diff --git a/tutorial1/rl-taxi-v3-using-q-learning.ipynb b/tutorial1/rl-taxi-v3-using-q-learning.ipynb
new file mode 100644
index 0000000..376f301
--- /dev/null
+++ b/tutorial1/rl-taxi-v3-using-q-learning.ipynb
@@ -0,0 +1,1598 @@
+{
+ "cells": [
+  {
+   "cell_type": "markdown",
+   "execution_count": null,
+   "metadata": {
+    "papermill": {
+     "duration": 0.005327,
+     "end_time": "2020-08-25T14:57:31.773342",
+     "exception": false,
+     "start_time": "2020-08-25T14:57:31.768015",
+     "status": "completed"
+    },
+    "tags": []
+   },
+   "source": [
+    "# Taxi-v3 using Q-Learning\n",
+    "\n",
+    "<img src=\"https://machinelearningjourney.com/wp-content/uploads/2020/07/Taxi-demo.gif\" style=\"height:200px;\"></img>\n",
+    "\n",
+    "\n",
+    "\n",
+    "There are 4 locations (labeled by different letters) and your job is to pick up the passenger at one location and drop him off in another. You receive +20 points for a successful dropoff, and lose 1 point for every timestep it takes. There is also a 10 point penalty for illegal pick-up and drop-off actions."
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "execution_count": null,
+   "metadata": {
+    "papermill": {
+     "duration": 0.003496,
+     "end_time": "2020-08-25T14:57:31.781034",
+     "exception": false,
+     "start_time": "2020-08-25T14:57:31.777538",
+     "status": "completed"
+    },
+    "tags": []
+   },
+   "source": [
+    "### 0. Necessary Dependancies"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 1,
+   "metadata": {
+    "_cell_guid": "79c7e3d0-c299-4dcb-8224-4455121ee9b0",
+    "_uuid": "d629ff2d2480ee46fbb7e2d37f6b5fab8052498a",
+    "execution": {
+     "iopub.execute_input": "2020-08-25T14:57:31.794019Z",
+     "iopub.status.busy": "2020-08-25T14:57:31.793384Z",
+     "iopub.status.idle": "2020-08-25T14:57:31.852938Z",
+     "shell.execute_reply": "2020-08-25T14:57:31.852320Z"
+    },
+    "papermill": {
+     "duration": 0.068197,
+     "end_time": "2020-08-25T14:57:31.853090",
+     "exception": false,
+     "start_time": "2020-08-25T14:57:31.784893",
+     "status": "completed"
+    },
+    "tags": []
+   },
+   "outputs": [],
+   "source": [
+    "import numpy as np\n",
+    "import gym\n",
+    "import random\n",
+    "\n",
+    "from tqdm import tqdm"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "execution_count": null,
+   "metadata": {
+    "papermill": {
+     "duration": 0.003555,
+     "end_time": "2020-08-25T14:57:31.861009",
+     "exception": false,
+     "start_time": "2020-08-25T14:57:31.857454",
+     "status": "completed"
+    },
+    "tags": []
+   },
+   "source": [
+    "### 1. Pre-Setup"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "execution_count": null,
+   "metadata": {
+    "papermill": {
+     "duration": 0.003625,
+     "end_time": "2020-08-25T14:57:31.868368",
+     "exception": false,
+     "start_time": "2020-08-25T14:57:31.864743",
+     "status": "completed"
+    },
+    "tags": []
+   },
+   "source": [
+    "**Create the Environment**"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 2,
+   "metadata": {
+    "execution": {
+     "iopub.execute_input": "2020-08-25T14:57:31.880366Z",
+     "iopub.status.busy": "2020-08-25T14:57:31.879762Z",
+     "iopub.status.idle": "2020-08-25T14:57:33.095674Z",
+     "shell.execute_reply": "2020-08-25T14:57:33.096470Z"
+    },
+    "papermill": {
+     "duration": 1.224504,
+     "end_time": "2020-08-25T14:57:33.096663",
+     "exception": false,
+     "start_time": "2020-08-25T14:57:31.872159",
+     "status": "completed"
+    },
+    "tags": []
+   },
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "+---------+\n",
+      "|R: |\u001b[43m \u001b[0m: :\u001b[35mG\u001b[0m|\n",
+      "| : | : : |\n",
+      "| : : : : |\n",
+      "| | : | : |\n",
+      "|\u001b[34;1mY\u001b[0m| : |B: |\n",
+      "+---------+\n",
+      "\n"
+     ]
+    }
+   ],
+   "source": [
+    "env = gym.make('Taxi-v3')\n",
+    "env.render()"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "execution_count": null,
+   "metadata": {
+    "papermill": {
+     "duration": 0.003726,
+     "end_time": "2020-08-25T14:57:33.105305",
+     "exception": false,
+     "start_time": "2020-08-25T14:57:33.101579",
+     "status": "completed"
+    },
+    "tags": []
+   },
+   "source": [
+    "**Create the Q-Table**\n",
+    "\n",
+    "The Q-table is NxM table where N corresponds to the number of states and M corresponds to the number of actions that the agent can take."
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 3,
+   "metadata": {
+    "execution": {
+     "iopub.execute_input": "2020-08-25T14:57:33.119712Z",
+     "iopub.status.busy": "2020-08-25T14:57:33.119122Z",
+     "iopub.status.idle": "2020-08-25T14:57:33.122348Z",
+     "shell.execute_reply": "2020-08-25T14:57:33.122834Z"
+    },
+    "papermill": {
+     "duration": 0.01239,
+     "end_time": "2020-08-25T14:57:33.122980",
+     "exception": false,
+     "start_time": "2020-08-25T14:57:33.110590",
+     "status": "completed"
+    },
+    "tags": []
+   },
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "Total possible actions: 6\n",
+      "Total states: 500\n"
+     ]
+    }
+   ],
+   "source": [
+    "action_size = env.action_space.n\n",
+    "print(f\"Total possible actions: {action_size}\")\n",
+    "\n",
+    "state_size = env.observation_space.n\n",
+    "print(f\"Total states: {state_size}\")"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 4,
+   "metadata": {
+    "execution": {
+     "iopub.execute_input": "2020-08-25T14:57:33.136502Z",
+     "iopub.status.busy": "2020-08-25T14:57:33.135665Z",
+     "iopub.status.idle": "2020-08-25T14:57:33.139228Z",
+     "shell.execute_reply": "2020-08-25T14:57:33.138593Z"
+    },
+    "papermill": {
+     "duration": 0.012441,
+     "end_time": "2020-08-25T14:57:33.139335",
+     "exception": false,
