Quadcopter_Project.ipynb

{
 "cells": [
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "# Project: Train a Quadcopter How to Fly\n",
    "\n",
    "Design an agent to fly a quadcopter, and then train it using a reinforcement learning algorithm of your choice! \n",
    "\n",
    "Try to apply the techniques you have learnt, but also feel free to come up with innovative ideas and test them."
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "## Instructions\n",
    "\n",
    "Take a look at the files in the directory to better understand the structure of the project. \n",
    "\n",
    "- `task.py`: Define your task (environment) in this file.\n",
    "- `agents/`: Folder containing reinforcement learning agents.\n",
    "    - `policy_search.py`: A sample agent has been provided here.\n",
    "    - `agent.py`: Develop your agent here.\n",
    "- `physics_sim.py`: This file contains the simulator for the quadcopter.  **DO NOT MODIFY THIS FILE**.\n",
    "\n",
    "For this project, you will define your own task in `task.py`.  Although we have provided a example task to get you started, you are encouraged to change it.  Later in this notebook, you will learn more about how to amend this file.\n",
    "\n",
    "You will also design a reinforcement learning agent in `agent.py` to complete your chosen task.  \n",
    "\n",
    "You are welcome to create any additional files to help you to organize your code.  For instance, you may find it useful to define a `model.py` file defining any needed neural network architectures.\n",
    "\n",
    "## Controlling the Quadcopter\n",
    "\n",
    "We provide a sample agent in the code cell below to show you how to use the sim to control the quadcopter.  This agent is even simpler than the sample agent that you'll examine (in `agents/policy_search.py`) later in this notebook!\n",
    "\n",
    "The agent controls the quadcopter by setting the revolutions per second on each of its four rotors.  The provided agent in the `Basic_Agent` class below always selects a random action for each of the four rotors.  These four speeds are returned by the `act` method as a list of four floating-point numbers.  \n",
    "\n",
    "For this project, the agent that you will implement in `agents/agent.py` will have a far more intelligent method for selecting actions!"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 1,
   "metadata": {},
   "outputs": [],
   "source": [
    "import random\n",
    "\n",
    "class Basic_Agent():\n",
    "    def __init__(self, task):\n",
    "        self.task = task\n",
    "    \n",
    "    def act(self):\n",
    "        new_thrust = random.gauss(450., 25.)\n",
    "        return [new_thrust + random.gauss(0., 1.) for x in range(4)]"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "Run the code cell below to have the agent select actions to control the quadcopter.  \n",
    "\n",
    "Feel free to change the provided values of `runtime`, `init_pose`, `init_velocities`, and `init_angle_velocities` below to change the starting conditions of the quadcopter.\n",
    "\n",
    "The `labels` list below annotates statistics that are saved while running the simulation.  All of this information is saved in a text file `data.txt` and stored in the dictionary `results`.  "
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 2,
   "metadata": {},
   "outputs": [],
   "source": [
    "%load_ext autoreload\n",
    "%autoreload 2\n",
    "\n",
    "import csv\n",
    "import numpy as np\n",
    "from task import Task\n",
    "\n",
    "# Modify the values below to give the quadcopter a different starting position.\n",
    "runtime = 5.                                     # time limit of the episode\n",
    "init_pose = np.array([0., 0., 10., 0., 0., 0.])  # initial pose\n",
    "init_velocities = np.array([0., 0., 0.])         # initial velocities\n",
    "init_angle_velocities = np.array([0., 0., 0.])   # initial angle velocities\n",
    "file_output = 'data.txt'                         # file name for saved results\n",
    "\n",
    "# Setup\n",
    "task = Task(init_pose, init_velocities, init_angle_velocities, runtime)\n",
    "agent = Basic_Agent(task)\n",
    "done = False\n",
    "labels = ['time', 'x', 'y', 'z', 'phi', 'theta', 'psi', 'x_velocity',\n",
    "          'y_velocity', 'z_velocity', 'phi_velocity', 'theta_velocity',\n",
    "          'psi_velocity', 'rotor_speed1', 'rotor_speed2', 'rotor_speed3', 'rotor_speed4']\n",
    "results = {x : [] for x in labels}\n",
    "\n",
    "# Run the simulation, and save the results.\n",
    "with open(file_output, 'w') as csvfile:\n",
    "    writer = csv.writer(csvfile)\n",
    "    writer.writerow(labels)\n",
    "    while True:\n",
    "        rotor_speeds = agent.act()\n",
    "        _, _, done = task.step(rotor_speeds)\n",
    "        to_write = [task.sim.time] + list(task.sim.pose) + list(task.sim.v) + list(task.sim.angular_v) + list(rotor_speeds)\n",
    "        for ii in range(len(labels)):\n",
    "            results[labels[ii]].append(to_write[ii])\n",
    "        writer.writerow(to_write)\n",
    "        if done:\n",
    "            break"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "Run the code cell below to visualize how the position of the quadcopter evolved during the simulation."
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 5,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "image/png": "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\n",
      "text/plain": [
       "<matplotlib.figure.Figure at 0x7f94f4775f28>"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    }
   ],
   "source": [
    "import matplotlib.pyplot as plt\n",
    "%matplotlib inline\n",
    "\n",
    "plt.plot(results['time'], results['x'], label='x')\n",
    "plt.plot(results['time'], results['y'], label='y')\n",
    "plt.plot(results['time'], results['z'], label='z')\n",
    "plt.legend()\n",
    "_ = plt.ylim()"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "The next code cell visualizes the velocity of the quadcopter."
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 6,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "image/png": "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\n",
      "text/plain": [
       "<matplotlib.figure.Figure at 0x7f94f03dfeb8>"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    }
   ],
   "source": [
    "plt.plot(results['time'], results['x_velocity'], label='x_hat')\n",
    "plt.plot(results['time'], results['y_velocity'], label='y_hat')\n",
    "plt.plot(results['time'], results['z_velocity'], label='z_hat')\n",
    "plt.legend()\n",
    "_ = plt.ylim()"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "Next, you can plot the Euler angles (the rotation of the quadcopter over the $x$-, $y$-, and $z$-axes),"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 7,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "image/png": "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\n",
      "text/plain": [
       "<matplotlib.figure.Figure at 0x7f94f03dfe80>"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    }
   ],
   "source": [
    "plt.plot(results['time'], results['phi'], label='phi')\n",
    "plt.plot(results['time'], results['theta'], label='theta')\n",
    "plt.plot(results['time'], results['psi'], label='psi')\n",
    "plt.legend()\n",
    "_ = plt.ylim()"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "before plotting the velocities (in radians per second) corresponding to each of the Euler angles."
