Merge pull request dennybritz#96 from bwseoh/upstream

correct typos

Author: dennybritz

FA/Q-Learning with Value Function Approximation.ipynb

@@ -74,7 +74,7 @@
     "scaler = sklearn.preprocessing.StandardScaler()\n",
     "scaler.fit(observation_examples)\n",
     "\n",
-    "# Used to converte a state to a featurizes represenation.\n",
+    "# Used to convert a state to a featurized representation.\n",
     "# We use RBF kernels with different variances to cover different parts of the space\n",
     "featurizer = sklearn.pipeline.FeatureUnion([\n",
     "        (\"rbf1\", RBFSampler(gamma=5.0, n_components=100)),\n",
@@ -186,7 +186,7 @@
    "source": [
     "def q_learning(env, estimator, num_episodes, discount_factor=1.0, epsilon=0.1, epsilon_decay=1.0):\n",
     "    \"\"\"\n",
-    "    Q-Learning algorithm for fff-policy TD control using Function Approximation.\n",
+    "    Q-Learning algorithm for off-policy TD control using Function Approximation.\n",
     "    Finds the optimal greedy policy while following an epsilon-greedy policy.\n",
     "    \n",
     "    Args:\n",