+     "start_time": "2020-08-25T14:57:33.126894",
+     "status": "completed"
+    },
+    "tags": []
+   },
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "[[0. 0. 0. 0. 0. 0.]\n",
+      " [0. 0. 0. 0. 0. 0.]\n",
+      " [0. 0. 0. 0. 0. 0.]\n",
+      " ...\n",
+      " [0. 0. 0. 0. 0. 0.]\n",
+      " [0. 0. 0. 0. 0. 0.]\n",
+      " [0. 0. 0. 0. 0. 0.]]\n"
+     ]
+    }
+   ],
+   "source": [
+    "qtable = np.zeros((state_size,action_size))\n",
+    "print(qtable)"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "execution_count": null,
+   "metadata": {
+    "papermill": {
+     "duration": 0.003682,
+     "end_time": "2020-08-25T14:57:33.147245",
+     "exception": false,
+     "start_time": "2020-08-25T14:57:33.143563",
+     "status": "completed"
+    },
+    "tags": []
+   },
+   "source": [
+    "**Hyperparameters**"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 5,
+   "metadata": {
+    "execution": {
+     "iopub.execute_input": "2020-08-25T14:57:33.160242Z",
+     "iopub.status.busy": "2020-08-25T14:57:33.159640Z",
+     "iopub.status.idle": "2020-08-25T14:57:33.162452Z",
+     "shell.execute_reply": "2020-08-25T14:57:33.161848Z"
+    },
+    "papermill": {
+     "duration": 0.011405,
+     "end_time": "2020-08-25T14:57:33.162551",
+     "exception": false,
+     "start_time": "2020-08-25T14:57:33.151146",
+     "status": "completed"
+    },
+    "tags": []
+   },
+   "outputs": [],
+   "source": [
+    "total_episodes = 50000       # Total episodes to train the agent for\n",
+    "total_test_episodes = 10     # Number of test episodes\n",
+    "max_steps = 99               # Terminate if the agent takes more than 99 steps\n",
+    "\n",
+    "alpha = 0.7                  # Learning rate\n",
+    "gamma = 0.618                # Discounting rate for rewards\n",
+    "\n",
+    "# parameters for maintaining trade-off between exploration-exploitation\n",
+    "epsilon = 1.0                # Exploration rate\n",
+    "max_epsilon = 1.0            # Exploration probability at the start\n",
+    "min_epsilon = 0.01           # Minimum exploration probability\n",
+    "decay_rate = 0.01            # rate at which epsilon shrinks "
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "execution_count": null,
+   "metadata": {
+    "papermill": {
+     "duration": 0.003746,
+     "end_time": "2020-08-25T14:57:33.170560",
+     "exception": false,
+     "start_time": "2020-08-25T14:57:33.166814",
+     "status": "completed"
+    },
+    "tags": []
+   },
+   "source": [
+    "### 2. Q-Learning Algorithm\n",
+    "\n",
+    "![](https://leimao.github.io/images/blog/2019-03-14-RL-On-Policy-VS-Off-Policy/q-learning.png)"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 6,
+   "metadata": {
+    "execution": {
+     "iopub.execute_input": "2020-08-25T14:57:33.187463Z",
+     "iopub.status.busy": "2020-08-25T14:57:33.186851Z",
+     "iopub.status.idle": "2020-08-25T14:57:52.341020Z",
+     "shell.execute_reply": "2020-08-25T14:57:52.340241Z"
+    },
+    "papermill": {
+     "duration": 19.166629,
+     "end_time": "2020-08-25T14:57:52.341197",
+     "exception": false,
+     "start_time": "2020-08-25T14:57:33.174568",
+     "status": "completed"
+    },
+    "tags": []
+   },
+   "outputs": [
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "100%|██████████| 50000/50000 [00:19<00:00, 2612.08it/s]\n"
+     ]
+    }
+   ],
+   "source": [
+    "# iterate over every episode\n",
+    "for episode in tqdm(range(total_episodes)):\n",
+    "    \n",
+    "    # Reset the environment at every episode\n",
+    "    state = env.reset()\n",
+    "    # flag to check if episode is terminated or not\n",
+    "    done = False\n",
+    "    \n",
+    "    # iterate over all steps that the agent can take in an episode\n",
+    "    for step in range(max_steps): \n",
+    "        \n",
+    "        # Select an action based on the epsilon-greedy policy\n",
+    "        \n",
+    "        # probability to select exploitation\n",
+    "        one_minus_epsilon = random.uniform(0,1)\n",
+    "        \n",
+    "        # if one_minus_epsilon is greater than epsilon then exploit \n",
+    "        if one_minus_epsilon > epsilon:\n",
+    "            action = np.argmax(qtable[state,:])\n",
+    "        # else explore by selecting an action randomly\n",
+    "        else:\n",
+    "            action = env.action_space.sample()\n",
+    "            \n",
+    "        # Take this action to reach the next state and get a reward \n",
+    "        new_state, reward, done, info = env.step(action)\n",
+    "        \n",
+    "        # update the Q-Table based on the formula given in the algorithm\n",
+    "        qtable[state,action] = qtable[state,action] + alpha*(reward + gamma*np.max(qtable[new_state,:]) - qtable[state,action])\n",
+    "        \n",
+    "        # update the current state\n",
+    "        state = new_state\n",
+    "        \n",
+    "        # if the agent has reached termination state then break\n",
+    "        if done:\n",
+    "            break\n",
+    "        \n",
+    "    # epsilon decay to maintain trade-off between exploration-exploitation\n",
+    "    epsilon = min_epsilon + (max_epsilon - min_epsilon)*np.exp(-decay_rate*episode)"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "execution_count": null,
+   "metadata": {
+    "papermill": {
+     "duration": 0.0119,
+     "end_time": "2020-08-25T14:57:52.367006",
+     "exception": false,
+     "start_time": "2020-08-25T14:57:52.355106",
+     "status": "completed"
+    },
+    "tags": []
+   },
+   "source": [
+    "### 3. Test the agent"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 7,
+   "metadata": {
+    "execution": {
+     "iopub.execute_input": "2020-08-25T14:57:52.401923Z",
+     "iopub.status.busy": "2020-08-25T14:57:52.400945Z",
+     "iopub.status.idle": "2020-08-25T14:57:52.430227Z",