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 8,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "image/png": "iVBORw0KGgoAAAANSUhEUgAAAX8AAAD8CAYAAACfF6SlAAAABHNCSVQICAgIfAhkiAAAAAlwSFlzAAALEgAACxIB0t1+/AAAADl0RVh0U29mdHdhcmUAbWF0cGxvdGxpYiB2ZXJzaW9uIDIuMS4wLCBodHRwOi8vbWF0cGxvdGxpYi5vcmcvpW3flQAAIABJREFUeJzs3XdYVUf6wPHvXLoUlWIFpViwAQpijy3F3pUYjRrjGjWmborZbLLZbLLpv81GXZOYWGIlGo0lGhM1lthBUFFUUBERFATpnXt+f4wN6XDp83keH+TcOWfmgr73nCnvCE3TUBRFUeoXXXU3QFEURal6KvgriqLUQyr4K4qi1EMq+CuKotRDKvgriqLUQyr4K4qi1EMq+CuKotRDKvgriqLUQyr4K4qi1EPG1d2Aotjb22vOzs7V3QxFUZRaJTAw8JamaQ4llauxwd/Z2ZmAgIDqboaiKEqtIoS4WppyqttHURSlHlLBX1EUpR5SwV9RFKUeqrF9/oXJyckhKiqKzMzM6m6KUgxzc3McHR0xMTGp7qYoilKEWhX8o6KisLa2xtnZGSFEdTdHKYSmacTHxxMVFYWLi0t1N0dRlCLUqm6fzMxM7OzsVOCvwYQQ2NnZqaczRanhalXwB1TgrwXU70hRar5a1e2jKIpSUXq9xs2UTCJupRMRn4Ze03jKt1Wl3rQEX0skOjGDxzs2xdioZtxzq+CvKEq9EXU7Hb9vjnI9MSPfcY+Wjeji2LBS6tQ0jZfXBxERn46LvSXzB7ZhtFcLjHSCiPh0TlxJIDopg1GeLXB1sKqUNhRGBX8Dubsi2d7ePt/xrVu3cu7cORYsWGCQet577z2srKx47bXXynRedHQ0L774Ihs3biQ4OJjo6GiGDRtmkDYpSm2Qnatn/togkjNy+OeoTrg6WGJjbsLoxYc4cvlWpQX/kOvJRMSn4+fjxJnrSfx1wyn+7/eLZOfpiUvJulfuy91hDHZvwsy+LvR2q/yxTRX8K9moUaMYNWpUdTeDFi1asHHjRgCCg4MJCAhQwV+pVntCb/LahlPseuURmlibV3p9H+0MJfhaIkumdGNol+b3jrs6WHL0cgKzH3GrlHq3nY7GxEjw1jB3GlqY8Pu5m6w6ehVbS1N8XWzp4WKLjYUJa45GsvroVaZ8dwxfZ1v8n+tZqR8AtTb4/3PbWc5FJxv0mh1b2PCPkZ2KLRMREcGQIUPo0aMHQUFBtGvXjh9++AGAhQsXsm3bNnJyctiwYQPu7u6sWLGCgIAAFi1aVOBaSUlJeHp6cvnyZXQ6Henp6bRv357Lly8TGRnJ888/T1xcHA0aNGDp0qW4u7vnOz84OJg5c+aQnp6Om5sby5Yto3HjxoSHhzNnzhzi4uIwMjJiw4YNGBkZMWLECE6ePMm7775LRkYGf/75J2+99RZ///vfOXz4MA4ODuj1etq1a8fRo0cLPMUoiiHtOnuD2+k5bA2OZlY/10qta8eZGJYfiuCZPs75Aj9AT1c7tgZHk5unN3h/vF6vsf1UNI+0daBRA1MAHu/UjMc7NStQ9pXH2jF3gBtbT0WTkZ1X6Xf+NWPkoZa5cOECs2fP5vTp09jY2PC///0PAHt7e06ePMncuXP5/PPPS7xOw4YN8fT0ZP/+/QBs27aNJ554AhMTE2bPns3ChQsJDAzk888/Z968eQXOnzZtGp988gmnT5+mS5cu/POf/wRgypQpPP/885w6dYrDhw/TvPn9f+ympqa8//77+Pn5ERwcjJ+fH1OnTmXNmjUA7N69G09PTxX4lUp37EoCAJtOXq/UeiJupfHGxtN4OTXiraEdCrzey9WO1KxcQgx8MwkQGHmb6KRMRnq2KFV5cxMjJvk4Mb23s8Hb8rBae+df0h16ZXJycqJPnz4ATJ06la+++gqAcePGAeDt7c2mTZtKdS0/Pz/8/f0ZOHAg69evZ968eaSmpnL48GEmTpx4r1xWVla+85KSkkhMTKR///4ATJ8+nYkTJ5KSksL169cZO3YsIFfblmTmzJmMHj2al19+mWXLlvHMM8+Uqu2KUl43kjK5Gp+Oq4Ml52KSuXAjhfbNrA1eT06enhfWBWFsJFg8pRumxgXvd3u42gJw9HI8Xk6NDFr/tlPRmBnreLRjU4Ne1xDUnX85PPw4dvd7MzMzAIyMjMjNzS3VtUaNGsXOnTtJSEggMDCQQYMGodfradSoEcHBwff+hIaGlup6mqaV4Z1ITk5ONG3alL1793Ls2DGGDh1a5msoSlkcuxIPwLsjOmKkE2wKiqqUehbuDefM9SQ+HteFlo0sCi3TxNqcNk2sOHIp3qB15+bp2XEmhsEdmmBlVvPus1XwL4fIyEiOHDkCwLp16+jbt2+5r2VlZYWvry8vvfQSI0aMwMjICBsbG1xcXNiwYQMgA/qpU6fyndewYUMaN27MwYMHAVi1ahX9+/fHxsYGR0dHfv75Z0A+MaSnp+c719rampSUlHzHZs2axdSpU5k0aRJGRkblfj+KUhrHriRgbWZMv7YO9G/nwJagaPL0Zb9xKc6pa4ks/iOcsV1bMqRz82LL9nS1JSAigZw8vcHqP3o5gVup2YwqZZdPVTNI8BdCDBFCXBBChAshCsxpFEK8KoQ4J4Q4LYTYI4RobYh6q0uHDh1YuXIlHh4eJCQkMHfu3Apdz8/Pj9WrV+Pn53fv2Jo1a/j+++/x9PSkU6dObNmypcB5K1eu5PXXX8fDw4Pg4GDeffddQH4QfPXVV3h4eNC7d29u3LiR77yBAwdy7tw5vLy88Pf3B+QTSGpqquryUarEscvx+Dg3xkgnGNu1JTeSMzl62XB33pk5ebz6YzAOVma8N6rkLuJervakZedx5nqSwdqw9dR1rMyMGdC+icGuaVCaplXoD2AEXAJcAVPgFNDxoTIDgQZ3/j4X8C/put7e3trDzp07V+BYVbty5YrWqVOn6m6GwZ04cULr27evwa5XE35XSs0Ul5KptX5zu7ZkX7imaZqWkZ2rdX73V+1V/+BCy+v1em3bqevaK+uDtMS07FLV8c+tZ7XWb27XDlyMLVObFv8RVro3UYLMnFytyz9+1V5ZH2SQ65UFEKCVInYboiPKFwjXNO0ygBBiPTAaOPfAB8wfD5Q/Ckw1QL2KgXz88ccsWbLk3owfRalMx+/M8vF1kQOt5iZGDO3SjF9Ox/DBmM5YmN7vdoxOzODdLSHsDo0F4FZaNstndMdIl3/cLSs3j3PRyZy6lkjQtUS2BEczrVdr+rUtcStbAOytzGjXVPb7zxvQpkLv7/yNZJYeuEJyZm6pZ/lUB0ME/5bAtQe+jwJ6FFP+WWCnAeqtFs7OzoSEhJT5vA8//PBeH/5dEydO5O233zZU08ptwYIFBluBrCglOXY5ngamRnRpeX9F7diujvwYEMX209H4utgSdTuD01FJLNobhl6Dvw/vgLmJEX//OYRPfj3P34bdn7L5a8gN3vzpNEkZOQA0sTZjXNeWLBjqXqDu4vR0tWNDQBQ5eXpMCpnvH5OUwaaT1xnl2QIn2wb5XsvMyePXkBusPnqVgKu3MTXWMdm3Ff3a1twp04YI/oWtRCh05EYIMRXwAfoX8fpsYDZAq1atDNC0muPtt9+uEYFeUarbsSsJeLdunC/A9nCxpWUjC17feDpf2X5t7fn32C73gu3Fmyl8e+Ay7s2sGeHRgo93nmfZoSt4OjZkTn83vFo1opmNebkWSPVyteOHI1c5HZWId2vbfK+lZOYwY9kJLtxM4YvfLvBEp2bM6ueKjbkx645fY1NQFInpOTjbNeDtYR0Y7+2IraVpOX46VccQwT8KcHrge0cg+uFCQohHgbeB/pqmZT38OoCmad8C3wL4+PgYduhfUZRql5iezYWbKQx/aJWtTif4bIIHx64k4NjYgpaNLXBq3ADHxhb5Avk7IzoSdjOVBZvOsOzQFUKuJzOjtzNvDXPHzLhis9R6uNoBcORSfL7gn6fXeGl9MOFxqfz3SS/O30hhzdGr7AyREylMjASPd2rG5O6t6O1mh05XO1KaGyL4nwDaCiFcgOvAk8BTDxYQQnQFvgGGaJoWa4A6FUWphY5fSUDT7gfaB/VuY0/vNsV3k5gY6Vg8pRujFv1JxK10Fj/VjeEexU/jLC1bS1Pcm1mz9lgkre0sGdalOUY6wb93hLL3fCwfjOnMaK+WjAbmD2zD5qDrZOXqGePVAjsrM4O0oSpVOPhrmpYrhJgP7ELO/FmmadpZIcT7yFHnrcBngBWw4c6neKSmadWf7UxRlCp1/EoCpsY6PJ3Kn0HT1tKUbfP7kqdp2Bs46L43qhNvbz7DC+uC+M/ui/Rxs2fV0avM6O3M1J73Z6hbmhnn+742MsiyM03TdgA7Hjr27gN/f9QQ9SiKUrsdu5JAV6dGFe6iaVxJ/ek9Xe347ZX+/Bpyg4V7w1h19Cr92znw9+EFcwLVdmqFbxklJibeS+S2b98+RowYUabzV6xYQXR0gSGRSjFjxox7aZzLIiAggBdffBGQ7/Hw4cOGbppSDyVl5HA2OqnQLp+axEgnGO7RnJ0v9eOnub355mnvGrP7liHVvXdUyR4M/uVRlcG/vHx8fO4lq1PBXzGU/Rfj0GvQv13p5t5XNyEE3q0bY25SN9Od1LxsQ6W1cwHcOGPYazbrAkM/LrbIggULuHTpEl5eXpiYmGBpacmECRMICQnB29ub1atXI4QgMDCQV199ldTUVOzt7VmxYgWHDh0iICCAKVOmYGFhwZEjR/jss8/Ytm0bGRkZ9O7dm2+++abQaWqhoaFMnz6d48ePA3JfgVGjRnH69OlC63owjTPAnj17eO2118jNzaV79+4sWbIEMzMzTpw4wUsvvURaWhpmZmbs2bPnXhrpRYsW8fXXX2NkZMTq1atZuHAh06ZN4+LFi5iYmJCcnIyHhwdhYWGYmJgY7veg1El7Qm9iZ2lq8MyZSvmoO/8y+vjjj3FzcyM4OJjPPvuMoKAgvvzyS86dO8fly5c5dOgQOTk5vPDCC2zcuJHAwEBmzpzJ22+/zYQJE/Dx8WHNmjUEBwdjYWHB/PnzOXHiBCEhIWRkZLB9+/ZC6+3QoQPZ2dlcvnwZAH9/fyZNmlRkXQ/KzMxkxowZ+Pv7c+bMGXJzc1myZAnZ2dn4+fnx3//+l1OnTrF7924sLO5nPnR2dmbOnDm88sorBAcH069fPwYMGMAvv/wCwPr16xk/frwK/EqJcvL0/HE+loHuTQqszlWqR+298y/hDr2q+Pr64ujoCICXlxcRERE0atSIkJAQHnvsMQDy8vIK3Inf9ccff/Dpp5+Snp5OQkICnTp1YuTIkYWWnTRpEj/++CMLFizA398ff39/Lly4UGJdFy5cwMXFhXbt2gEy9//ixYsZPHgwzZs3p3v37gDY2NiU+H5nzZrFp59+ypgxY1i+fDlLly4txU9Jqe8CIm6TnJnLox1qaJKzeqj2Bv8a4m4Of7ifx1/TNDp16nQv7XNRMjMzmTdvHgEBATg5OfHee++RmZlZZHk/Pz8mTpzIuHHjEELQtm1bzpw5U2JdWhE5/jVNK/NKyD59+hAREcH+/fvJy8ujc+fOZTpfqZ/2hN7E1EhX6lw7SuVT3T5lVFgu/Ie1b9+euLi4ewE5JyeHs2fPFjj/bqC3t7cnNTW1xJk5bm5uGBkZ8a9//ete+ufi6rrL3d2diIgIwsPDgfu5/93d3YmOjubEiRMApKSkFNiEprD3O23aNCZPnqzSPyultud8LL3c7LCsgZua1Fcq+JeRnZ0dffr0oXPnzrz++uuFljE1NWXjxo28+eabeHp64uXldW/GzIwZM5gzZw5eXl6YmZnxl7/8hS5dujBmzJh73S/FuZv7f9KkSSXWdZe5uTnLly9n4sSJdOnSBZ1Ox5w5czA1NcXf358XXngBT09PHnvssQJPHiNHjmTz5s14eXnd2zhmypQp3L59m8mTJ5f556fUP5fiUrlyK011+dQwoqgugerm4+OjBQQE5DsWGhpKhw51b7FFbbNx40a2bNnCqlWriiyjflfKXd/sv8RHO89zaMGgIrdSVAxHCBGoaZpPSeXUM5hSJi+88AI7d+5kx44dJRdWFGBPaCwdmtuowF/DqOBfAz3//PMcOnQo37GXXnqpRvSxL1y4sLqboNQit9OyCbiawPMDK7ZBimJ4KvjXQIsXL67uJiiKQey7GIteg8EdmlZ3U5SHqAFfRVEqzc4zN3CwNsOjZfmzeCqVQwV/RVEqRcj1JH47d5NJPo61ZoOT+kQFf0VRKsVnuy7Q0MKE2Y+4VXdTlEKo4F+Jvv76a3744QeDXU+laFZqiyOX4tl/MY7nB7rR0ELlfqqJ1IBvJZozZ051NwGQKZp9fOS033379mFlZUXv3r2ruVVKXaVpGp/8ep5mNuZM6+Vc3c1RiqDu/MsoIiICd3d3pk+fjoeHBxMmTCA9PZ0FCxbQsWNHPDw8eO211wB47733+Pzzzwu9TmhoKL6+vvmu6+HhAUBgYCD9+/fH29ubJ554gpiYmALn79mzh65du9KlSxdmzpxJVlYWACdOnKB37954enri6+tLSkrKvU1nIiIi+Prrr/nPf/5zb8Wui4sLOTk5ACQnJ+Ps7Hzve0Upj9/O3ST4WiIvP9q2zubCrwtq7Z3/J8c/4XzCeYNe093WnTd93yyx3IULF/j+++/p06cPM2fOZNGiRWzevJnz588jhCAxMbHEazyYotnV1bVAiuYtW7bg4OCAv78/b7/9NsuWLbt37t0UzXv27KFdu3ZMmzaNJUuWMG/ePPz8/PD396d79+4kJycXmqLZysrq3gfU3RTNY8aMUSmalQrL02t8tusCrg6WTPB2rO7mKMVQd/7l4OTkRJ8+fQCYOnUqBw4cwNzcnFmzZrFp0yYaNGhQquvcTdEMMj+/n59fvhTNXl5efPDBB0RFReU7r7AUzQcOHODChQsFUjQbGxf/+T5r1iyWL18OwPLly2vEQjKldtI0jc9/u0B4bCqvP96+Tm59WJfU2jv/0tyhV5aH0yCbmJhw/Phx9uzZw/r161m0aBF79+4t8ToqRbNSE+TpNY5ejicmKRMHazMcrMxoamOGnZVZySffoddrvLftLD8cucqT3Z0Y0rlZJbZYMYRaG/yrU2RkJEeOHKFXr16sW7cOLy8vkpKSGDZsGD179qRNm9ItZS8pRXOvXr3Iycnh4sWLdOrU6d55D6ZobtOmTaEpmrt3705KSkq+bh+QKZqTk5PzHbubovmdd96p4E9GqU0ux6Xy08koNp28TkxSwX0kPh7XhSd9W5V4nZw8Pa9tOMWW4GhmP+LKW0Pdy3wTolQ99VxWDh06dGDlypV4eHiQkJDArFmzGDFiBB4eHvTv35///Oc/pb6WStGsVIc/zscy6Iv9LNl3Cfdm1ix+qhv7XhvAxjm9WDKlG+2bWvPdn1eKfMq8KyM7jzmrAtkSHM3rT7RXgb8WUSmdyygiIoIRI0YQEhJSre0wpNKkaC6rmvC7Uor2in8w+y/GsfOlfjS1MS/w+o8nrvHGT6fxn92THq52hV4jKSOHWStPEHD1Nv8a3ZmpPVtXdrOVUlApnZVSUSma6x9N0/gz/BZ92tgXGvgBRnq24INfzrH6WGShwT82JZNp3x/nUlwqCyd3ZYRHi8putmJgKviXkbOzc5nv+lWKZqUmuXgzlbiULPq1sS+yjIWpEeO9HVl99CpxKR1xsL4/+BsZn87U749xKzWLZTO6q315aykV/KuAStGs1CQHw+IA6NO26OAPMKVHa5YfiuDHgGv38vHfTM5k8tKjpGXnsmZWD7q2alzp7VUqh0EGfIUQQ4QQF4QQ4UKIBYW8/ogQ4qQQIlcIMaEiddXUMQrlPvU7qtn+DL+Fq71liTtrtWliRS9XO9YeiyRPr5GcmcP0ZcdJTM9m9bMq8Nd2FQ7+QggjYDEwFOgITBZCdHyoWCQwA1hbkbrMzc2Jj49XwaUG0zSN+Ph4zM0L70tWqld2rp5jlxPoW8Jd/11Te7bmemIGv5+7ydzVgYTHprJkqjedVX7+Ws8Q3T6+QLimaZcBhBDrgdHAubsFNE2LuPOaviIVOTo6EhUVRVxcXEUuo1Qyc3NzHB3V0v6a6GTkbTJy8uhTTH//gx7r2BR7KzNeWh9EVq6eLyZ68kg71cdfFxgi+LcErj3wfRTQwwDXLcDExAQXF5fKuLSi1AuHwm+hE9DLrfDpmw8zNdYx2deJhXvDef2J9oxX+XrqDEME/8JWdJSrX0YIMRuYDdCqVckrCxVFKZuDYbfwdGqEjXnpk/e9MKgtfdrY08PFthJbplQ1Qwz4RgFOD3zvCESX50Kapn2raZqPpmk+Dg7q0VJRDCkpPYfTUYnFTvEsjKmxjp6udmrlbh1jiOB/AmgrhHARQpgCTwJbDXBdRVEM6MjlePQa9FXz8hUMEPw1TcsF5gO7gFDgR03Tzgoh3hdCjAIQQnQXQkQBE4FvhBBnK1qvoihl82d4HA1MjfByalTdTVFqAIMs8tI0bQew46Fj7z7w9xPI7iBFUarJn2G36Olqh6mxyueoqKyeilIvHAyLIyI+nYHtVZePIqngryh1XGZOHu/8HIKLvSWTujuVfIJSL6jcPopSxy3Zd4mI+HRWP9sDM2O1oboiqTt/RanDLselsmTfJUZ7tSh1SgelflDBX1HqKE3TeGdLCGYmOt4erjbWUfJTwV9R6qitp6I5FB7PG0PcaWKtEu0p+angryh1kKZpfLk7jM4tbXiqFJuwK/WPCv6KUgcdv5LAlVtpzOjtgpFOpWVQClLBX1HqIP8T17A2M2ZYl2bV3RSlhlLBX1HqmOTMHHaExDDSqwUNTNVsbqVwKvgrSh2zNTiazBw9fj5qQZdSNBX8FaWO8T9xDfdm1ng4qq0WlaKp4K8odcjZ6CTOXE/Cr7uTyr+vFEt1CCpKLREem4r/iUha21kytWfrQsv8eOIapkY6xni1rOLWKbWNCv6KUoPp9Ro7Q26w6mgERy8nAGBiJBjo3oSWjSzylc3MyePn4Gie6NyMxpam1dFcpRZR3T6KUoN9tTeM59eeJOp2Bm8Mac/2F/oiECzaG16g7Oag6yRl5KiBXqVU1J2/otRQV+PT+N++Swz3aM5XT3a9t1hrsq8Ta45FMm+AG062DQC4mZzJRztC6e7cmN5udtXZbKWWUHf+ilIDaZrGP7aexUQneHdEx3yrdOcNbINOd//uX9M03tp0huw8PZ9O8ESnVvQqpaCCv6LUQL+fu8m+C3G88lg7mtrkT8rW1MacKT1asfFkFFfj09h08jp7z8fy+hPuuNhbVlOLldpGBX9FqWEysvP457ZztG9qzfTezoWWmdvfDWOd4P1t5/jntrP4tG7MjCLKKkphVPBXlBpm8R/hXE/M4P3RnTAxKvy/aBMbc57u2Zo952PJytXz6QQPlcBNKRMV/BWlBrmemMG3By4ztmtLergWP3D7XH83Wtk24J0RHXF1sKqiFip1hZrtoyg1yJJ94WhovPZE+xLLOlibsf/1AWolr1Iu6s5fKVFaVi7p2bnV3Yw6LyYpgx9PRDHRx6nAAq6iqMCvlJe681cKlZun52DYLX46GcXv527S1MacdbN7ljooKWW3ZN8lNDTmDXCr7qYo9YC681cKOB2VSM+P9vLMihP8GX6LsV1bcjs9G79vjnAtIb26m1cn3UjKZP3xa0zwdsSxcYPqbo5SD6jgrxTwzYHL5Or1fPu0N8f/9igfj/dgzaweJGfk8OS3R4mMVx8Ahvb1/kvoNY15A9pUd1OUekIFfyWf5Mwcdp+7yWjPFjzeqRmmxvKfiIdjI9b+pSdp2bn4fXuEq/Fp1dzS2iM7V8/8tSdZdzwSTdMKvB6bnMm645GM69byXroGRalsBgn+QoghQogLQohwIcSCQl43E0L433n9mBDC2RD11kcpmTno9QUDiKH8GnKDrFw9Y7oWTAncuWVD1s7qSWZOHk8tPUbU7dr9BKDXa4TGJFf6k8yxK/FsPx3DW5vOMH9tEEkZOfdeuxqfxt82h5Cr13h+oLrrV6pOhQd8hRBGwGLgMSAKOCGE2Kpp2rkHij0L3NY0rY0Q4kngE8CvonUXJU+vGWTBi16vodc0jItYaGMISek5/HQyinZNrentZldkXpaLN1P4ak8Yv5yJwb2ZDX99rB2DOzQx+GyPn4Ou09quAV5OjQp9vWMLG1Y924Onlh7lqaXH8H+uJ80b1p5B4OxcPdtPR3PgYhx/ht/iVmo2OgGjPFvw4uC2lTJffk9oLGbGOp4f2Ib/7gnjVFQiLz/ajl1nb7A79CZGQvDS4La0tlOpGZSqIwp7DC3TBYToBbynadoTd75/C0DTtI8eKLPrTpkjQghj4AbgoBVTuY+PjxYQEFDm9sQkZTB2/Zs0d0igUQOTMp9/V2J6DldupWFhaoR7M+sSy99KzULT5Nzr0tA0mYkxKjGD3Dw9AOYmRjS1McfO0hRNgxy9npw8PbdSs0lIy0InBA5WZiRm5JCZk4eVuTGtGjfAxqL87/NB2bl6gq7dpmWjBjg2Lj6gp2blEhqTjKmRjo4tbIpciVod4lKyyNNrNGtoXuC1S7GpxKVmYWKko6GFCQ0tTMjIyeNmciZ6TcPe0gwHGzOszUww1Odq0LVELEzkv6OUzFzCY1PJys3DxEhHExszmtqYY1qDfn5K9XO3dedN3zfLda4QIlDTNJ+SyhliqmdL4NoD30cBPYoqo2larhAiCbADbj1YSAgxG5gN0KpVq3I1xtpc/qcNi02hYwsbLE3L9hZz8vRExKcTn5qFkU6QmJ5HenYeDUyNijxHr2lE3EpDr4GVmTEWxZQFSM7I4Up8GhnZeTS0MMHJ1prMnDxuJmdxNT6tQH+6kU7QoqEFzRtaYGwk0DSIS80i6nY652KScXWwokkpP3SKE58mP8DsrUreCMTKzBj3Zjacv5HMuZhk2je1xtyk+PddFfSaxtX4NHLvdI09+AEQm5xFXGoWjo0Lfrg1b2hOdGImN1MyiUvNwlgnsLEwwdbSFHur8v9sM3LyyMrJo8WddlibG9PFsSFpWblYmxujU/P0lWpiiOBf2L/eh+/oS1MGTdO+Bb4FeedfnsamGWIgAAAgAElEQVRYmRmz2e9Txv7vEFcTNDbP60OLUsxN1zSNDQFRfLgjlIzsPJ4f2IYnfZ3o9+kftGvhxL+GdC7y3A0B19i//zSmxjo0XSOWze5ZZHfMiYgEpn53jOYNzfl0eMcCXTehMckcuRR/J/CY0KiBKW4OVjQs5O4+MyeP51YFcuBkHM9M8GSCt2MpfkJFG/rfg7Q31rFuZJ9Sn3P0cjxzVgdyOlLPv8d1YXQ1bx+4MTCK/ftP0bG5DeeDk3n1aR8e69iUM1FJjF9ymJ5udqzw615k91pKZg6HwuPZfzGWP87HcSY5k1l9XXh7eIdydbF9s/8SRyPPs/SpQWqNhFKjGOJZMwp4cOsgRyC6qDJ3un0aAgkGqLtQzRqas2xGd9Ky8pi54gQpmTnFlr8Ul8rkpUd546fTtGtqxY6X+vLSo21pamPOCI/mbDoZVew11h6PpE0TK94b2YljVxLYdPJ6oeUu3Ejh2RUnaNnYgk3z+vBox6YFAkqH5jbM7OvCBG9HBrk3pVurxoUGfpDdRN887U1vNzve2HiKrafkjz02JZPvDl5myndHWbgnrFSrc8/fSCY0JpmxhQz0Fqenqx07XuxHxxY2vLQ+mNc3nKrW1cD+JyJxtbdk49xedGnZkBfXBXEwLI55awOxtzLlSz+vYvPdW5ubMKRzMz4a58GRtwYxo7cz3/15hY92ni90pk5J9pyPxb2ZtQr8So1jiOB/AmgrhHARQpgCTwJbHyqzFZh+5+8TgL3F9fcbQofmNiyZ2o3w2FTmrTlZ6AwZTdNY/Ec4Q788yLnoZD4a1wX/2b1o0+R+H/+0Xs6kZefxc1DhAf1cdDJBkYlM9m3Fk92d6NaqER/uCCUxPTtfuejEDKYvO465iRE/zPTF1kB7rJqbGLF0mg8+rW15xT+Yyd8epee/9/DBL6Fcv53BF79fpP9n+1hz7Co5d8YWCvNzUDRGOsEIj+ZlbkOLRhas+0tPXhjUho0no3hhbVBF3lK5hcemciLiNpO6O9HA1JjvpnfHzsqUp78/zo2kTBZN6Vamn7sQgn+M7MjTPVvz7YHLfPLrhTJ9ACSmZxN49TaDOzQpz9tRlEpV4eCvaVouMB/YBYQCP2qadlYI8b4QYtSdYt8DdkKIcOBVoMB00MrQr60D/xjZkYNht/j17I0Crx8Mu8Vnuy4wyL0Ju//an8m+rQrcFXo6NqRLy4asOnq10P/4a49fxdRYx/huLdHpBB+M6UJSRg6f/HoBkLN5Dl+6xbRlx0nLymXlTF+Dr+BsYGrMsme6492qMZEJ6cwd4MbuV/uz7/WB/DS3F61tG/D25hBGLvyTtKyCd+V6vcaW4Ov0b+eAXTn7t42NdPz18fbMH9iGvRdiiUnKqOjbKrMfA65hrBOM6yafXhyszVjxTHda2TbgvVGd6NaqcZmvKYTg/dGdmNqzFV/vv8T/9l0qtFxkfDofbD9H6gM/3/0X48jTawxyb1q+N6QolcgguX00TdsB7Hjo2LsP/D0TmGiIusrqqR6tWX4ogoV7wxnaudm9bhZN0/hy90VaNDTnq8ld7y1mepgQgqd7teaNjac5diWBng+k2U3LyuXnoGhGeDSnUQN5R9mxhQ3P3OkqOHAxjuuJMgiaGetY8YwvHZrbVMr7tDIzxv+5gmMN3q1t2TCnF5uDrvPqj6fYEhzNUz3yD6bvuxhLTFImbw/vUOF2jO/myMK94WwNjua5/lWXoyY7V89PgVEM7tCEJtb3B3nbNLHmwBsDK3RtIQTvj+rMjaQsvt5/iVn9XDAzzj+4vWT/JdYdjyQsNpXvp/tgbKRj7/lYbC1Ni5w2qyjVqc7PLzPSCZ4f2IbQmGR2h8beO/5n+C1ORiYyd2Cb+4E/Nxuig+U8zAeM9GhBQwsTVh29mu/4tlPRpGblMuWhYPryY+14tEMTurVuzJtD3Fk505ejbw2mVyVvrF3UgKQQgrFdW9KhuQ0/HIko8ASz4vBVmtqY8USnZhVug7O9JV1bNWJzEd1klWVP6E3i07J5snv5ZomVRKcTTOnZipTMXA5ezDdJjZw8Pb+GxODY2IL9F+N4d+tZcvP07LsQx4D2DmqTFaVGqvPBH2C0Vwta2Tbgqz1haJqGpmn8d3cYzRuaM8nnzgyZnExY9yR82x++Gwxhv9/7ELAwNWKityO7Qm4QGpN8L3iuPR5J+6bWBboTrMxkf/PCyV2ZO8CN/u0caGygPv7yEkLwdM/WnL+RwsnI2/eOX4pL5cDFOKb0aG2wufrjurbk/I0UQmOSDXK90lh/4hrNbMx5pJ1DpdXRt409jRqYsP10/vkMhy/Fczs9h3dGdGTuADfWHovkpfXBJGXkMFh1+Sg1VN0M/jGnIeN+gDM20vH8QDfOXE9i38U4Dl+KJ+DqbeYNcJOP77lZ8OPTcGkP+D4HaXGwZgIsHQRRgQBM7dkanRAM/e9BPP/5GxO/PszpqCSe6tGq1uRUH+3VAmszY1Yduf8Es+rIVUyNdEz2Ndwd83CPFhjrRJGD5IZ2PTGDA2FxTPJxrNS7bBMjHUM6NeP3czfJzMm7d3z7qWiszYzp386B1x9vzwiP5vxyJgZjnaBfO/tKa4+iVETdC/7xl+CbfnDyh3yHx3Z1pGUjC77aE8Z/d4fRzMacSd2dZFfPj9Mh7DcY+V8Y9inMD4SRX0FyNGyZB8jujF9f7sdH47owwrMF2bl62jW1KjQHTk1laWbMeG9Hdpy5wa3ULFKzctkYGMVwj+alXplcGraWpgxo78CW4GjyKjEPEcjB6ve3nUUnBBN9nEo+oYJGeLQgLTuPfRdkF2JWbh67zt7gsU5NMTcxQqcTfD7Rk/7tHBjh0Rwbc8OsvlYUQ6t7m7nYuUHrPnDie+g1H3RyYM7UWMecAW6883MIAO+P7oSZTsCGmXBxJwz/P/CeIa9hbAre0yErGX77OyRFQUNHXB2scHWwYnI1vTVDmNqzFSsOR/BjwDUsTY1Jzcplem9ng9czpmtLdofGcvRyPH3ayLvfCzdS2B16k+m9nbEyM8w/vSX7L7Hr7E3+PrxDlWTE7Olqi52lKdtOxTCkc3MOXrxFcmYuIz1a3CtjbmLEypm+5VoXoChVpe7d+QN0nwWJVyF8d77Dk3wcaWZjTlMbMyb5OMGV/RC6DR59D7o/W/A6boPk10t/VHqTq0qbJtb0crVjzdFIVh6JwNOpUaXMRnm0Q1OszYzZHHQdTdNYffQqoxb9yWe7LjBq4Z8GGQ84cDGOz3+7wCjPFjzb18UArS6ZsZGOoV2asef8TdKyctl+OpqGFib3PuAeVFu6A5X6qW4G/w4jwaoZHF+a77CZsRErZnZnxTO+Mg9N4HKwsIUecwu/TpOO8jqX9lZBo6vO071acz0xg8txaczo3bpS6jA3MWJol2bsPBPD3NUn+fvPIfRwtePrqd6kZuUyZvEh1heR3740riWk88K6INo3tebj8V2qNNCO9GhBZo6eHWdi+P3cTYY8sO+BotQWdfNfrJGJ7MIJ3w0Jl/O95N7MRs61T7kJ538Br6fApGD2RwCEkHf/l/8AfV7hZWqhxzo2pamNGfZWpgzrUvYVvaU1pmtL0rLz2B16k78Nc2fFjO4M6dyMX17sR3dnWxZsOsPHO8+X+brZuXqeWxWIpml887Q3DcqYvK+iujvb0tTGjI92nictO4+Rni1KPklRapi6GfxBBn+dkez7L0zwatDn3u/nL4rbIDlzKCbY0C2sNiZGOhY/1Y3/TfEusFjJkHq62PHWUHc2zu3N7Efc7q2edrA2Y+VMX8Z2bcmyQ1eITcks03VXH73KuZhkPpvoWS058HU6wbAuzUlIy8bO0pSerrZV3gZFqai6G/xtmoP7CAhaDdkP7dSk10PgSnDuB/Zti7+O253VoXWs68fH2RZfl8oNWjqd4Ln+boWOKRjpBC8ObktOnsbaY5GlvmZSeg5f7Q2jX1t7Hu9YfXPoR9wZ4B3apVmlbvajKJWlbv+r9f0LZCZCyE/5j1/eKweES7rrB7C0h+aeEF63gn9N4GJvyYD2Dqw5Fkl2btFJ5x60eF84SRk5vDW0fCmWDaVbq0b8Y2RHtfWiUmvV7eDfug84dIDj38qFXHcFroAGdnJguDTcBkHUccisuhWr9cWM3s7EpWSxMySmxLLXEtJZcSiCCd0c6diicnIklZYQgmf6uNSqLSwV5UF1O/gLAb1fgBunYVF3OL1BLtw6vwO8poBxKRc2uQ2W4wMRf1Zue+uhR9o64GJvyfJDESWW/XTXBXQ6+Ovj7Su/YYpSx9Xt4A9