_series = [[0], [0], [0.5], [0], [0.1], [0.3]]
+action_series = [[0], [0.3], [0], [0], [0.1], [0.7]]
 
 for i in range(10):
     action = action_series[i]