+     "shell.execute_reply": "2020-08-25T14:57:52.426409Z"
+    },
+    "papermill": {
+     "duration": 0.051592,
+     "end_time": "2020-08-25T14:57:52.430443",
+     "exception": false,
+     "start_time": "2020-08-25T14:57:52.378851",
+     "status": "completed"
+    },
+    "tags": []
+   },
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "********************************************************************************\n",
+      "Episode 1:\n",
+      "+---------+\n",
+      "|\u001b[34;1mR\u001b[0m: | : :G|\n",
+      "| : | : : |\n",
+      "| : : : : |\n",
+      "| | :\u001b[43m \u001b[0m| : |\n",
+      "|\u001b[35mY\u001b[0m| : |B: |\n",
+      "+---------+\n",
+      "\n",
+      "+---------+\n",
+      "|\u001b[34;1mR\u001b[0m: | : :G|\n",
+      "| : | : : |\n",
+      "| : :\u001b[43m \u001b[0m: : |\n",
+      "| | : | : |\n",
+      "|\u001b[35mY\u001b[0m| : |B: |\n",
+      "+---------+\n",
+      "  (North)\n",
+      "+---------+\n",
+      "|\u001b[34;1mR\u001b[0m: | : :G|\n",
+      "| : | : : |\n",
+      "| :\u001b[43m \u001b[0m: : : |\n",
+      "| | : | : |\n",
+      "|\u001b[35mY\u001b[0m| : |B: |\n",
+      "+---------+\n",
+      "  (West)\n",
+      "+---------+\n",
+      "|\u001b[34;1mR\u001b[0m: | : :G|\n",
+      "| :\u001b[43m \u001b[0m| : : |\n",
+      "| : : : : |\n",
+      "| | : | : |\n",
+      "|\u001b[35mY\u001b[0m| : |B: |\n",
+      "+---------+\n",
+      "  (North)\n",
+      "+---------+\n",
+      "|\u001b[34;1mR\u001b[0m: | : :G|\n",
+      "|\u001b[43m \u001b[0m: | : : |\n",
+      "| : : : : |\n",
+      "| | : | : |\n",
+      "|\u001b[35mY\u001b[0m| : |B: |\n",
+      "+---------+\n",
+      "  (West)\n",
+      "+---------+\n",
+      "|\u001b[34;1m\u001b[43mR\u001b[0m\u001b[0m: | : :G|\n",
+      "| : | : : |\n",
+      "| : : : : |\n",
+      "| | : | : |\n",
+      "|\u001b[35mY\u001b[0m| : |B: |\n",
+      "+---------+\n",
+      "  (North)\n",
+      "+---------+\n",
+      "|\u001b[42mR\u001b[0m: | : :G|\n",
+      "| : | : : |\n",
+      "| : : : : |\n",
+      "| | : | : |\n",
+      "|\u001b[35mY\u001b[0m| : |B: |\n",
+      "+---------+\n",
+      "  (Pickup)\n",
+      "+---------+\n",
+      "|R: | : :G|\n",
+      "|\u001b[42m_\u001b[0m: | : : |\n",
+      "| : : : : |\n",
+      "| | : | : |\n",
+      "|\u001b[35mY\u001b[0m| : |B: |\n",
+      "+---------+\n",
+      "  (South)\n",
+      "+---------+\n",
+      "|R: | : :G|\n",
+      "| : | : : |\n",
+      "|\u001b[42m_\u001b[0m: : : : |\n",
+      "| | : | : |\n",
+      "|\u001b[35mY\u001b[0m| : |B: |\n",
+      "+---------+\n",
+      "  (South)\n",
+      "+---------+\n",
+      "|R: | : :G|\n",
+      "| : | : : |\n",
+      "| : : : : |\n",
+      "|\u001b[42m_\u001b[0m| : | : |\n",
+      "|\u001b[35mY\u001b[0m| : |B: |\n",
+      "+---------+\n",
+      "  (South)\n",
+      "+---------+\n",
+      "|R: | : :G|\n",
+      "| : | : : |\n",
+      "| : : : : |\n",
+      "| | : | : |\n",
+      "|\u001b[35m\u001b[42mY\u001b[0m\u001b[0m| : |B: |\n",
+      "+---------+\n",
+      "  (South)\n",
+      "Score: 10\n",
+      "********************************************************************************\n",
+      "Episode 2:\n",
+      "+---------+\n",
+      "|R: | : :\u001b[34;1mG\u001b[0m|\n",
+      "| : | : : |\n",
+      "| : : : : |\n",
+      "|\u001b[43m \u001b[0m| : | : |\n",
+      "|\u001b[35mY\u001b[0m| : |B: |\n",
+      "+---------+\n",
+      "\n",
+      "+---------+\n",
+      "|R: | : :\u001b[34;1mG\u001b[0m|\n",
+      "| : | : : |\n",
+      "|\u001b[43m \u001b[0m: : : : |\n",
+      "| | : | : |\n",
+      "|\u001b[35mY\u001b[0m| : |B: |\n",
+      "+---------+\n",
+      "  (North)\n",
+      "+---------+\n",
+      "|R: | : :\u001b[34;1mG\u001b[0m|\n",
+      "| : | : : |\n",
+      "| :\u001b[43m \u001b[0m: : : |\n",
+      "| | : | : |\n",
+      "|\u001b[35mY\u001b[0m| : |B: |\n",
+      "+---------+\n",
+      "  (East)\n",
+      "+---------+\n",
+      "|R: | : :\u001b[34;1mG\u001b[0m|\n",
+      "| : | : : |\n",
+      "| : :\u001b[43m \u001b[0m: : |\n",
+      "| | : | : |\n",
+      "|\u001b[35mY\u001b[0m| : |B: |\n",
+      "+---------+\n",
+      "  (East)\n",
+      "+---------+\n",
+      "|R: | : :\u001b[34;1mG\u001b[0m|\n",
+      "| : | : : |\n",
+      "| : : :\u001b[43m \u001b[0m: |\n",
+      "| | : | : |\n",
+      "|\u001b[35mY\u001b[0m| : |B: |\n",
+      "+---------+\n",
+      "  (East)\n",
+      "+---------+\n",
+      "|R: | : :\u001b[34;1mG\u001b[0m|\n",
+      "| : | : : |\n",
+      "| : : : :\u001b[43m \u001b[0m|\n",
+      "| | : | : |\n",
+      "|\u001b[35mY\u001b[0m| : |B: |\n",
+      "+---------+\n",
+      "  (East)\n",
+      "+---------+\n",
+      "|R: | : :\u001b[34;1mG\u001b[0m|\n",
+      "| : | : :\u001b[43m \u001b[0m|\n",
+      "| : : : : |\n",
+      "| | : | : |\n",
+      "|\u001b[35mY\u001b[0m| : |B: |\n",
+      "+---------+\n",
+      "  (North)\n",
+      "+---------+\n",
+      "|R: | : :\u001b[34;1m\u001b[43mG\u001b[0m\u001b[0m|\n",
+      "| : | : : |\n",
+      "| : : : : |\n",
+      "| | : | : |\n",
+      "|\u001b[35mY\u001b[0m| : |B: |\n",
+      "+---------+\n",
+      "  (North)\n",
+      "+---------+\n",
+      "|R: | : :\u001b[42mG\u001b[0m|\n",
+      "| : | : : |\n",
+      "| : : : : |\n",
+      "| | : | : |\n",
+      "|\u001b[35mY\u001b[0m| : |B: |\n",
+      "+---------+\n",
+      "  (Pickup)\n",
+      "+---------+\n",
+      "|R: | : :G|\n",
+      "| : | : :\u001b[42m_\u001b[0m|\n",
+      "| : : : : |\n",
+      "| | : | : |\n",
+      "|\u001b[35mY\u001b[0m| : |B: |\n",
+      "+---------+\n",
+      "  (South)\n",
+      "+---------+\n",
+      "|R: | : :G|\n",
+      "| : | : : |\n",
+      "| : : : :\u001b[42m_\u001b[0m|\n",
+      "| | : | : |\n",
+      "|\u001b[35mY\u001b[0m| : |B: |\n",
+      "+---------+\n",
+      "  (South)\n",