yNs/UTWBuA5tmwf96gZZXui6fu5x8wcRSpn9QDEqnE0zv1Zrga4kEX0ssslxQ5G22nYpmdj/XQvfmVRSlbOp+8BcC2gyG2Qdg3Hdg3hDaD5crgUvL2Ayc+9a5Qd+aYry3I5amRqw8HFHo6zl5et7behZ7KzNmV2GaaEWpy+p+8L9LpwOPifDyaXhyTdnPbzNYrhlIuGL4ttVz1uYmTPRxYvvp6EKnfS7cE8apqCTeH93JYGkhFKW+qz/B/0HlmSVyN9XDxV8N2xYFgGm9WpOn13hpXXC+/ZJPRCSw6I9wJng7VuqCNEWpb+pn8C8P+7bQ0lsuGtOXblqiUnquDlZ8PtGTExEJPPntUeJSskjOzOEV/2AcG8ttGBVFMRwV/MuixxyID5PrBBSDG9fNkaXTfbgcl8aErw/zqv8pYpIy+Y+fl+ruURQDU8G/LDqOAaumcOybgq9pWoHtH5WyG9i+CWv+0oOkjBx2h95k/sA2eLcu+8briqIUTwX/sjA2BZ+ZcuOX+Ev3j+dmwaoxsHoc5OVWX/vqiG6tGvPT3N78bZg7LwxSK2gVpTKo4F9W3s+AzkSuGgZ5t//Lq3B5n5wKevDzam1eXeHmYMXsR9xU3hxFqSTqf1ZZWTeFzuMgaI1M93DsG5k87pE3wMMP9n8CkUeru5WKoijFUsG/PHo8B9kpsO0l2PU3mT10wFsw7HNo1Ap+mgUZRa9WLSA6KH/uIUVRlEqmgn95tPQGx+5wdhM4tIexX8tFZOY2MP57mT9o+8ulGwCOPQ/fDoCD/1fpzVYURblLBf/yGvAWNPeCJ9eCmfX9444+MPBvcHYzHPyi5A+A4NXya9CqOrVbmKIoNZuaPF1ebQbLP4Xp+wrEhsLef0FqLAz5SO4q9rC8HDi1HiwdIPm63Ci+7aP5y2x/BS78KlNQN7AFqybQfwHYq1kwiqKUX4Xu/IUQtkKI34UQYXe+FjohWwjxqxAiUQixvSL11Ro6Ixi3FHrNh+PfwMZnIKeQrQrDfoO0OBj+hQzuQT/kfz06CAKWga0LNHKS4wLntsDRxaVrR3aaWnugKEqhKtrtswDYo2laW2DPne8L8xnwdAXrql10OnjiQ3j8Axmw10wo+AEQtFouGms/HDyelPsMpN26//reD8DCFiavh8nr4Nld0H4YhG4vuYvo5ln4rA0sGyI/RCpCr1frFxSljqlo8B8NrLzz95XAmMIKaZq2B0ipYF21U+8XYOy3EHFQzgy6K+UmXNwFnpPByBi6PQ36O91AAFcPQ/hu6PuyHEi+q+MoSIuFa8eKrjM3GzY/ByYWEB8O3w6En5+XdRYmPQFWjpQfNlmp+V8L2w0Lu8KKYbKbSlGUOqGiwb+ppmkxAHe+Nql4k+ogTz/ZBRTwPYRsksdOr5ebynSdKr9v0kHOIApaJbtq9vxLPhV0/0v+a7V9HIzM4NzWous78BncOAOjFsGLJ6H3fDjtD4u7y9lFD9v5ptyl7MBnsLCb3Nw+6TpsmAFrxsu7/mvHYN/HBvlxKIpS/UoM/kKI3UKIkEL+jDZ0Y4QQs4UQAUKIgLi4OENfvno9+h609IGtL8rUEEGrwamnzBZ6V7dpEHf+zkKxw/DI62DaIP91zKzlQHPo1sKzi14PlLOMPJ8C92Fy85rHP4B5R8DIFPynQGbS/fLnf4EzP8pFas/uhkatYduL8J9Oshtq4NvyA8Rrqrzu1cP3z9U0OLwIlg4q+qlCUZQaSWgVGBAUQlwABmiaFiOEaA7s0zSt0A1WhRADgNc0TRtRmmv7+PhoAQEB5W5bjZQYCV/3BVNrSI6Sd+bdHhgKyUqBz9tDTppcLDY/UOYTeljwOvh5DszaI6eW3pWTAd88Igd65x4Gi0b5z4s4JLt32g0Bv9WQmQiLe8gnjL/slXVpmpymeu0Y+M6+v+NZVgp83U+ONcz9Uz59bH8FTq2Vr3caCxNXGPTHpShK2QkhAjVN8ympXEW7fbYC0+/8fTqwpYLXq9satYIxS2TgN7GETg8NkZhZy9QRIKdzFhb4AdoPkfmFzj304979Hty6CKMWFgz8AM595CD0hV/gzy9g5xuQkQBj/ne/LiFkG4Z+kn+rSzNrOYMp+TpseR5WjpCBf8Bb8ung7Gb5pKAoSq1Q0Xn+HwM/CiGeBSKBiQBCCB9gjqZps+58fxBwB6yEEFHAs5qm7apg3bWT+3CZBsLIJP/isLseeR0aOso8QUWxaAyu/WXXz2Pvy4AdtBqOfS33HChq/QHI16+flIO7cGexmkfp2u7UHfq/Cfv+DSYNYNIP0HG0HGA+uxl++avc6/jBAWpFUWqkCnX7VKY62e1jSIErZd/8cwchOxVWjpKBd8pGOXuoONnpcvaO0MHMXfKDqLTycuHwV9D2MWjW5f7xqAD47lHo/qxct6AoSrUobbePCv61Vdot+LwtdJkIYb/LRWKzdhfe3VOYvFxAK1vgL8nOBfLpY+av0Kqn4a6rKEqpVVWfv1JdLO2hdR85hVPTw1P+pQ/8IJ8ODBn4AQb9XXZZPbieQVGUGkkF/9qs69NgbA5+q/IPzlYXMyvo9bycbnojpLpboyhKMVTwr808/eDNCHB5pLpbcp+Hn1xPELSquluiKEoxVPCv7UwsqrsF+TWwlTOaTvurDWoUpQZTwV8xvK5PQ8ZtOF8/krgqSm2kgr9ieK4DoaETnFRdP4pSU6ngrxieTgdeU+DyPpnSQlGUGkcFf6VydJ0ivwatqd52KIpSKBX8lcrRqBW4DoDgNYbZm1jT1B7HD8vNhgs7C+7BoCiloIK/Unm6PQ1J12T3T0XkZMDyYXI3tBq6Ir1K6fVw+ke5P8O6J+HQl9XdIqUWUsFfqTzuI8DMRiZ9Ky9Ng20vyf0NLu2Vu5/VZ5HH4Jt+sOkvMjW4fTu48Gt1t0qphVTwVyqPsZlMAHdhZ/m7bA5/JdcMPPIG2LrCnvcL38SmPsjLhY0zISMRxn8Pzx2QA+s3z8id1xSlDFTwVyqX+whIv1X8nsNFufgb/P4P6DgGBv5N7hsQexZCNhq+nbXB+W1yL4hhn0GXCXJWVbsh8rWwev5EpJSZCv5K5WrzqEz3EFrGBV+x5+GnZ6FZZ7nZjBDQaZxMI/3Hh3Kws745+jU0doZ2T9w/5tBebr1Z37vDlDJTwV+pXOY2ctbP+W2lH6y9FQ4/jJJJ655cB6aW8rhOB4PehdsREPRDJTW4hooOgmtHwfc50BndPy6EvPu/vE/u01DVbkfA8uGyOy4rperrV8pNBX+l8rmPkIu9bpYi02fCZbnPsD4Ppm+DRk75X2/7GLTqBfs/rZ5gV12Ofg2mVvfXTzyo3ROQmwkRB4s+X9Pg+FK4ec5wbboVLmdhXQ+Eg1/AV90gcIWakltLqOCvVL72QwFRctfP7QhYMVIGsulboYl7wTJCwOB/QOpNOLmyMlpb86TchJCf5OCuecOCrzv3lXtCF9f1E/Yb7HgNlg6CU/4Vb1NsKCwfKn9Xs36HWXvlgPy2l+Db/pAaV/E6lEqlgr9S+ayayJ29ikr0lnAF9n8Gy4bILSmnbYGmnYq+Xute0NJb5g6qi/P+L/0hn4DuClgG+lzo8Vzh5Y3NwG2gDP5F/Tz+/BJsHKFlN9g8G3a8XvZxE02D5Bg4vwNWDJfbgM7YIcdhHL3lDm4TlsOtMPjxaZXVtYar6AbuilI67iPgt7dloLd1kYEk5Cc49g1EHZdlWveBIR+VbkP5rlNh+ysQEwwtulZu26vS2Z9hw3T591a95P4IAd/Lrp3iNuxp94T8cL15Vg6SPyjymFwnMeRj6D4Ldr8HRxZBzGn5hGVsVvB6Wamym+7GGfnn5lm4dRGykuXrNo7y3AfbJAR0Hgdockrq9ldh9CJ5XKlxVPBXqob7cBn8z/8i9x3e/jJc2AEO7vDoe9B5QsH+/eJ0Hg+/vgVBq+tO8E+5IX8uLbpCh1Fwap38HqDHnOLPbfu4/Hrx14LB/9CXYNEYuk2TW3c+8SE06Qhb5kHwWvB5Jn/55Bj4uq+cogvy3Kad5QeRfTtwaCefvMysC29L5/FyttaBT6FpR7m7m1LjqOCvVA1bFxlAjn8LBz+Xg7WPfwg95+afvVJa5g1lgDyzAR7/oOZtalNWmgZb5kNOJoxbCvZtoe8rEH0S4i/JGVPFsW4mPzQu7oJHXrt/PPa8/JAd8Nb9WVMAXk/Bie/g0H/l/gtGD4SCg19AZiJMXAmO3cGmRdnv3ge8BXHn4be/y7GA9kPLdr5S6VSfv1J1OoyExKsyGMz5E3rPL1/gv6vrVMhMkk8TtV3AMgj/HR7/lwz8IANuS2/wmFS64NtuCESdgCOL5WpgkMHdpAH4zs5fVgjo9yrcvgLnfr5/PDFSztjp+jR0GgMNW5av20ang7Ffyw/8dU/C1hchPaHs11EqjQr+StXp/SL4rYGZv8mug4py7iezh9b2/YJvhcs7ZLfBsk++vHo8J7t/dv0NvhskB2bP/AjdpsvtNR/WfjjYt4c//3N/oHj/p3Ig95HXy9+Ou0wt4Zmd0Gu+7J5b5CO7mapzkD4nQ45FRAdXXxtqCBX8lapj2gA6jMjfxVAROh14TYXL++H2VcNcszrsfEOugh69uGKDoxaN4Sl/mLhC9tuvnyyPF9XnrtNB35flwG7Yb7J7KXgt+MyUd/yGYGYlxxieOwC2bvDzXPlBV11+f1cOoG9/uW7OFCsDFfyV2s3rToA7ta5621FetyPg0h4ZoG2aV/x6QkCnsTD/BPSYC4PeKX4gvctEueXmwS9g30dy5k+/Vyvejoc16wwzd4HPs3Km0ekfDV9HScJ+l2NOTTrJFdMXdlZ9G2oQFfyV2u3upjFBq2X3SW0TtFp2s3g9ZdjrWjSCoR/LO/viGJnI7rhrx+TgeY/n5LqMyqDTwdBP5JTerS9UbddL2i34eZ6c5fTsb3Lc6Y9/198MsVQw+AshbIUQvwshwu58bVxIGS8hxBEhxFkhxGkhhF9F6lSUAnrPh5QYWOQt0w2c8pd9uzWdPk9uc+k2GBo6Vl87uk6FBvZy74XeL1ZuXUYmchZRA3tYP6VqVgJrmhxwzkyUM6nMrKD/ApkKO3Rr5ddfQwmtAv1eQohPgQRN0z4WQiwAGmua9uZDZdoBmqZpYUKIFkAg0EHTtMTiru3j46MFBASUu21KPZNyQ/ZXn/xBzmBpYC+7UrrPksnl7srJkFMQU+PkPPa0W+DkK1cgV7WLv8HaiTBpFXQcVfX1P+jKQcjLhjaDq6a+6CC5ortJRzkLzKoJWDYBp+5y7MKQApbLPv7HP5Q3CiA/eP/XS3aTzT1csVlnNYwQIlDTNJ8Sy1Uw+F8ABmiaFiOEaA7s0zStfQnnnAImaJoWVlw5FfyVctHrZYKzw19B+G65HsBnJuTlQORRiDkF+pz85zTpCPOOVH1b/afC1SPwaigYm1Z9/dUt5CfY9gpkJd0/1thF/i4MtW4jfDes9QOXR2DKT7Lr6a6zm2HDDPk04DHJMPXVAKUN/hWddtFU07QYgDsfAMV2FgohfAFT4FIF61WUwul04Npf/okOggOfy6mMRmYyr03v+dCiG1g3B0s7Ob/+yGK56My0QdW1MzVWDjj2nFs/Az/IlcCdx0N2mvx5RJ2Q21Me+AwGv1vx60cFgv80cOggZ0DpHurl7jBarkPY95EcJDcyqXidtUiJwV8IsRtoVshLb5elojtPBquA6ZqmFTrKIoSYDcwGaNWqVVkurygFtegKT66RXTzmNoXnsHHqAYcXQuw5cCzxZslwTq2Tydq6Tqu6OmsqU0u5AtzWRe7TfOgr6DKp8KyupXUrDNZMAEt7mPpT4dlQdTo5G2qdn5wFVM/SUJQ44Ktp2qOapnUu5M8W4OadoH43uMcWdg0hhA3wC/B3TdOOFlPXt5qm+Wia5uPg4FC+d6QoD7NyKDzwAzT3lF9jqnDmiabJjKROPQyz2K0ueexf8sPgl1fLPw8/NhRWjZX9+E9vBuumRZdt94RcGPfHR3JtRD1S0ameW4E7KQiZDmx5uIAQwhTYDPygadqGCtanKIbV0EkOMMacMvy19XkQFSBXza4cJQc4V46CH0ZDfJhMtKbkZ+UAj70PVw9B8JqynZtwBTY9Jwdys5JhysbiM6GCHPAd+okc7P79nfK3uxaqaPD/GHhMCBEGPHbne4QQPkKI7+6UmQQ8AswQQgTf+eNVwXoVxTCEgOZehg/+x76BT13hu8FyPnnGbdAZy81PMhPBpb/sZ1YK6vo0OPWE396BtPiSy2sa7Hpbpo849zP0fgFeDIYWpQwztq5yPcSZDXLWUz1Rodk+lUnN9lGqzO//kIO+f4s2zOBrZhJ80UGuau3xHLgMkIPLSundPAff9JN7GkzZCCbmRZeNCpAfsl0mym6j8qyUzsmAxb4yCd6cP2v14G9pZ/uoFb6K0txTTv+MCzXM9U7/CDlpcmOazuNV4C+Pph1hzBI5bXfjM/ezlBYm5CeZG2n4F+VPkWFiAUM/lWtA9vwTMpPLd51aRAV/Rbk36GuArh9Nk4uKmnvKKaVK+XlMgqGfyf0Itr5QeCoGfR6EbJKDtoXN6CmL9kOh0zg5++vzdrDxWQjbXWcTwKngryiNXWRqA0ME/6gTEHtWLixT2xdWXI/ZcmOYU2sLzwYaeQRSb9zZProJvJkAAAlbSURBVNIAJiyDZ3fLXEvhu2HNeDi+1DDXrmFU8FcUnQ6aeRgm0VjAMjC1lttSKobR/03wfQ6OLpZ34g8K+Un207cbYpi6hJApJkb8H7x2Ua4Vqe37RRRBBX9FAdlNczOk+L7lkqQnyC4ITz+ZPEwxDCHkVp22rnIf6Lu/o7xcOLdFBv4Ht6g0FGMzudjsxmm5aKyOUcFfUUAG/9xMuHWx/Nc4tQ7yssD7mZLLKmVjbCpn8sSdh8Dl8tiV/ZAeLwfVK0unsYCQTxh1jAr+igIVH/TVNNnl4+grp3gqhuc+XG7d+ce/ISNRPmWZ2UCbRyuvTpvm4NwXzmyscwO/KvgrCshN040tyh/8L+yE+HA50KtUDiHgiTsL5v74EEK3gfuI4tcAGELn8XJF9o3TlVtPFVPBX1FA5oFp1qV8wf/SH7Bxpswe2WmM4dum3NfcQ24+c/xbmQraULN8itNxtFydfWZj5ddVhVTwV5S7mnvKu7sH55Pr82SisOC1sON12PuB3Hf3rou/yXzxdm4wY7vh8tArRRv0DphayZxMrgMqv74GtnK3tZBNdWrbx4rm81eUuqO5J5xYCjFBcj/g0K3yrj4nTb5uYgm5GXKPgDaPgnMf2PuhXI369M8ySCiVz7opjP9ObtBTVWkYOo+HsF1yr+PWvaqmzkqmgr+i3HV30HfpIPnVurmctunUQ873tmsjt4s8uRICV0L479DSR+aLt2hUfe2uj9oPrdr63IeBsTmEbFTBX1HqnCYdweNJuQFIx9EysD+8+1PDljDwb/DI63D1MLT0VnP66wMza7me4OzPstupDnzYq6yeiqIopXHlIKwaA9YtZLdTqx7V3aJCqayeiqIohuTSD2b+Jp8Glw+VYz/6vOpuVbmp4K8oilJajt7w3AE5pXfvv2D9FDnwXAup4K8oilIW5g1h/Pcy///FnTLddA3tPi+OGvBVFEUpKyHkLm0Zt2HfR2DTAga/W92tKhMV/BVFUcqr/5uQHA0Hv5BTg33/Ut0tKjUV/BVFUcpLCBj+f5AWJ1eAp8RAz+drxdadqs9fURSlIoyM5RhAp7HyCeDLzvDrW5B0vbpbViwV/BVFUSrKtAFMXA7PH4eOY+DYN/C/npAaW90tK5IK/oqiKIbi0B7GLoGZv0JWMlzcVd0tKpIK/oqiKIbm2B1sWsLFX6u7JUVSwV9RFMXQhIC2j8PlfZCbVd2tKZQK/oqiKJWh3ROQnSoTANZAKvgriqJUBpf/b+/eY+wo6zCOf59UblYNJaxl6TbFhBYvoLScQGIjiXIpVkL5R6NRUhElJJqg/kGqxhgSQzQoEv8kiAFvDREMBC9QcdWUqHS3bmlrxYIB27TYGjTQREXg8Y8ZI9Ztu5uzM++eM88nOZmZs3N2njeb/Z0371zeC2HBCbD7odJJppXiHxHRhOMXVl8A8/Skb1/FX9IpkjZJ2l0vF02zzzJJk5KmJO2UdF0/x4yIGBgr1sCzT1Yzwx1Ngekh++35bwAetr0ceLjePtx+4O22zwUuADZIOr3P40ZEzH/LL62Wu4/S+9+2EW46HTZ9Af7xXDu56L/4rwPurNfvBK48fAfbL9j+z+nuE+bgmBERg2HRMhh545GHfv7+V3jws9VMYY/cCl9fCRN3wEsvNh6t30K82PZ+gHr5+ul2krRU0mPAHuDLtvcdYb9rJU1Imjh48GCf0SIi5oEVa6orfv75/P//bPym6gvgqnvhY+Nw6gp44FPVZDENPyb6mMVf0k8l7ZjmtW6mB7G9x/ZbgTOB9ZIWH2G/22z3bPdGRkZm3oqIiPlq+Rp4+V/w5Pj/vv/MDthyO/Q+AqedA0tWwdU/gvd9C1Z+sLpXoEHHfKqn7YuP9DNJf5Y0anu/pFHgqA+ysL1P0k7gHcD3Z502ImLQLL2gmgBm6rtw5kXVVUA2/PgGOPFkeOfn/ruvBG++opVY/Q773A+sr9fXA/cdvoOkMUkn1euLgNXA430eNyJiMCx4FZx3dTXr19fOhl/cDJPfhKcfgYs+D68+pUisfp/n/yXgbknXAH8C3gsgqQdcZ/ujwJuAr0oyIOArtrf3edyIiMFxyY1w1lrYfAuMf7F6b/RtsGr90T/XIHmezj3Z6/U8MTFROkZExNx6ZjtsvQvO+zAsfsuc/3pJk7Z7x9ovM3lFRLTptHNg7c2lU+Sa+4iILkrxj4jooBT/iIgOSvGPiOigFP+IiA5K8Y+I6KAU/4iIDkrxj4jooHl7h6+kg8DTs/jIqcBfGoozX6XN3ZA2d8dctHuZ7WM+FnneFv/ZkjQxk1uah0na3A1pc3e02e4M+0REdFCKf0REBw1T8b+tdIAC0uZuSJu7o7V2D82Yf0REzNww9fwjImKGhqL4S7pM0uOSnpC0oXSepkm6Q9IBSTtKZ2mLpKWSxiXtkrRT0vWlMzVN0omSHpW0rW7zjaUztUXSAkm/lfRA6SxtkPSUpO2SpiS1MovVwA/7SFoA/AG4BNgLbAE+YPt3RYM1SNKFwCHgLttnl87TBkmjwKjtrZJeC0wCVw7531nAQtuHJB0HbAaut/3rwtEaJ+nTQA94ne3LS+dpmqSngJ7t1u5tGIae//nAE7b/aPsFYCOwrnCmRtn+JfBs6Rxtsr3f9tZ6/XlgF7CkbKpmuXKo3jyufg12b20GJI0B7wFuL51lmA1D8V8C7HnF9l6GvCh0naQzgJXAb8omaV49/DEFHAA22R76NgO3AjcAL5cO0iIDD0malHRtGwcchuKvad4b+t5RV0l6DXAP8Enbz5XO0zTbL9k+FxgDzpc01MN8ki4HDtieLJ2lZattrwLeDXy8Htpt1DAU/73A0ldsjwH7CmWJBtXj3vcA37F9b+k8bbL9N+DnwGWFozRtNXBFPQa+EXiXpG+XjdQ82/vq5QHgB1TD2Y0ahuK/BVgu6Q2SjgfeD9xfOFPMsfrk5zeAXbZvKZ2nDZJGJJ1cr58EXAz8vmyqZtn+jO0x22dQ/S//zPaHCsdqlKSF9UUMSFoIXAo0fiXfwBd/2y8CnwAepDoJeLftnWVTNUvS94BfAWdJ2ivpmtKZWrAauIqqJzhVv9aWDtWwUWBc0mNUnZxNtjtx6WPHLAY2S9oGPAr80PZPmj7owF/qGRERszfwPf+IiJi9FP+IiA5K8Y+I6KAU/4iIDkrxj4jooBT/iIgOSvGPiOigFP+IiA76N35WrYQnb4oCAAAAAElFTkSuQmCC\n",
      "text/plain": [
       "<matplotlib.figure.Figure at 0x7f94ee26ef28>"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    }
   ],
   "source": [
    "plt.plot(results['time'], results['phi_velocity'], label='phi_velocity')\n",
    "plt.plot(results['time'], results['theta_velocity'], label='theta_velocity')\n",
    "plt.plot(results['time'], results['psi_velocity'], label='psi_velocity')\n",
    "plt.legend()\n",
    "_ = plt.ylim()"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "Finally, you can use the code cell below to print the agent's choice of actions.  "
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 9,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "image/png": "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\n",
      "text/plain": [
       "<matplotlib.figure.Figure at 0x7f94ee2ced68>"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    }
   ],
   "source": [
    "plt.plot(results['time'], results['rotor_speed1'], label='Rotor 1 revolutions / second')\n",
    "plt.plot(results['time'], results['rotor_speed2'], label='Rotor 2 revolutions / second')\n",
    "plt.plot(results['time'], results['rotor_speed3'], label='Rotor 3 revolutions / second')\n",
    "plt.plot(results['time'], results['rotor_speed4'], label='Rotor 4 revolutions / second')\n",
    "plt.legend()\n",
    "_ = plt.ylim()"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "When specifying a task, you will derive the environment state from the simulator.  Run the code cell below to print the values of the following variables at the end of the simulation:\n",
    "- `task.sim.pose` (the position of the quadcopter in ($x,y,z$) dimensions and the Euler angles),\n",
    "- `task.sim.v` (the velocity of the quadcopter in ($x,y,z$) dimensions), and\n",
    "- `task.sim.angular_v` (radians/second for each of the three Euler angles)."
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 10,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "[ 22.11643063  -0.83938066  24.83411547   0.30119688   5.46954704   0.        ]\n",
      "[ 13.32309768   0.94426614   0.81502723]\n",
      "[ 0.22470381 -0.30101198  0.        ]\n"
     ]
    }
   ],
   "source": [
    "# the pose, velocity, and angular velocity of the quadcopter at the end of the episode\n",
    "print(task.sim.pose)\n",
    "print(task.sim.v)\n",
    "print(task.sim.angular_v)"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "In the sample task in `task.py`, we use the 6-dimensional pose of the quadcopter to construct the state of the environment at each timestep.  However, when amending the task for your purposes, you are welcome to expand the size of the state vector by including the velocity information.  You can use any combination of the pose, velocity, and angular velocity - feel free to tinker here, and construct the state to suit your task.\n",
    "\n",
    "## The Task\n",
    "\n",
    "A sample task has been provided for you in `task.py`.  Open this file in a new window now. \n",
    "\n",
    "The `__init__()` method is used to initialize several variables that are needed to specify the task.  \n",
    "- The simulator is initialized as an instance of the `PhysicsSim` class (from `physics_sim.py`).  \n",
    "- Inspired by the methodology in the original DDPG paper, we make use of action repeats.  For each timestep of the agent, we step the simulation `action_repeats` timesteps.  If you are not familiar with action repeats, please read the **Results** section in [the DDPG paper](https://arxiv.org/abs/1509.02971).\n",
    "- We set the number of elements in the state vector.  For the sample task, we only work with the 6-dimensional pose information.  To set the size of the state (`state_size`), we must take action repeats into account.  \n",
    "- The environment will always have a 4-dimensional action space, with one entry for each rotor (`action_size=4`). You can set the minimum (`action_low`) and maximum (`action_high`) values of each entry here.\n",
    "- The sample task in this provided file is for the agent to reach a target position.  We specify that target position as a variable.\n",
    "\n",
    "The `reset()` method resets the simulator.  The agent should call this method every time the episode ends.  You can see an example of this in the code cell below.\n",
    "\n",
    "The `step()` method is perhaps the most important.  It accepts the agent's choice of action `rotor_speeds`, which is used to prepare the next state to pass on to the agent.  Then, the reward is computed from `get_reward()`.  The episode is considered done if the time limit has been exceeded, or the quadcopter has travelled outside of the bounds of the simulation.\n",
    "\n",
    "In the next section, you will learn how to test the performance of an agent on this task."
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "## The Agent\n",
    "\n",
    "The sample agent given in `agents/policy_search.py` uses a very simplistic linear policy to directly compute the action vector as a dot product of the state vector and a matrix of weights. Then, it randomly perturbs the parameters by adding some Gaussian noise, to produce a different policy. Based on the average reward obtained in each episode (`score`), it keeps track of the best set of parameters found so far, how the score is changing, and accordingly tweaks a scaling factor to widen or tighten the noise.\n",
    "\n",
    "Run the code cell below to see how the agent performs on the sample task."
