修改算法部分bug

Author: wgyhhhh

docs/python/code.ipynb

@@ -208,7 +208,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 11,
+   "execution_count": null,
    "id": "1b269f11",
    "metadata": {},
    "outputs": [],
@@ -259,7 +259,7 @@
     "            2: np.array([0, 1]),   # 右（row不变，col增大）\n",
     "            3: np.array([1, 0]),   # 下（row增大，col不变）\n",
     "            4: np.array([0, -1]),  # 左（row不变，col减小）\n",
-    "}\n",
+    "        }\n",
     "\n",
     "        self.reward_list = reward_list if reward_list is not None else [0, 1, -10, -1]\n",
     "\n",