+      "+---------+\n",
+      "|R: | : :G|\n",
+      "| : | : : |\n",
+      "| : : :\u001b[42m_\u001b[0m: |\n",
+      "| | : | : |\n",
+      "|\u001b[35mY\u001b[0m| : |B: |\n",
+      "+---------+\n",
+      "  (West)\n",
+      "+---------+\n",
+      "|R: | : :G|\n",
+      "| : | : : |\n",
+      "| : :\u001b[42m_\u001b[0m: : |\n",
+      "| | : | : |\n",
+      "|\u001b[35mY\u001b[0m| : |B: |\n",
+      "+---------+\n",
+      "  (West)\n",
+      "+---------+\n",
+      "|R: | : :G|\n",
+      "| : | : : |\n",
+      "| :\u001b[42m_\u001b[0m: : : |\n",
+      "| | : | : |\n",
+      "|\u001b[35mY\u001b[0m| : |B: |\n",
+      "+---------+\n",
+      "  (West)\n",
+      "+---------+\n",
+      "|R: | : :G|\n",
+      "| : | : : |\n",
+      "|\u001b[42m_\u001b[0m: : : : |\n",
+      "| | : | : |\n",
+      "|\u001b[35mY\u001b[0m| : |B: |\n",
+      "+---------+\n",
+      "  (West)\n",
+      "+---------+\n",
+      "|R: | : :G|\n",
+      "| : | : : |\n",
+      "| : : : : |\n",
+      "|\u001b[42m_\u001b[0m| : | : |\n",
+      "|\u001b[35mY\u001b[0m| : |B: |\n",
+      "+---------+\n",
+      "  (South)\n",
+      "+---------+\n",
+      "|R: | : :G|\n",
+      "| : | : : |\n",
+      "| : : : : |\n",
+      "| | : | : |\n",
+      "|\u001b[35m\u001b[42mY\u001b[0m\u001b[0m| : |B: |\n",
+      "+---------+\n",
+      "  (South)\n",
+      "Score: 4\n",
+      "********************************************************************************\n",
+      "Episode 3:\n",
+      "+---------+\n",
+      "|\u001b[35mR\u001b[0m:\u001b[43m \u001b[0m| : :G|\n",
+      "| : | : : |\n",
+      "| : : : : |\n",
+      "| | : | : |\n",
+      "|\u001b[34;1mY\u001b[0m| : |B: |\n",
+      "+---------+\n",
+      "\n",
+      "+---------+\n",
+      "|\u001b[35mR\u001b[0m: | : :G|\n",
+      "| :\u001b[43m \u001b[0m| : : |\n",
+      "| : : : : |\n",
+      "| | : | : |\n",
+      "|\u001b[34;1mY\u001b[0m| : |B: |\n",
+      "+---------+\n",
+      "  (South)\n",
+      "+---------+\n",
+      "|\u001b[35mR\u001b[0m: | : :G|\n",
+      "| : | : : |\n",
+      "| :\u001b[43m \u001b[0m: : : |\n",
+      "| | : | : |\n",
+      "|\u001b[34;1mY\u001b[0m| : |B: |\n",
+      "+---------+\n",
+      "  (South)\n",
+      "+---------+\n",
+      "|\u001b[35mR\u001b[0m: | : :G|\n",
+      "| : | : : |\n",
+      "|\u001b[43m \u001b[0m: : : : |\n",
+      "| | : | : |\n",
+      "|\u001b[34;1mY\u001b[0m| : |B: |\n",
+      "+---------+\n",
+      "  (West)\n",
+      "+---------+\n",
+      "|\u001b[35mR\u001b[0m: | : :G|\n",
+      "| : | : : |\n",
+      "| : : : : |\n",
+      "|\u001b[43m \u001b[0m| : | : |\n",
+      "|\u001b[34;1mY\u001b[0m| : |B: |\n",
+      "+---------+\n",
+      "  (South)\n",
+      "+---------+\n",
+      "|\u001b[35mR\u001b[0m: | : :G|\n",
+      "| : | : : |\n",
+      "| : : : : |\n",
+      "| | : | : |\n",
+      "|\u001b[34;1m\u001b[43mY\u001b[0m\u001b[0m| : |B: |\n",
+      "+---------+\n",
+      "  (South)\n",
+      "+---------+\n",
+      "|\u001b[35mR\u001b[0m: | : :G|\n",
+      "| : | : : |\n",
+      "| : : : : |\n",
+      "| | : | : |\n",
+      "|\u001b[42mY\u001b[0m| : |B: |\n",
+      "+---------+\n",
+      "  (Pickup)\n",
+      "+---------+\n",
+      "|\u001b[35mR\u001b[0m: | : :G|\n",
+      "| : | : : |\n",
+      "| : : : : |\n",
+      "|\u001b[42m_\u001b[0m| : | : |\n",
+      "|Y| : |B: |\n",
+      "+---------+\n",
+      "  (North)\n",
+      "+---------+\n",
+      "|\u001b[35mR\u001b[0m: | : :G|\n",
+      "| : | : : |\n",
+      "|\u001b[42m_\u001b[0m: : : : |\n",
+      "| | : | : |\n",
+      "|Y| : |B: |\n",
+      "+---------+\n",
+      "  (North)\n",
+      "+---------+\n",
+      "|\u001b[35mR\u001b[0m: | : :G|\n",
+      "|\u001b[42m_\u001b[0m: | : : |\n",
+      "| : : : : |\n",
+      "| | : | : |\n",
+      "|Y| : |B: |\n",
+      "+---------+\n",
+      "  (North)\n",
+      "+---------+\n",
+      "|\u001b[35m\u001b[42mR\u001b[0m\u001b[0m: | : :G|\n",
+      "| : | : : |\n",
+      "| : : : : |\n",
+      "| | : | : |\n",
+      "|Y| : |B: |\n",
+      "+---------+\n",
+      "  (North)\n",
+      "Score: 10\n",
+      "********************************************************************************\n",
+      "Episode 4:\n",
+      "+---------+\n",
+      "|\u001b[34;1mR\u001b[0m: | :\u001b[43m \u001b[0m:G|\n",
+      "| : | : : |\n",
+      "| : : : : |\n",
+      "| | : | : |\n",
+      "|Y| : |\u001b[35mB\u001b[0m: |\n",
+      "+---------+\n",
+      "\n",
+      "+---------+\n",
+      "|\u001b[34;1mR\u001b[0m: | : :G|\n",
+      "| : | :\u001b[43m \u001b[0m: |\n",
+      "| : : : : |\n",
+      "| | : | : |\n",
+      "|Y| : |\u001b[35mB\u001b[0m: |\n",
+      "+---------+\n",
+      "  (South)\n",
+      "+---------+\n",
+      "|\u001b[34;1mR\u001b[0m: | : :G|\n",
+      "| : | : : |\n",
+      "| : : :\u001b[43m \u001b[0m: |\n",
+      "| | : | : |\n",
+      "|Y| : |\u001b[35mB\u001b[0m: |\n",
+      "+---------+\n",
+      "  (South)\n",
+      "+---------+\n",
+      "|\u001b[34;1mR\u001b[0m: | : :G|\n",
+      "| : | : : |\n",
+      "| : :\u001b[43m \u001b[0m: : |\n",
+      "| | : | : |\n",
+      "|Y| : |\u001b[35mB\u001b[0m: |\n",
+      "+---------+\n",
+      "  (West)\n",
+      "+---------+\n",
+      "|\u001b[34;1mR\u001b[0m: | : :G|\n",
+      "| : | : : |\n",
+      "| :\u001b[43m \u001b[0m: : : |\n",
+      "| | : | : |\n",
+      "|Y| : |\u001b[35mB\u001b[0m: |\n",
+      "+---------+\n",
+      "  (West)\n",
+      "+---------+\n",
+      "|\u001b[34;1mR\u001b[0m: | : :G|\n",
+      "| : | : : |\n",
+      "|\u001b[43m \u001b[0m: : : : |\n",
+      "| | : | : |\n",
+      "|Y| : |\u001b[35mB\u001b[0m: |\n",
+      "+---------+\n",
+      "  (West)\n",
+      "+---------+\n",
+      "|\u001b[34;1mR\u001b[0m: | : :G|\n",
+      "|\u001b[43m \u001b[0m: | : : |\n",
+      "| : : : : |\n",
+      "| | : | : |\n",