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 11,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "Episode = 1000, score =  -1.074 (best =  -0.139), noise_scale = 3.2625"
     ]
    }
   ],
   "source": [
    "import sys\n",
    "import pandas as pd\n",
    "from agents.policy_search import PolicySearch_Agent\n",
    "from task import Task\n",
    "\n",
    "num_episodes = 1000\n",
    "target_pos = np.array([0., 0., 10.])\n",
    "task = Task(target_pos=target_pos)\n",
    "agent = PolicySearch_Agent(task) \n",
    "\n",
    "\n",
    "for i_episode in range(1, num_episodes+1):\n",
    "    state = agent.reset_episode() # start a new episode\n",
    "    while True:\n",
    "        action = agent.act(state)\n",
    "        next_state, reward, done = task.step(action)\n",
    "        agent.step(reward, done)\n",
    "        state = next_state\n",
    "        if done:\n",
    "            print(\"\\rEpisode = {:4d}, score = {:7.3f} (best = {:7.3f}), noise_scale = {}\".format(\n",
    "                i_episode, agent.score, agent.best_score, agent.noise_scale), end=\"\")  # [debug]\n",
    "            break\n",
    "    sys.stdout.flush()"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "This agent should perform very poorly on this task.  And that's where you come in!"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {
    "collapsed": true
   },
   "source": [
    "## Define the Task, Design the Agent, and Train Your Agent!\n",
    "\n",
    "Amend `task.py` to specify a task of your choosing.  If you're unsure what kind of task to specify, you may like to teach your quadcopter to takeoff, hover in place, land softly, or reach a target pose.  \n",
    "\n",
    "After specifying your task, use the sample agent in `agents/policy_search.py` as a template to define your own agent in `agents/agent.py`.  You can borrow whatever you need from the sample agent, including ideas on how you might modularize your code (using helper methods like `act()`, `learn()`, `reset_episode()`, etc.).\n",
    "\n",
    "Note that it is **highly unlikely** that the first agent and task that you specify will learn well.  You will likely have to tweak various hyperparameters and the reward function for your task until you arrive at reasonably good behavior.\n",
    "\n",
    "As you develop your agent, it's important to keep an eye on how it's performing. Use the code above as inspiration to build in a mechanism to log/save the total rewards obtained in each episode to file.  If the episode rewards are gradually increasing, this is an indication that your agent is learning."
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 20,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "\n",
      "Ep=   1, score=-22.413 (best= 23.065) pos=0.56 1.57 0.0\n",
      "Ep=   2, score=-22.244 (best= 23.095) pos=0.55 1.59 0.0\n",
      "Ep=   3, score=-22.641 (best= 23.095) pos=0.58 1.56 0.0\n",
      "Ep=   4, score=-25.981 (best= 23.095) pos=-0.42 2.25 0.0\n",
      "Ep=   5, score=-22.010 (best= 23.095) pos=0.35 -1.63 0.0\n",
      "Ep=   6, score= -5.595 (best= 27.941) pos=-0.3 -0.04 0.0\n",
      "Ep=   7, score=-27.381 (best= 27.941) pos=-2.3 0.17 0.0\n",
      "Ep=   8, score=-17.015 (best= 27.941) pos=-1.15 0.41 0.0\n",
      "Ep=   9, score=-41.718 (best= 27.941) pos=-3.1 -1.08 0.0\n",
      "Ep=  10, score=-28.751 (best= 27.941) pos=-0.88 -1.33 0.0\n",
      "Ep=  11, score= -9.261 (best= 31.274) pos=-0.07 -1.46 0.0\n",
      "Ep=  12, score=-28.897 (best= 31.274) pos=-0.0 -1.82 0.0\n",
      "Ep=  13, score= -2.872 (best= 31.274) pos=0.0 -0.25 0.0\n",
      "Ep=  14, score=-36.922 (best= 31.274) pos=-1.9 2.43 0.0\n",
      "Ep=  15, score=-13.587 (best= 31.274) pos=0.02 0.63 0.0\n",
      "Ep=  16, score=-62.388 (best= 31.274) pos=-7.31 0.91 0.0\n",
      "Ep=  17, score=-28.819 (best= 31.274) pos=-2.66 0.36 0.0\n",
      "Ep=  18, score=-69.389 (best= 31.274) pos=-8.3 -0.47 0.0\n",
      "Ep=  19, score=-41.796 (best= 31.274) pos=3.4 0.65 0.0\n",
      "Ep=  20, score=-6826.401 (best= 31.274) pos=96.5 21.12 89.94\n",
      "Ep=  21, score=-656.455 (best= 31.274) pos=-0.34 39.49 0.0\n",
      "Ep=  22, score=-226.116 (best= 31.274) pos=-6.56 14.07 0.0\n",
      "Ep=  23, score=-39.717 (best= 31.274) pos=2.6 0.63 0.0\n",
      "Ep=  24, score=-101.448 (best= 45.090) pos=12.88 0.12 0.0\n",
      "Ep=  25, score=-125.433 (best= 45.090) pos=-9.13 -5.9 0.0\n",
      "Ep=  26, score=-201.935 (best= 45.090) pos=-12.26 7.91 0.0\n",
      "Ep=  27, score=-5093.980 (best= 45.090) pos=-44.52 5.12 134.02\n",
      "Ep=  28, score=-36.016 (best= 45.090) pos=-2.93 0.03 0.0\n",
      "Ep=  29, score=-3511.004 (best= 45.090) pos=-16.62 1.74 72.27\n",
      "Ep=  30, score=-3266.143 (best= 45.090) pos=54.19 14.11 53.41\n",
      "Ep=  31, score=-1014.848 (best= 45.090) pos=-46.76 -0.17 0.0\n",
      "Ep=  32, score=-4480.868 (best= 45.090) pos=69.5 -5.36 72.87\n",
      "Ep=  33, score=-187.434 (best= 45.090) pos=8.78 7.07 0.0\n",
      "Ep=  34, score=  8.929 (best= 45.090) pos=0.01 0.67 0.0\n",
      "Ep=  35, score=-2982.586 (best= 45.090) pos=12.81 22.43 42.04\n",
      "Ep=  36, score=-44.887 (best= 45.090) pos=-5.87 -0.17 0.0\n",
      "Ep=  37, score=-51.016 (best= 45.090) pos=-5.85 0.29 0.0\n",
      "Ep=  38, score=-69.138 (best= 45.090) pos=-6.03 0.07 0.0\n",
      "Ep=  39, score=-15.518 (best= 45.090) pos=-0.8 -0.01 0.0\n",
      "Ep=  40, score=-137.798 (best= 45.090) pos=-11.85 0.62 0.0\n",
      "Ep=  41, score=-168.545 (best= 45.090) pos=-12.48 1.88 0.0\n",
      "Ep=  42, score=-71.963 (best= 45.090) pos=-5.88 1.39 0.0\n",
      "Ep=  43, score=-20.568 (best= 45.090) pos=2.15 -0.16 0.0\n",
      "Ep=  44, score=-35.963 (best= 45.090) pos=-5.07 0.04 0.0\n",
      "Ep=  45, score=-16.755 (best= 45.090) pos=-1.89 1.3 0.0\n",
      "Ep=  46, score=-38.586 (best= 45.090) pos=-2.55 1.46 0.0\n",
      "Ep=  47, score= -8.395 (best= 45.090) pos=-1.52 0.01 0.0\n",
      "Ep=  48, score=-33.947 (best= 45.090) pos=-1.74 -1.25 0.0\n",
      "Ep=  49, score=-12.376 (best= 45.090) pos=-1.45 0.01 0.0\n",
      "Ep=  50, score=  0.163 (best= 45.090) pos=0.58 -0.0 0.0\n",
      "Ep=  51, score=-26.823 (best= 45.090) pos=0.74 -0.51 0.0\n",
      "Ep=  52, score=-20.438 (best= 45.090) pos=1.78 -0.0 0.0\n",
      "Ep=  53, score=-14.077 (best= 45.090) pos=1.06 -0.0 0.0\n",
      "Ep=  54, score=  2.225 (best= 45.090) pos=0.44 0.0 0.0\n",
      "Ep=  55, score=  2.038 (best= 45.090) pos=-0.36 -0.18 0.0\n",
      "Ep=  56, score=  4.429 (best= 45.090) pos=-1.35 0.85 0.0\n",
      "Ep=  57, score=  4.247 (best= 45.090) pos=0.29 0.0 0.0\n",
      "Ep=  58, score=  3.853 (best= 45.090) pos=0.33 0.0 0.0\n",
      "Ep=  59, score= -2.045 (best= 45.090) pos=-0.86 0.45 0.0\n",
      "Ep=  60, score=-12.023 (best= 45.090) pos=1.38 -0.0 0.0\n",
      "Ep=  61, score=-28.705 (best= 45.090) pos=2.04 -0.16 0.0\n",
      "Ep=  62, score=-28.044 (best= 45.090) pos=1.99 -0.18 0.0\n",
      "Ep=  63, score=-12.744 (best= 45.090) pos=-0.97 -0.05 0.0\n",
      "Ep=  64, score= -3.902 (best= 45.090) pos=0.05 0.0 0.0\n",
      "Ep=  65, score= -5.073 (best= 45.090) pos=-0.24 -0.0 0.0\n",
      "Ep=  66, score= -8.037 (best= 45.090) pos=-0.49 0.51 0.0\n",
      "Ep=  67, score=-11.010 (best= 45.090) pos=-1.27 -0.05 0.0\n",
      "Ep=  68, score= -7.588 (best= 45.090) pos=-0.07 -0.23 0.0\n",
      "Ep=  69, score=-26.103 (best= 45.090) pos=-0.84 1.4 0.0\n",
      "Ep=  70, score=-71.068 (best= 45.090) pos=-5.0 1.74 0.0\n",
      "Ep=  71, score= -8.662 (best= 45.090) pos=-0.06 0.33 0.0\n",
      "Ep=  72, score=-36.912 (best= 45.090) pos=-2.64 0.71 0.0\n",
      "Ep=  73, score=-20.605 (best= 45.090) pos=-2.02 0.0 0.0\n",
      "Ep=  74, score=-20.863 (best= 45.090) pos=-1.33 -0.24 0.0\n",
      "Ep=  75, score=-23.502 (best= 45.090) pos=-2.49 0.01 0.0\n",
      "Ep=  76, score=-19.517 (best= 45.090) pos=-2.14 0.0 0.0\n",
      "Ep=  77, score=-17.183 (best= 45.090) pos=-2.3 0.0 0.0\n",
      "Ep=  78, score=-24.814 (best= 45.090) pos=-2.42 0.01 0.0\n",
      "Ep=  79, score=-23.925 (best= 45.090) pos=-2.46 0.0 0.0\n",
      "Ep=  80, score=-25.057 (best= 45.090) pos=-2.4 0.0 0.0\n",
      "Ep=  81, score=-32.657 (best= 45.090) pos=-2.83 0.58 0.0\n",
      "Ep=  82, score=-13.781 (best= 45.090) pos=-1.12 -0.09 0.0\n",
      "Ep=  83, score=-21.958 (best= 45.090) pos=-1.87 0.08 0.0\n",
      "Ep=  84, score=-20.406 (best= 45.090) pos=-2.05 0.0 0.0\n",
      "Ep=  85, score=-19.259 (best= 45.090) pos=-1.13 0.0 0.0\n",
      "Ep=  86, score=-13.716 (best= 45.090) pos=-0.49 -0.0 0.0\n",
      "Ep=  87, score=-12.363 (best= 45.090) pos=-0.41 -0.0 0.0\n",
      "Ep=  88, score=-10.914 (best= 45.090) pos=-0.33 0.12 0.0\n",
      "Ep=  89, score=-18.575 (best= 45.090) pos=-1.01 0.0 0.0\n",
      "Ep=  90, score=-10.412 (best= 45.090) pos=0.12 0.4 0.0\n",
      "Ep=  91, score= -8.075 (best= 45.090) pos=-0.07 -0.0 0.0\n",
      "Ep=  92, score= -3.229 (best= 45.090) pos=0.12 0.29 0.0\n",
      "Ep=  93, score=-39.557 (best= 45.090) pos=-3.36 0.28 0.0\n",
      "Ep=  94, score= -9.991 (best= 45.090) pos=-0.6 -0.28 0.0\n",
      "Ep=  95, score= -7.272 (best= 45.090) pos=0.4 -0.0 0.0\n",
      "Ep=  96, score=-11.090 (best= 45.090) pos=-0.29 -0.0 0.0\n",
      "Ep=  97, score=-21.444 (best= 45.090) pos=-1.15 -0.95 0.0\n",
      "Ep=  98, score=-26.368 (best= 45.090) pos=2.15 0.49 0.0\n",
      "Ep=  99, score=-21.933 (best= 45.090) pos=1.84 -0.0 0.0\n",
