fix a bug of forget passing in 'hallway' when invoke 'discrete_bayes_sim' which

generates a different likelihood value compared with previous cell

02-Discrete-Bayes.ipynb

@@ -1347,7 +1347,7 @@
    "outputs": [
     {
      "data": {
-      "image/png": "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 truncated
+      "image/png": "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 truncated
       "text/plain": [
        "<Figure size 900x400 with 1 Axes>"
       ]
@@ -1358,7 +1358,7 @@
    ],
    "source": [
     "measurements = [1, 0, 1, 0, 0, 1, 1]\n",
-    "priors, posteriors = discrete_bayes_sim(prior, kernel, measurements, z_prob);\n",
+    "priors, posteriors = discrete_bayes_sim(prior, kernel, measurements, z_prob, hallway);\n",
     "plot_posterior(posteriors, 6)"
    ]
   },