+      "|Y| : |\u001b[35mB\u001b[0m: |\n",
+      "+---------+\n",
+      "  (North)\n",
+      "+---------+\n",
+      "|\u001b[34;1m\u001b[43mR\u001b[0m\u001b[0m: | : :G|\n",
+      "| : | : : |\n",
+      "| : : : : |\n",
+      "| | : | : |\n",
+      "|Y| : |\u001b[35mB\u001b[0m: |\n",
+      "+---------+\n",
+      "  (North)\n",
+      "+---------+\n",
+      "|\u001b[42mR\u001b[0m: | : :G|\n",
+      "| : | : : |\n",
+      "| : : : : |\n",
+      "| | : | : |\n",
+      "|Y| : |\u001b[35mB\u001b[0m: |\n",
+      "+---------+\n",
+      "  (Pickup)\n",
+      "+---------+\n",
+      "|R: | : :G|\n",
+      "|\u001b[42m_\u001b[0m: | : : |\n",
+      "| : : : : |\n",
+      "| | : | : |\n",
+      "|Y| : |\u001b[35mB\u001b[0m: |\n",
+      "+---------+\n",
+      "  (South)\n",
+      "+---------+\n",
+      "|R: | : :G|\n",
+      "| :\u001b[42m_\u001b[0m| : : |\n",
+      "| : : : : |\n",
+      "| | : | : |\n",
+      "|Y| : |\u001b[35mB\u001b[0m: |\n",
+      "+---------+\n",
+      "  (East)\n",
+      "+---------+\n",
+      "|R: | : :G|\n",
+      "| : | : : |\n",
+      "| :\u001b[42m_\u001b[0m: : : |\n",
+      "| | : | : |\n",
+      "|Y| : |\u001b[35mB\u001b[0m: |\n",
+      "+---------+\n",
+      "  (South)\n",
+      "+---------+\n",
+      "|R: | : :G|\n",
+      "| : | : : |\n",
+      "| : :\u001b[42m_\u001b[0m: : |\n",
+      "| | : | : |\n",
+      "|Y| : |\u001b[35mB\u001b[0m: |\n",
+      "+---------+\n",
+      "  (East)\n",
+      "+---------+\n",
+      "|R: | : :G|\n",
+      "| : | : : |\n",
+      "| : : :\u001b[42m_\u001b[0m: |\n",
+      "| | : | : |\n",
+      "|Y| : |\u001b[35mB\u001b[0m: |\n",
+      "+---------+\n",
+      "  (East)\n",
+      "+---------+\n",
+      "|R: | : :G|\n",
+      "| : | : : |\n",
+      "| : : : : |\n",
+      "| | : |\u001b[42m_\u001b[0m: |\n",
+      "|Y| : |\u001b[35mB\u001b[0m: |\n",
+      "+---------+\n",
+      "  (South)\n",
+      "+---------+\n",
+      "|R: | : :G|\n",
+      "| : | : : |\n",
+      "| : : : : |\n",
+      "| | : | : |\n",
+      "|Y| : |\u001b[35m\u001b[42mB\u001b[0m\u001b[0m: |\n",
+      "+---------+\n",
+      "  (South)\n",
+      "Score: 5\n",
+      "********************************************************************************\n",
+      "Episode 5:\n",
+      "+---------+\n",
+      "|R: | : :G|\n",
+      "| : | : : |\n",
+      "| : : : : |\n",
+      "| | : | : |\n",
+      "|\u001b[35mY\u001b[0m| : |\u001b[34;1m\u001b[43mB\u001b[0m\u001b[0m: |\n",
+      "+---------+\n",
+      "\n",
+      "+---------+\n",
+      "|R: | : :G|\n",
+      "| : | : : |\n",
+      "| : : : : |\n",
+      "| | : | : |\n",
+      "|\u001b[35mY\u001b[0m| : |\u001b[42mB\u001b[0m: |\n",
+      "+---------+\n",
+      "  (Pickup)\n",
+      "+---------+\n",
+      "|R: | : :G|\n",
+      "| : | : : |\n",
+      "| : : : : |\n",
+      "| | : |\u001b[42m_\u001b[0m: |\n",
+      "|\u001b[35mY\u001b[0m| : |B: |\n",
+      "+---------+\n",
+      "  (North)\n",
+      "+---------+\n",
+      "|R: | : :G|\n",
+      "| : | : : |\n",
+      "| : : :\u001b[42m_\u001b[0m: |\n",
+      "| | : | : |\n",
+      "|\u001b[35mY\u001b[0m| : |B: |\n",
+      "+---------+\n",
+      "  (North)\n",
+      "+---------+\n",
+      "|R: | : :G|\n",
+      "| : | : : |\n",
+      "| : :\u001b[42m_\u001b[0m: : |\n",
+      "| | : | : |\n",
+      "|\u001b[35mY\u001b[0m| : |B: |\n",
+      "+---------+\n",
+      "  (West)\n",
+      "+---------+\n",
+      "|R: | : :G|\n",
+      "| : | : : |\n",
+      "| :\u001b[42m_\u001b[0m: : : |\n",
+      "| | : | : |\n",
+      "|\u001b[35mY\u001b[0m| : |B: |\n",
+      "+---------+\n",
+      "  (West)\n",
+      "+---------+\n",
+      "|R: | : :G|\n",
+      "| : | : : |\n",
+      "|\u001b[42m_\u001b[0m: : : : |\n",
+      "| | : | : |\n",
+      "|\u001b[35mY\u001b[0m| : |B: |\n",
+      "+---------+\n",
+      "  (West)\n",
+      "+---------+\n",
+      "|R: | : :G|\n",
+      "| : | : : |\n",
+      "| : : : : |\n",
+      "|\u001b[42m_\u001b[0m| : | : |\n",
+      "|\u001b[35mY\u001b[0m| : |B: |\n",
+      "+---------+\n",
+      "  (South)\n",
+      "+---------+\n",
+      "|R: | : :G|\n",
+      "| : | : : |\n",
+      "| : : : : |\n",
+      "| | : | : |\n",
+      "|\u001b[35m\u001b[42mY\u001b[0m\u001b[0m| : |B: |\n",
+      "+---------+\n",
+      "  (South)\n",
+      "Score: 12\n",
+      "********************************************************************************\n",
+      "Episode 6:\n",
+      "+---------+\n",
+      "|R: | : :\u001b[34;1mG\u001b[0m|\n",
+      "| : | : : |\n",
+      "| : : : : |\n",
+      "| | : | : |\n",
+      "|\u001b[35mY\u001b[0m|\u001b[43m \u001b[0m: |B: |\n",
+      "+---------+\n",
+      "\n",
+      "+---------+\n",
+      "|R: | : :\u001b[34;1mG\u001b[0m|\n",
+      "| : | : : |\n",
+      "| : : : : |\n",
+      "| |\u001b[43m \u001b[0m: | : |\n",
+      "|\u001b[35mY\u001b[0m| : |B: |\n",
+      "+---------+\n",
+      "  (North)\n",
+      "+---------+\n",
+      "|R: | : :\u001b[34;1mG\u001b[0m|\n",
+      "| : | : : |\n",
+      "| :\u001b[43m \u001b[0m: : : |\n",
+      "| | : | : |\n",
+      "|\u001b[35mY\u001b[0m| : |B: |\n",
+      "+---------+\n",
+      "  (North)\n",
+      "+---------+\n",
+      "|R: | : :\u001b[34;1mG\u001b[0m|\n",
+      "| : | : : |\n",
+      "| : :\u001b[43m \u001b[0m: : |\n",
+      "| | : | : |\n",
+      "|\u001b[35mY\u001b[0m| : |B: |\n",
+      "+---------+\n",
+      "  (East)\n",
+      "+---------+\n",
+      "|R: | : :\u001b[34;1mG\u001b[0m|\n",
+      "| : | : : |\n",
+      "| : : :\u001b[43m \u001b[0m: |\n",
+      "| | : | : |\n",
+      "|\u001b[35mY\u001b[0m| : |B: |\n",
+      "+---------+\n",
+      "  (East)\n",
+      "+---------+\n",
+      "|R: | : :\u001b[34;1mG\u001b[0m|\n",
+      "| : | : : |\n",
+      "| : : : :\u001b[43m \u001b[0m|\n",
+      "| | : | : |\n",