      "Ep= 100, score= -3.741 (best= 45.090) pos=0.86 -0.34 0.0\n",
      "Ep= 101, score=  3.246 (best= 45.090) pos=0.09 -0.43 0.0\n",
      "Ep= 102, score= -9.983 (best= 45.090) pos=0.7 -0.74 0.0\n",
      "Ep= 103, score= -3.044 (best= 45.090) pos=-1.09 0.0 0.0\n",
      "Ep= 104, score= -7.868 (best= 45.090) pos=-1.3 0.0 0.0\n",
      "Ep= 105, score=-11.221 (best= 45.090) pos=-1.42 0.01 0.0\n",
      "Ep= 106, score=-14.243 (best= 45.090) pos=-1.49 0.0 0.0\n",
      "Ep= 107, score= -8.050 (best= 45.090) pos=-1.51 0.01 0.0\n",
      "Ep= 108, score= -8.977 (best= 45.090) pos=-1.53 0.01 0.0\n",
      "Ep= 109, score= -8.818 (best= 45.090) pos=-1.53 0.02 0.0\n",
      "Ep= 110, score= -8.372 (best= 45.090) pos=-1.52 0.06 0.0\n",
      "Ep= 111, score=-31.303 (best= 45.090) pos=-1.48 -1.09 0.0\n",
      "Ep= 112, score=-23.959 (best= 45.090) pos=-1.66 0.4 0.0\n",
      "Ep= 113, score=-18.931 (best= 45.090) pos=-1.44 0.46 0.0\n",
      "Ep= 114, score=-35.015 (best= 45.090) pos=-1.92 1.57 0.0\n",
      "Ep= 115, score=-12.366 (best= 45.090) pos=-0.82 -0.45 0.0\n",
      "Ep= 116, score=-21.784 (best= 45.090) pos=-1.39 0.7 0.0\n",
      "Ep= 117, score=  2.708 (best= 45.090) pos=-0.0 -0.0 0.0\n",
      "Ep= 118, score= -3.283 (best= 45.090) pos=-0.0 -0.02 0.0\n",
      "Ep= 119, score=  2.708 (best= 45.090) pos=-0.0 -0.0 0.0\n",
      "Ep= 120, score=  2.708 (best= 45.090) pos=0.0 0.0 0.0\n",
      "Ep= 121, score= -7.848 (best= 45.090) pos=0.0 0.38 0.0\n",
      "Ep= 122, score=  2.708 (best= 45.090) pos=0.0 -0.0 0.0\n",
      "Ep= 123, score=  2.708 (best= 45.090) pos=0.0 0.0 0.0\n",
      "Ep= 124, score=  2.708 (best= 45.090) pos=0.0 -0.0 0.0\n",
      "Ep= 125, score=  2.708 (best= 45.090) pos=-0.0 0.0 0.0\n",
      "Ep= 126, score=  2.708 (best= 45.090) pos=-0.0 0.0 0.0\n",
      "Ep= 127, score=  2.708 (best= 45.090) pos=-0.0 -0.0 0.0\n",
      "Ep= 128, score= -3.296 (best= 45.090) pos=-0.03 -0.0 0.0\n",
      "Ep= 129, score=  2.708 (best= 45.090) pos=0.0 0.0 0.0\n",
      "Ep= 130, score=  2.708 (best= 45.090) pos=-0.0 -0.0 0.0\n",
      "Ep= 131, score= -3.275 (best= 45.090) pos=-0.01 0.02 0.0\n",
      "Ep= 132, score=  2.708 (best= 45.090) pos=-0.0 -0.0 0.0\n",
      "Ep= 133, score= -3.255 (best= 45.090) pos=0.0 0.02 0.0\n",
      "Ep= 134, score=  2.708 (best= 45.090) pos=0.0 0.0 0.0\n",
      "Ep= 135, score= -3.277 (best= 45.090) pos=-0.01 0.02 0.0\n",
      "Ep= 136, score= -3.249 (best= 45.090) pos=-0.0 -0.01 0.0\n",
      "Ep= 137, score=  2.708 (best= 45.090) pos=0.0 0.0 0.0\n",
      "Ep= 138, score=  2.708 (best= 45.090) pos=-0.0 0.0 0.0\n",
      "Ep= 139, score=  2.708 (best= 45.090) pos=-0.0 0.0 0.0\n",
      "Ep= 140, score=  2.708 (best= 45.090) pos=0.0 -0.0 0.0\n",
      "Ep= 141, score=  2.709 (best= 45.090) pos=0.0 -0.0 0.0\n",
      "Ep= 142, score=  2.708 (best= 45.090) pos=-0.0 0.0 0.0\n",
      "Ep= 143, score=  2.708 (best= 45.090) pos=-0.0 -0.0 0.0\n",
      "Ep= 144, score= -3.307 (best= 45.090) pos=-0.0 -0.03 0.0\n"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "Ep= 145, score=  2.708 (best= 45.090) pos=-0.0 -0.0 0.0\n",
      "Ep= 146, score= -3.263 (best= 45.090) pos=0.01 0.03 0.0\n",
      "Ep= 147, score= -3.296 (best= 45.090) pos=-0.01 -0.01 0.0\n",
      "Ep= 148, score=  2.708 (best= 45.090) pos=-0.0 0.0 0.0\n",
      "Ep= 149, score=  2.708 (best= 45.090) pos=-0.0 0.0 0.0\n",
      "Ep= 150, score=  2.711 (best= 45.090) pos=0.0 -0.01 0.0\n",
      "Ep= 151, score=  2.708 (best= 45.090) pos=-0.0 0.0 0.0\n",
      "Ep= 152, score= -3.244 (best= 45.090) pos=-0.01 -0.02 0.0\n",
      "Ep= 153, score= -3.293 (best= 45.090) pos=0.01 0.02 0.0\n",
      "Ep= 154, score= -3.324 (best= 45.090) pos=0.06 0.03 0.0\n",
      "Ep= 155, score= -3.288 (best= 45.090) pos=-0.0 -0.0 0.0\n",
      "Ep= 156, score= -3.296 (best= 45.090) pos=0.01 -0.01 0.0\n",
      "Ep= 157, score= -3.292 (best= 45.090) pos=-0.01 -0.01 0.0\n",
      "Ep= 158, score= -3.276 (best= 45.090) pos=0.01 -0.02 0.0\n",
      "Ep= 159, score= -3.247 (best= 45.090) pos=0.03 -0.02 0.0\n",
      "Ep= 160, score= -3.228 (best= 45.090) pos=0.02 -0.02 0.0\n",
      "Ep= 161, score= -3.173 (best= 45.090) pos=0.01 0.0 0.0\n",
      "Ep= 162, score= -3.219 (best= 45.090) pos=-0.01 -0.01 0.0\n",
      "Ep= 163, score= -3.204 (best= 45.090) pos=-0.04 -0.05 0.0\n",
      "Ep= 164, score= -2.228 (best= 45.090) pos=-0.06 0.02 0.0\n",
      "Ep= 165, score= -3.260 (best= 45.090) pos=-0.05 -0.03 0.0\n",
      "Ep= 166, score= -2.412 (best= 45.090) pos=0.01 -0.09 0.0\n",
      "Ep= 167, score= -2.011 (best= 45.090) pos=0.14 0.1 0.0\n",
      "Ep= 168, score= -2.729 (best= 45.090) pos=-0.0 -0.07 0.0\n",
      "Ep= 169, score= -2.873 (best= 45.090) pos=-0.06 0.0 0.0\n",
      "Ep= 170, score= -2.537 (best= 45.090) pos=-0.06 0.11 0.0\n",
      "Ep= 171, score= -2.276 (best= 45.090) pos=-0.01 0.03 0.0\n",
      "Ep= 172, score= -2.881 (best= 45.090) pos=-0.02 0.1 0.0\n",
      "Ep= 173, score=  2.686 (best= 45.090) pos=-0.0 0.01 0.0\n",
      "Ep= 174, score=  2.700 (best= 45.090) pos=0.03 0.0 0.0\n",
      "Ep= 175, score= -7.512 (best= 45.090) pos=-0.18 -0.04 0.0\n",
      "Ep= 176, score= -2.178 (best= 45.090) pos=0.11 0.0 0.0\n",
      "Ep= 177, score= -2.504 (best= 45.090) pos=0.07 0.0 0.0\n",
      "Ep= 178, score=  2.708 (best= 45.090) pos=-0.0 0.0 0.0\n",
      "Ep= 179, score= -2.436 (best= 45.090) pos=0.17 -0.0 0.0\n",
      "Ep= 180, score= -2.626 (best= 45.090) pos=0.16 0.0 0.0\n",
      "Ep= 181, score= -2.657 (best= 45.090) pos=0.05 0.01 0.0\n",
      "Ep= 182, score= -3.427 (best= 45.090) pos=0.2 0.0 0.0\n",
      "Ep= 183, score=  2.708 (best= 45.090) pos=-0.0 0.0 0.0\n",
      "Ep= 184, score= -2.263 (best= 45.090) pos=0.02 0.0 0.0\n",
      "Ep= 185, score= -2.025 (best= 45.090) pos=0.15 -0.0 0.0\n",
      "Ep= 186, score= -2.445 (best= 45.090) pos=0.17 -0.0 0.0\n",
      "Ep= 187, score= -2.218 (best= 45.090) pos=-0.11 -0.0 0.0\n",
      "Ep= 188, score= -7.143 (best= 45.090) pos=0.03 -0.0 0.0\n",
      "Ep= 189, score= -2.603 (best= 45.090) pos=0.07 -0.02 0.0\n",
      "Ep= 190, score= -2.187 (best= 45.090) pos=0.14 0.0 0.0\n",
      "Ep= 191, score= -3.391 (best= 45.090) pos=0.17 0.0 0.0\n",
      "Ep= 192, score= -2.509 (best= 45.090) pos=0.03 0.01 0.0\n",
      "Ep= 193, score= -2.453 (best= 45.090) pos=0.12 -0.0 0.0\n",
      "Ep= 194, score= -6.848 (best= 45.090) pos=0.11 -0.0 0.0\n",
      "Ep= 195, score= -2.511 (best= 45.090) pos=0.03 0.01 0.0\n",
      "Ep= 196, score= -2.570 (best= 45.090) pos=0.02 0.01 0.0\n",
      "Ep= 197, score= -3.385 (best= 45.090) pos=0.12 0.0 0.0\n",
      "Ep= 198, score= -7.217 (best= 45.090) pos=-0.2 0.0 0.0\n",
      "Ep= 199, score= -3.361 (best= 45.090) pos=0.19 0.0 0.0\n",
      "Ep= 200, score= -2.479 (best= 45.090) pos=-0.23 0.0 0.0\n",
      "Ep= 201, score= -3.323 (best= 45.090) pos=-0.05 0.01 0.0\n",
      "Ep= 202, score=  2.708 (best= 45.090) pos=-0.0 0.0 0.0\n",
      "Ep= 203, score= -2.329 (best= 45.090) pos=0.19 0.0 0.0\n",
      "Ep= 204, score= -2.502 (best= 45.090) pos=0.04 0.07 0.0\n",
      "Ep= 205, score= -2.478 (best= 45.090) pos=0.17 0.0 0.0\n",
      "Ep= 206, score=  2.708 (best= 45.090) pos=-0.0 0.0 0.0\n",
      "Ep= 207, score= -7.203 (best= 45.090) pos=0.05 -0.0 0.0\n",
      "Ep= 208, score= -3.193 (best= 45.090) pos=-0.19 0.14 0.0\n",
      "Ep= 209, score= -6.957 (best= 45.090) pos=-0.03 -0.0 0.0\n",
      "Ep= 210, score= -6.977 (best= 45.090) pos=-0.0 -0.0 0.0\n",
      "Ep= 211, score= -3.554 (best= 45.090) pos=-0.31 -0.04 0.0\n",
      "Ep= 212, score=  2.708 (best= 45.090) pos=-0.0 0.0 0.0\n",
      "Ep= 213, score= -1.139 (best= 45.090) pos=0.06 0.0 0.0\n",
      "Ep= 214, score= -7.094 (best= 45.090) pos=-0.17 -0.0 0.0\n",
      "Ep= 215, score=  2.708 (best= 45.090) pos=-0.0 0.0 0.0\n",
      "Ep= 216, score= -3.870 (best= 45.090) pos=-0.39 0.34 0.0\n",
      "Ep= 217, score= -2.857 (best= 45.090) pos=-0.25 -0.17 0.0\n",
      "Ep= 218, score= -3.788 (best= 45.090) pos=0.47 -0.03 0.0\n",
      "Ep= 219, score= -3.387 (best= 45.090) pos=-0.58 -0.16 0.0\n",
      "Ep= 220, score= -3.474 (best= 45.090) pos=-0.19 0.07 0.0\n",
      "Ep= 221, score= -8.642 (best= 45.090) pos=0.27 -0.46 0.0\n",
      "Ep= 222, score= -2.713 (best= 45.090) pos=-0.05 -0.11 0.0\n",
      "Ep= 223, score=-24.879 (best= 45.090) pos=-1.73 -0.86 0.0\n",
      "Ep= 224, score=-10.061 (best= 45.090) pos=0.44 0.56 0.0\n",
      "Ep= 225, score= -3.099 (best= 45.090) pos=-0.42 -0.05 0.0\n",
      "Ep= 226, score= -2.404 (best= 45.090) pos=0.17 -0.0 0.0\n",
      "Ep= 227, score= -3.015 (best= 45.090) pos=-0.4 0.03 0.0\n",
      "Ep= 228, score= -2.247 (best= 45.090) pos=0.17 -0.0 0.0\n",
      "Ep= 229, score= -2.339 (best= 45.090) pos=0.17 -0.0 0.0\n",
      "Ep= 230, score= -3.126 (best= 45.090) pos=0.08 0.0 0.0\n",
      "Ep= 231, score= -2.581 (best= 45.090) pos=-0.14 0.18 0.0\n",
      "Ep= 232, score=  2.708 (best= 45.090) pos=-0.0 0.0 0.0\n",
      "Ep= 233, score= -2.517 (best= 45.090) pos=-0.02 -0.07 0.0\n",
      "Ep= 234, score= -2.540 (best= 45.090) pos=0.16 -0.0 0.0\n",
      "Ep= 235, score= -1.697 (best= 45.090) pos=-0.02 -0.0 0.0\n",
      "Ep= 236, score= -2.547 (best= 45.090) pos=0.16 -0.0 0.0\n",
      "Ep= 237, score= -2.554 (best= 45.090) pos=0.16 -0.0 0.0\n",
      "Ep= 238, score= -2.807 (best= 45.090) pos=-0.47 0.09 0.0\n",
      "Ep= 239, score= -2.722 (best= 45.090) pos=-0.31 0.0 0.0\n",
      "Ep= 240, score= -2.901 (best= 45.090) pos=-0.34 0.03 0.0\n",