+      "|\u001b[35mY\u001b[0m| : |B: |\n",
+      "+---------+\n",
+      "  (East)\n",
+      "+---------+\n",
+      "|R: | : :\u001b[34;1mG\u001b[0m|\n",
+      "| : | : :\u001b[43m \u001b[0m|\n",
+      "| : : : : |\n",
+      "| | : | : |\n",
+      "|\u001b[35mY\u001b[0m| : |B: |\n",
+      "+---------+\n",
+      "  (North)\n",
+      "+---------+\n",
+      "|R: | : :\u001b[34;1m\u001b[43mG\u001b[0m\u001b[0m|\n",
+      "| : | : : |\n",
+      "| : : : : |\n",
+      "| | : | : |\n",
+      "|\u001b[35mY\u001b[0m| : |B: |\n",
+      "+---------+\n",
+      "  (North)\n",
+      "+---------+\n",
+      "|R: | : :\u001b[42mG\u001b[0m|\n",
+      "| : | : : |\n",
+      "| : : : : |\n",
+      "| | : | : |\n",
+      "|\u001b[35mY\u001b[0m| : |B: |\n",
+      "+---------+\n",
+      "  (Pickup)\n",
+      "+---------+\n",
+      "|R: | : :G|\n",
+      "| : | : :\u001b[42m_\u001b[0m|\n",
+      "| : : : : |\n",
+      "| | : | : |\n",
+      "|\u001b[35mY\u001b[0m| : |B: |\n",
+      "+---------+\n",
+      "  (South)\n",
+      "+---------+\n",
+      "|R: | : :G|\n",
+      "| : | : : |\n",
+      "| : : : :\u001b[42m_\u001b[0m|\n",
+      "| | : | : |\n",
+      "|\u001b[35mY\u001b[0m| : |B: |\n",
+      "+---------+\n",
+      "  (South)\n",
+      "+---------+\n",
+      "|R: | : :G|\n",
+      "| : | : : |\n",
+      "| : : :\u001b[42m_\u001b[0m: |\n",
+      "| | : | : |\n",
+      "|\u001b[35mY\u001b[0m| : |B: |\n",
+      "+---------+\n",
+      "  (West)\n",
+      "+---------+\n",
+      "|R: | : :G|\n",
+      "| : | : : |\n",
+      "| : :\u001b[42m_\u001b[0m: : |\n",
+      "| | : | : |\n",
+      "|\u001b[35mY\u001b[0m| : |B: |\n",
+      "+---------+\n",
+      "  (West)\n",
+      "+---------+\n",
+      "|R: | : :G|\n",
+      "| : | : : |\n",
+      "| :\u001b[42m_\u001b[0m: : : |\n",
+      "| | : | : |\n",
+      "|\u001b[35mY\u001b[0m| : |B: |\n",
+      "+---------+\n",
+      "  (West)\n",
+      "+---------+\n",
+      "|R: | : :G|\n",
+      "| : | : : |\n",
+      "|\u001b[42m_\u001b[0m: : : : |\n",
+      "| | : | : |\n",
+      "|\u001b[35mY\u001b[0m| : |B: |\n",
+      "+---------+\n",
+      "  (West)\n",
+      "+---------+\n",
+      "|R: | : :G|\n",
+      "| : | : : |\n",
+      "| : : : : |\n",
+      "|\u001b[42m_\u001b[0m| : | : |\n",
+      "|\u001b[35mY\u001b[0m| : |B: |\n",
+      "+---------+\n",
+      "  (South)\n",
+      "+---------+\n",
+      "|R: | : :G|\n",
+      "| : | : : |\n",
+      "| : : : : |\n",
+      "| | : | : |\n",
+      "|\u001b[35m\u001b[42mY\u001b[0m\u001b[0m| : |B: |\n",
+      "+---------+\n",
+      "  (South)\n",
+      "Score: 4\n",
+      "********************************************************************************\n",
+      "Episode 7:\n",
+      "+---------+\n",
+      "|\u001b[34;1m\u001b[43mR\u001b[0m\u001b[0m: | : :\u001b[35mG\u001b[0m|\n",
+      "| : | : : |\n",
+      "| : : : : |\n",
+      "| | : | : |\n",
+      "|Y| : |B: |\n",
+      "+---------+\n",
+      "\n",
+      "+---------+\n",
+      "|\u001b[42mR\u001b[0m: | : :\u001b[35mG\u001b[0m|\n",
+      "| : | : : |\n",
+      "| : : : : |\n",
+      "| | : | : |\n",
+      "|Y| : |B: |\n",
+      "+---------+\n",
+      "  (Pickup)\n",
+      "+---------+\n",
+      "|R: | : :\u001b[35mG\u001b[0m|\n",
+      "|\u001b[42m_\u001b[0m: | : : |\n",
+      "| : : : : |\n",
+      "| | : | : |\n",
+      "|Y| : |B: |\n",
+      "+---------+\n",
+      "  (South)\n",
+      "+---------+\n",
+      "|R: | : :\u001b[35mG\u001b[0m|\n",
+      "| : | : : |\n",
+      "|\u001b[42m_\u001b[0m: : : : |\n",
+      "| | : | : |\n",
+      "|Y| : |B: |\n",
+      "+---------+\n",
+      "  (South)\n",
+      "+---------+\n",
+      "|R: | : :\u001b[35mG\u001b[0m|\n",
+      "| : | : : |\n",
+      "| :\u001b[42m_\u001b[0m: : : |\n",
+      "| | : | : |\n",
+      "|Y| : |B: |\n",
+      "+---------+\n",
+      "  (East)\n",
+      "+---------+\n",
+      "|R: | : :\u001b[35mG\u001b[0m|\n",
+      "| : | : : |\n",
+      "| : :\u001b[42m_\u001b[0m: : |\n",
+      "| | : | : |\n",
+      "|Y| : |B: |\n",
+      "+---------+\n",
+      "  (East)\n",
+      "+---------+\n",
+      "|R: | : :\u001b[35mG\u001b[0m|\n",
+      "| : | : : |\n",
+      "| : : :\u001b[42m_\u001b[0m: |\n",
+      "| | : | : |\n",
+      "|Y| : |B: |\n",
+      "+---------+\n",
+      "  (East)\n",
+      "+---------+\n",
+      "|R: | : :\u001b[35mG\u001b[0m|\n",
+      "| : | : : |\n",
+      "| : : : :\u001b[42m_\u001b[0m|\n",
+      "| | : | : |\n",
+      "|Y| : |B: |\n",
+      "+---------+\n",
+      "  (East)\n",
+      "+---------+\n",
+      "|R: | : :\u001b[35mG\u001b[0m|\n",
+      "| : | : :\u001b[42m_\u001b[0m|\n",
+      "| : : : : |\n",
+      "| | : | : |\n",
+      "|Y| : |B: |\n",
+      "+---------+\n",
+      "  (North)\n",
+      "+---------+\n",
+      "|R: | : :\u001b[35m\u001b[42mG\u001b[0m\u001b[0m|\n",
+      "| : | : : |\n",
+      "| : : : : |\n",
+      "| | : | : |\n",
+      "|Y| : |B: |\n",
+      "+---------+\n",
+      "  (North)\n",
+      "Score: 11\n",
+      "********************************************************************************\n",
+      "Episode 8:\n",
+      "+---------+\n",
+      "|R: | : :\u001b[35mG\u001b[0m|\n",
+      "| : | : : |\n",
+      "| :\u001b[43m \u001b[0m: : : |\n",
+      "| | : | : |\n",
+      "|Y| : |\u001b[34;1mB\u001b[0m: |\n",
+      "+---------+\n",
+      "\n",
+      "+---------+\n",
+      "|R: | : :\u001b[35mG\u001b[0m|\n",
+      "| : | : : |\n",
+      "| : :\u001b[43m \u001b[0m: : |\n",
+      "| | : | : |\n",
+      "|Y| : |\u001b[34;1mB\u001b[0m: |\n",
+      "+---------+\n",
+      "  (East)\n",
+      "+---------+\n",
+      "|R: | : :\u001b[35mG\u001b[0m|\n",
+      "| : | : : |\n",
+      "| : : :\u001b[43m \u001b[0m: |\n",
+      "| | : | : |\n",
+      "|Y| : |\u001b[34;1mB\u001b[0m: |\n",
+      "+---------+\n",
+      "  (East)\n",
+      "+---------+\n",
+      "|R: | : :\u001b[35mG\u001b[0m|\n",
+      "| : | : : |\n",
+      "| : : : : |\n",
+      "| | : |\u001b[43m \u001b[0m: |\n",
+      "|Y| : |\u001b[34;1mB\u001b[0m: |\n",
+      "+---------+\n",
+      "  (South)\n",
+      "+---------+\n",
+      "|R: | : :\u001b[35mG\u001b[0m|\n",
+      "| : | : : |\n",
+      "| : : : : |\n",
+      "| | : | : |\n",
+      "|Y| : |\u001b[34;1m\u001b[43mB\u001b[0m\u001b[0m: |\n",
+      "+---------+\n",
+      "  (South)\n",
+      "+---------+\n",
+      "|R: | : :\u001b[35mG\u001b[0m|\n",
+      "| : | : : |\n",
+      "| : : : : |\n",
+      "| | : | : |\n",
+      "|Y| : |\u001b[42mB\u001b[0m: |\n",
+      "+---------+\n",
+      "  (Pickup)\n",
+      "+---------+\n",
+      "|R: | : :\u001b[35mG\u001b[0m|\n",
+      "| : | : : |\n",
+      "| : : : : |\n",
+      "| | : | : |\n",
+      "|Y| : |B:\u001b[42m_\u001b[0m|\n",
+      "+---------+\n",
+      "  (East)\n",
+      "+---------+\n",
+      "|R: | : :\u001b[35mG\u001b[0m|\n",
+      "| : | : : |\n",
+      "| : : : : |\n",
+      "| | : | :\u001b[42m_\u001b[0m|\n",
+      "|Y| : |B: |\n",
+      "+---------+\n",
+      "  (North)\n",
+      "+---------+\n",
+      "|R: | : :\u001b[35mG\u001b[0m|\n",
+      "| : | : : |\n",
+      "| : : : :\u001b[42m_\u001b[0m|\n",
+      "| | : | : |\n",
+      "|Y| : |B: |\n",
+      "+---------+\n",
+      "  (North)\n",
+      "+---------+\n",
+      "|R: | : :\u001b[35mG\u001b[0m|\n",
+      "| : | : :\u001b[42m_\u001b[0m|\n",
+      "| : : : : |\n",
+      "| | : | : |\n",
+      "|Y| : |B: |\n",
+      "+---------+\n",
+      "  (North)\n",
+      "+---------+\n",
+      "|R: | : :\u001b[35m\u001b[42mG\u001b[0m\u001b[0m|\n",
+      "| : | : : |\n",
+      "| : : : : |\n",
+      "| | : | : |\n",
+      "|Y| : |B: |\n",
+      "+---------+\n",
+      "  (North)\n",
+      "Score: 10\n",
+      "********************************************************************************\n",
+      "Episode 9:\n",
+      "+---------+\n",
+      "|\u001b[35mR\u001b[0m: |\u001b[43m \u001b[0m: :G|\n",
+      "| : | : : |\n",
+      "| : : : : |\n",
+      "| | : | : |\n",
+      "|Y| : |\u001b[34;1mB\u001b[0m: |\n",
+      "+---------+\n",
+      "\n",
+      "+---------+\n",
+      "|\u001b[35mR\u001b[0m: | :\u001b[43m \u001b[0m:G|\n",
+      "| : | : : |\n",
+      "| : : : : |\n",
+      "| | : | : |\n",
+      "|Y| : |\u001b[34;1mB\u001b[0m: |\n",
+      "+---------+\n",
+      "  (East)\n",
+      "+---------+\n",
+      "|\u001b[35mR\u001b[0m: | : :G|\n",
+      "| : | :\u001b[43m \u001b[0m: |\n",
+      "| : : : : |\n",
+      "| | : | : |\n",
+      "|Y| : |\u001b[34;1mB\u001b[0m: |\n",
+      "+---------+\n",
+      "  (South)\n",
+      "+---------+\n",
+      "|\u001b[35mR\u001b[0m: | : :G|\n",
+      "| : | : : |\n",
+      "| : : :\u001b[43m \u001b[0m: |\n",
+      "| | : | : |\n",
+      "|Y| : |\u001b[34;1mB\u001b[0m: |\n",
+      "+---------+\n",
+      "  (South)\n",
+      "+---------+\n",
+      "|\u001b[35mR\u001b[0m: | : :G|\n",
+      "| : | : : |\n",
+      "| : : : : |\n",
+      "| | : |\u001b[43m \u001b[0m: |\n",
+      "|Y| : |\u001b[34;1mB\u001b[0m: |\n",
+      "+---------+\n",
+      "  (South)\n",
+      "+---------+\n",
+      "|\u001b[35mR\u001b[0m: | : :G|\n",
+      "| : | : : |\n",
+      "| : : : : |\n",
+      "| | : | : |\n",
+      "|Y| : |\u001b[34;1m\u001b[43mB\u001b[0m\u001b[0m: |\n",
+      "+---------+\n",
+      "  (South)\n",
+      "+---------+\n",
+      "|\u001b[35mR\u001b[0m: | : :G|\n",
+      "| : | : : |\n",
+      "| : : : : |\n",
+      "| | : | : |\n",
+      "|Y| : |\u001b[42mB\u001b[0m: |\n",
+      "+---------+\n",
+      "  (Pickup)\n",
+      "+---------+\n",
+      "|\u001b[35mR\u001b[0m: | : :G|\n",
+      "| : | : : |\n",
+      "| : : : : |\n",
+      "| | : |\u001b[42m_\u001b[0m: |\n",
+      "|Y| : |B: |\n",
+      "+---------+\n",
+      "  (North)\n",
+      "+---------+\n",
+      "|\u001b[35mR\u001b[0m: | : :G|\n",
+      "| : | : : |\n",
+      "| : : :\u001b[42m_\u001b[0m: |\n",
+      "| | : | : |\n",
+      "|Y| : |B: |\n",
+      "+---------+\n",
+      "  (North)\n",
+      "+---------+\n",
+      "|\u001b[35mR\u001b[0m: | : :G|\n",
+      "| : | : : |\n",
+      "| : :\u001b[42m_\u001b[0m: : |\n",
+      "| | : | : |\n",
+      "|Y| : |B: |\n",
+      "+---------+\n",
+      "  (West)\n",
+      "+---------+\n",
+      "|\u001b[35mR\u001b[0m: | : :G|\n",
+      "| : | : : |\n",
+      "| :\u001b[42m_\u001b[0m: : : |\n",
+      "| | : | : |\n",
+      "|Y| : |B: |\n",
+      "+---------+\n",
+      "  (West)\n",
+      "+---------+\n",
+      "|\u001b[35mR\u001b[0m: | : :G|\n",
+      "| : | : : |\n",
+      "|\u001b[42m_\u001b[0m: : : : |\n",
+      "| | : | : |\n",
+      "|Y| : |B: |\n",
+      "+---------+\n",
+      "  (West)\n",
+      "+---------+\n",
+      "|\u001b[35mR\u001b[0m: | : :G|\n",
+      "|\u001b[42m_\u001b[0m: | : : |\n",
+      "| : : : : |\n",
+      "| | : | : |\n",
+      "|Y| : |B: |\n",
+      "+---------+\n",
+      "  (North)\n",
+      "+---------+\n",
+      "|\u001b[35m\u001b[42mR\u001b[0m\u001b[0m: | : :G|\n",
+      "| : | : : |\n",
+      "| : : : : |\n",
+      "| | : | : |\n",
+      "|Y| : |B: |\n",
+      "+---------+\n",
+      "  (North)\n",
+      "Score: 7\n",
+      "********************************************************************************\n",
+      "Episode 10:\n",
+      "+---------+\n",
+      "|\u001b[34;1mR\u001b[0m: | : :\u001b[35m\u001b[43mG\u001b[0m\u001b[0m|\n",
+      "| : | : : |\n",
+      "| : : : : |\n",
+      "| | : | : |\n",
+      "|Y| : |B: |\n",
+      "+---------+\n",
+      "\n",
+      "+---------+\n",
+      "|\u001b[34;1mR\u001b[0m: | :\u001b[43m \u001b[0m:\u001b[35mG\u001b[0m|\n",
+      "| : | : : |\n",
+      "| : : : : |\n",
+      "| | : | : |\n",
+      "|Y| : |B: |\n",
+      "+---------+\n",
+      "  (West)\n",
+      "+---------+\n",
+      "|\u001b[34;1mR\u001b[0m: | : :\u001b[35mG\u001b[0m|\n",
+      "| : | :\u001b[43m \u001b[0m: |\n",
+      "| : : : : |\n",
+      "| | : | : |\n",
+      "|Y| : |B: |\n",
+      "+---------+\n",
+      "  (South)\n",
+      "+---------+\n",
+      "|\u001b[34;1mR\u001b[0m: | : :\u001b[35mG\u001b[0m|\n",
+      "| : | : : |\n",
+      "| : : :\u001b[43m \u001b[0m: |\n",
+      "| | : | : |\n",
+      "|Y| : |B: |\n",
+      "+---------+\n",
+      "  (South)\n",
+      "+---------+\n",
+      "|\u001b[34;1mR\u001b[0m: | : :\u001b[35mG\u001b[0m|\n",
+      "| : | : : |\n",
+      "| : :\u001b[43m \u001b[0m: : |\n",
+      "| | : | : |\n",
+      "|Y| : |B: |\n",
+      "+---------+\n",
+      "  (West)\n",
+      "+---------+\n",
+      "|\u001b[34;1mR\u001b[0m: | : :\u001b[35mG\u001b[0m|\n",
+      "| : | : : |\n",
+      "| :\u001b[43m \u001b[0m: : : |\n",
+      "| | : | : |\n",
+      "|Y| : |B: |\n",
+      "+---------+\n",
+      "  (West)\n",
+      "+---------+\n",
+      "|\u001b[34;1mR\u001b[0m: | : :\u001b[35mG\u001b[0m|\n",
+      "| :\u001b[43m \u001b[0m| : : |\n",
+      "| : : : : |\n",
+      "| | : | : |\n",
+      "|Y| : |B: |\n",
+      "+---------+\n",
+      "  (North)\n",
+      "+---------+\n",
+      "|\u001b[34;1mR\u001b[0m: | : :\u001b[35mG\u001b[0m|\n",
+      "|\u001b[43m \u001b[0m: | : : |\n",
+      "| : : : : |\n",
+      "| | : | : |\n",
+      "|Y| : |B: |\n",
+      "+---------+\n",
+      "  (West)\n",
+      "+---------+\n",
+      "|\u001b[34;1m\u001b[43mR\u001b[0m\u001b[0m: | : :\u001b[35mG\u001b[0m|\n",
+      "| : | : : |\n",
+      "| : : : : |\n",
+      "| | : | : |\n",
+      "|Y| : |B: |\n",
+      "+---------+\n",
+      "  (North)\n",
+      "+---------+\n",
+      "|\u001b[42mR\u001b[0m: | : :\u001b[35mG\u001b[0m|\n",
+      "| : | : : |\n",
+      "| : : : : |\n",
+      "| | : | : |\n",
+      "|Y| : |B: |\n",
+      "+---------+\n",
+      "  (Pickup)\n",
+      "+---------+\n",
+      "|R: | : :\u001b[35mG\u001b[0m|\n",
+      "|\u001b[42m_\u001b[0m: | : : |\n",
+      "| : : : : |\n",
+      "| | : | : |\n",
+      "|Y| : |B: |\n",
+      "+---------+\n",
+      "  (South)\n",
+      "+---------+\n",
+      "|R: | : :\u001b[35mG\u001b[0m|\n",
+      "| : | : : |\n",
+      "|\u001b[42m_\u001b[0m: : : : |\n",
+      "| | : | : |\n",
+      "|Y| : |B: |\n",
+      "+---------+\n",
+      "  (South)\n",
+      "+---------+\n",
+      "|R: | : :\u001b[35mG\u001b[0m|\n",
+      "| : | : : |\n",
+      "| :\u001b[42m_\u001b[0m: : : |\n",
+      "| | : | : |\n",
+      "|Y| : |B: |\n",
+      "+---------+\n",
+      "  (East)\n",
+      "+---------+\n",
+      "|R: | : :\u001b[35mG\u001b[0m|\n",
+      "| : | : : |\n",
+      "| : :\u001b[42m_\u001b[0m: : |\n",
+      "| | : | : |\n",
+      "|Y| : |B: |\n",
+      "+---------+\n",
+      "  (East)\n",
+      "+---------+\n",
+      "|R: | : :\u001b[35mG\u001b[0m|\n",
+      "| : | : : |\n",
+      "| : : :\u001b[42m_\u001b[0m: |\n",
+      "| | : | : |\n",
+      "|Y| : |B: |\n",
+      "+---------+\n",
+      "  (East)\n",
+      "+---------+\n",
+      "|R: | : :\u001b[35mG\u001b[0m|\n",
+      "| : | : : |\n",
+      "| : : : :\u001b[42m_\u001b[0m|\n",
+      "| | : | : |\n",
+      "|Y| : |B: |\n",
+      "+---------+\n",
+      "  (East)\n",
+      "+---------+\n",
+      "|R: | : :\u001b[35mG\u001b[0m|\n",
+      "| : | : :\u001b[42m_\u001b[0m|\n",
+      "| : : : : |\n",
+      "| | : | : |\n",
+      "|Y| : |B: |\n",
+      "+---------+\n",
+      "  (North)\n",
+      "+---------+\n",
+      "|R: | : :\u001b[35m\u001b[42mG\u001b[0m\u001b[0m|\n",
+      "| : | : : |\n",
+      "| : : : : |\n",
+      "| | : | : |\n",
+      "|Y| : |B: |\n",
+      "+---------+\n",
+      "  (North)\n",
+      "Score: 3\n",
+      "Average Rewards: 7.6\n"
+     ]
+    }
+   ],
+   "source": [
+    "# keep track of all rewards\n",
+    "rewards = []\n",
+    "\n",
+    "for episode in range(total_test_episodes):\n",
+    "    \n",
+    "    state = env.reset()\n",
+    "    done = False\n",
+    "    total_rewards = 0\n",
+    "    print(f\"{'*'*80}\")\n",
+    "    print(f\"Episode {episode + 1}:\")\n",
+    "    \n",
+    "    for step in range(max_steps):\n",
+    "        \n",
+    "        # render every frame of the agent\n",
+    "        env.render()\n",
+    "        \n",
+    "        # take an action that has max expected future reward given in that state\n",
+    "        action = np.argmax(qtable[state,:])\n",
+    "        \n",
+    "        new_state, reward, done, info = env.step(action)\n",
+    "        \n",
+    "        total_rewards += reward\n",
+    "        \n",
+    "        if done:\n",
+    "            # keep track of rewards received at every episode\n",
+    "            rewards.append(total_rewards)\n",
+    "            print(f\"Score: {total_rewards}\")\n",
+    "            break\n",
+    "        \n",
+    "        state = new_state\n",
+    "\n",
+    "env.close()\n",
+    "print(f\"Average Rewards: {sum(rewards)/total_test_episodes}\")"
+   ]
+  }
+ ],
+ "metadata": {
+  "kernelspec": {
+   "display_name": "Python 3",
+   "language": "python",
+   "name": "python3"
+  },
+  "language_info": {
+   "codemirror_mode": {
+    "name": "ipython",
+    "version": 3
+   },
+   "file_extension": ".py",
+   "mimetype": "text/x-python",
+   "name": "python",
+   "nbconvert_exporter": "python",
+   "pygments_lexer": "ipython3",
+   "version": "3.7.6"
+  },
+  "papermill": {
+   "duration": 25.17346,
+   "end_time": "2020-08-25T14:57:52.552402",
+   "environment_variables": {},
+   "exception": null,
+   "input_path": "__notebook__.ipynb",
+   "output_path": "__notebook__.ipynb",
+   "parameters": {},
+   "start_time": "2020-08-25T14:57:27.378942",
+   "version": "2.1.0"
+  }
+ },
+ "nbformat": 4,
+ "nbformat_minor": 4
+}