      "Ep= 241, score= -3.495 (best= 45.090) pos=-0.42 0.21 0.0\n",
      "Ep= 242, score= -2.486 (best= 45.090) pos=0.17 -0.0 0.0\n",
      "Ep= 243, score= -3.103 (best= 45.090) pos=-0.28 0.01 0.0\n",
      "Ep= 244, score= -1.610 (best= 45.090) pos=-0.01 0.03 0.0\n",
      "Ep= 245, score= -3.181 (best= 45.090) pos=-0.3 0.06 0.0\n",
      "Ep= 246, score= -2.565 (best= 45.090) pos=0.16 -0.0 0.0\n",
      "Ep= 247, score= -2.546 (best= 45.090) pos=0.16 -0.0 0.0\n",
      "Ep= 248, score= -2.962 (best= 45.090) pos=-0.29 0.03 0.0\n",
      "Ep= 249, score= -2.998 (best= 45.090) pos=-0.27 0.08 0.0\n",
      "Ep= 250, score= -2.982 (best= 45.090) pos=-0.29 0.06 0.0\n",
      "Ep= 251, score= -3.048 (best= 45.090) pos=-0.28 -0.04 0.0\n",
      "Ep= 252, score=  2.708 (best= 45.090) pos=-0.0 0.0 0.0\n",
      "Ep= 253, score= -3.246 (best= 45.090) pos=-0.33 0.11 0.0\n",
      "Ep= 254, score=  2.708 (best= 45.090) pos=-0.0 0.0 0.0\n",
      "Ep= 255, score= -2.990 (best= 45.090) pos=-0.27 0.04 0.0\n",
      "Ep= 256, score= -3.177 (best= 45.090) pos=-0.34 0.13 0.0\n",
      "Ep= 257, score= -2.519 (best= 45.090) pos=0.16 -0.0 0.0\n",
      "Ep= 258, score= -2.272 (best= 45.090) pos=0.17 -0.0 0.0\n",
      "Ep= 259, score= -2.691 (best= 45.090) pos=-0.04 0.04 0.0\n",
      "Ep= 260, score= -2.882 (best= 45.090) pos=-0.08 0.0 0.0\n",
      "Ep= 261, score= -6.415 (best= 45.090) pos=-0.06 -0.0 0.0\n",
      "Ep= 262, score= -2.051 (best= 45.090) pos=-0.09 0.0 0.0\n",
      "Ep= 263, score= -2.717 (best= 45.090) pos=0.12 -0.08 0.0\n",
      "Ep= 264, score= -3.642 (best= 45.090) pos=-0.21 -0.13 0.0\n",
      "Ep= 265, score=-10.158 (best= 45.090) pos=-0.31 0.49 0.0\n",
      "Ep= 266, score=-25.262 (best= 45.090) pos=-1.02 1.17 0.0\n",
      "Ep= 267, score=  2.708 (best= 45.090) pos=-0.0 -0.0 0.0\n",
      "Ep= 268, score= -3.301 (best= 45.090) pos=-0.04 0.0 0.0\n",
      "Ep= 269, score=  2.708 (best= 45.090) pos=-0.0 0.0 0.0\n",
      "Ep= 270, score=  2.709 (best= 45.090) pos=0.0 0.0 0.0\n",
      "Ep= 271, score=  2.708 (best= 45.090) pos=-0.0 0.0 0.0\n",
      "Ep= 272, score= -3.277 (best= 45.090) pos=0.04 -0.0 0.0\n",
      "Ep= 273, score=  2.708 (best= 45.090) pos=-0.0 0.0 0.0\n",
      "Ep= 274, score=  2.708 (best= 45.090) pos=-0.0 0.0 0.0\n",
      "Ep= 275, score=  2.708 (best= 45.090) pos=0.0 -0.0 0.0\n",
      "Ep= 276, score=  2.708 (best= 45.090) pos=-0.0 0.0 0.0\n",
      "Ep= 277, score=  2.708 (best= 45.090) pos=-0.0 0.0 0.0\n",
      "Ep= 278, score= -3.253 (best= 45.090) pos=-0.0 -0.0 0.0\n",
      "Ep= 279, score=  2.708 (best= 45.090) pos=-0.0 -0.0 0.0\n",
      "Ep= 280, score=  2.708 (best= 45.090) pos=-0.0 0.0 0.0\n",
      "Ep= 281, score=  2.708 (best= 45.090) pos=-0.0 0.0 0.0\n",
      "Ep= 282, score=  2.708 (best= 45.090) pos=-0.0 -0.0 0.0\n",
      "Ep= 283, score=  2.708 (best= 45.090) pos=-0.0 -0.0 0.0\n",
      "Ep= 284, score=  2.708 (best= 45.090) pos=0.0 0.0 0.0\n",
      "Ep= 285, score=  2.708 (best= 45.090) pos=-0.0 -0.0 0.0\n",
      "Ep= 286, score=  2.708 (best= 45.090) pos=-0.0 0.0 0.0\n",
      "Ep= 287, score=  2.708 (best= 45.090) pos=-0.0 0.0 0.0\n",
      "Ep= 288, score=  2.708 (best= 45.090) pos=-0.0 0.0 0.0\n",
      "Ep= 289, score=  2.708 (best= 45.090) pos=0.0 0.0 0.0\n"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "Ep= 290, score=  2.708 (best= 45.090) pos=0.0 0.0 0.0\n",
      "Ep= 291, score=  2.708 (best= 45.090) pos=-0.0 0.0 0.0\n",
      "Ep= 292, score= -3.246 (best= 45.090) pos=-0.04 0.01 0.0\n",
      "Ep= 293, score=  2.708 (best= 45.090) pos=-0.0 -0.0 0.0\n",
      "Ep= 294, score= -3.234 (best= 45.090) pos=-0.03 0.0 0.0\n",
      "Ep= 295, score= -3.210 (best= 45.090) pos=-0.03 0.0 0.0\n",
      "Ep= 296, score=  2.708 (best= 45.090) pos=0.0 0.0 0.0\n",
      "Ep= 297, score=  2.708 (best= 45.090) pos=-0.0 0.0 0.0\n",
      "Ep= 298, score= -3.195 (best= 45.090) pos=0.02 0.0 0.0\n",
      "Ep= 299, score=  2.708 (best= 45.090) pos=-0.0 0.0 0.0\n",
      "Ep= 300, score=  2.708 (best= 45.090) pos=-0.0 0.0 0.0\n",
      "Ep= 301, score=  2.708 (best= 45.090) pos=-0.0 0.0 0.0\n",
      "Ep= 302, score=  2.708 (best= 45.090) pos=-0.0 -0.0 0.0\n",
      "Ep= 303, score=  2.708 (best= 45.090) pos=-0.0 0.0 0.0\n",
      "Ep= 304, score=  2.709 (best= 45.090) pos=0.0 -0.0 0.0\n",
      "Ep= 305, score=  2.708 (best= 45.090) pos=0.0 0.0 0.0\n",
      "Ep= 306, score=  2.708 (best= 45.090) pos=-0.0 0.0 0.0\n",
      "Ep= 307, score=  2.708 (best= 45.090) pos=-0.0 -0.0 0.0\n",
      "Ep= 308, score=  2.708 (best= 45.090) pos=-0.0 -0.0 0.0\n",
      "Ep= 309, score= -3.167 (best= 45.090) pos=0.04 -0.0 0.0\n",
      "Ep= 310, score=  2.708 (best= 45.090) pos=-0.0 -0.0 0.0\n",
      "Ep= 311, score=  2.708 (best= 45.090) pos=-0.0 0.0 0.0\n",
      "Ep= 312, score= -3.241 (best= 45.090) pos=0.06 -0.0 0.0\n",
      "Ep= 313, score= -3.220 (best= 45.090) pos=0.03 0.0 0.0\n",
      "Ep= 314, score=  2.708 (best= 45.090) pos=-0.0 0.0 0.0\n",
      "Ep= 315, score= -3.205 (best= 45.090) pos=0.01 -0.01 0.0\n",
      "Ep= 316, score=  2.708 (best= 45.090) pos=-0.0 0.0 0.0\n",
      "Ep= 317, score= -3.170 (best= 45.090) pos=0.04 -0.0 0.0\n",
      "Ep= 318, score= -3.114 (best= 45.090) pos=-0.02 -0.0 0.0\n",
      "Ep= 319, score=  2.708 (best= 45.090) pos=-0.0 0.0 0.0\n",
      "Ep= 320, score=  2.708 (best= 45.090) pos=-0.0 0.0 0.0\n",
      "Ep= 321, score=  2.708 (best= 45.090) pos=0.0 0.0 0.0\n",
      "Ep= 322, score=  2.709 (best= 45.090) pos=-0.0 0.0 0.0\n",
      "Ep= 323, score= -3.088 (best= 45.090) pos=0.01 -0.0 0.0\n",
      "Ep= 324, score= -3.096 (best= 45.090) pos=-0.01 -0.0 0.0\n",
      "Ep= 325, score=  2.708 (best= 45.090) pos=-0.0 -0.0 0.0\n",
      "Ep= 326, score=  2.708 (best= 45.090) pos=-0.0 -0.0 0.0\n",
      "Ep= 327, score=  2.708 (best= 45.090) pos=-0.0 -0.0 0.0\n",
      "Ep= 328, score=  2.708 (best= 45.090) pos=-0.0 0.0 0.0\n",
      "Ep= 329, score= -3.089 (best= 45.090) pos=0.02 -0.0 0.0\n",
      "Ep= 330, score=  2.708 (best= 45.090) pos=0.0 0.0 0.0\n",
      "Ep= 331, score=  2.708 (best= 45.090) pos=-0.0 0.0 0.0\n",
      "Ep= 332, score=  2.708 (best= 45.090) pos=-0.0 0.0 0.0\n",
      "Ep= 333, score=  2.708 (best= 45.090) pos=0.0 0.0 0.0\n",
      "Ep= 334, score=  2.708 (best= 45.090) pos=-0.0 -0.0 0.0\n",
      "Ep= 335, score=  2.708 (best= 45.090) pos=-0.0 0.0 0.0\n",
      "Ep= 336, score= -3.078 (best= 45.090) pos=0.1 -0.0 0.0\n",
      "Ep= 337, score=  2.708 (best= 45.090) pos=-0.0 0.0 0.0\n",
      "Ep= 338, score=  2.708 (best= 45.090) pos=-0.0 0.0 0.0\n",
      "Ep= 339, score=  2.708 (best= 45.090) pos=0.0 0.0 0.0\n",
      "Ep= 340, score=  2.708 (best= 45.090) pos=-0.0 -0.0 0.0\n",
      "Ep= 341, score=  2.708 (best= 45.090) pos=0.0 0.0 0.0\n",
      "Ep= 342, score=  2.708 (best= 45.090) pos=-0.0 0.0 0.0\n",
      "Ep= 343, score= -3.284 (best= 45.090) pos=-0.0 -0.0 0.0\n",
      "Ep= 344, score= -3.279 (best= 45.090) pos=0.01 -0.0 0.0\n",
      "Ep= 345, score=  2.708 (best= 45.090) pos=-0.0 -0.0 0.0\n",
      "Ep= 346, score=  2.708 (best= 45.090) pos=-0.0 -0.0 0.0\n",
      "Ep= 347, score=  2.708 (best= 45.090) pos=-0.0 0.0 0.0\n",
      "Ep= 348, score= -3.227 (best= 45.090) pos=-0.01 -0.0 0.0\n",
      "Ep= 349, score=  2.708 (best= 45.090) pos=0.0 -0.0 0.0\n",
      "Ep= 350, score=  2.708 (best= 45.090) pos=0.0 0.0 0.0\n",
      "Ep= 351, score=  2.708 (best= 45.090) pos=-0.0 -0.0 0.0\n",
      "Ep= 352, score=  2.708 (best= 45.090) pos=0.0 0.0 0.0\n",
      "Ep= 353, score=  2.708 (best= 45.090) pos=0.0 -0.0 0.0\n",
      "Ep= 354, score=  2.708 (best= 45.090) pos=0.0 -0.0 0.0\n",
      "Ep= 355, score=  2.708 (best= 45.090) pos=-0.0 -0.0 0.0\n",
      "Ep= 356, score=  2.708 (best= 45.090) pos=-0.0 -0.0 0.0\n",
      "Ep= 357, score=  2.708 (best= 45.090) pos=-0.0 0.0 0.0\n",
      "Ep= 358, score=  2.708 (best= 45.090) pos=0.0 0.0 0.0\n",
      "Ep= 359, score=  2.708 (best= 45.090) pos=-0.0 0.0 0.0\n",
      "Ep= 360, score=  2.709 (best= 45.090) pos=0.0 0.0 0.0\n",
      "Ep= 361, score= -3.025 (best= 45.090) pos=-0.02 -0.0 0.0\n",
      "Ep= 362, score= -2.392 (best= 45.090) pos=-0.18 -0.0 0.0\n",
      "Ep= 363, score=  2.709 (best= 45.090) pos=-0.0 0.0 0.0\n",
      "Ep= 364, score=  2.708 (best= 45.090) pos=0.0 0.0 0.0\n",
      "Ep= 365, score=  2.708 (best= 45.090) pos=0.0 0.0 0.0\n",
      "Ep= 366, score= -6.968 (best= 45.090) pos=0.89 -0.0 0.0\n",
      "Ep= 367, score= -3.264 (best= 45.090) pos=0.11 -0.0 0.0\n",
      "Ep= 368, score= -3.252 (best= 45.090) pos=-0.01 0.0 0.0\n",
      "Ep= 369, score= -1.558 (best= 45.090) pos=-0.09 -0.0 0.0\n",
      "Ep= 370, score= -7.660 (best= 45.090) pos=-0.16 -0.0 0.0\n",
      "Ep= 371, score= -7.169 (best= 45.090) pos=0.62 0.0 0.0\n",
      "Ep= 372, score= -3.737 (best= 45.090) pos=0.13 -0.0 0.0\n",
      "Ep= 373, score= -2.115 (best= 45.090) pos=0.2 0.0 0.0\n",
      "Ep= 374, score=-15.000 (best= 45.090) pos=1.63 -0.0 0.0\n",
      "Ep= 375, score=-11.329 (best= 45.090) pos=0.74 -0.0 0.0\n",
      "Ep= 376, score=-15.259 (best= 45.090) pos=1.33 -0.0 0.0\n",
      "Ep= 377, score=-20.882 (best= 45.090) pos=2.61 0.0 0.0\n",
      "Ep= 378, score=-11.391 (best= 45.090) pos=-1.03 0.0 0.0\n",
      "Ep= 379, score=-11.208 (best= 45.090) pos=-1.48 0.0 0.0\n",
      "Ep= 380, score=-10.913 (best= 45.090) pos=-1.46 -0.0 0.0\n",
      "Ep= 381, score=-16.161 (best= 45.090) pos=-1.74 0.0 0.0\n",
      "Ep= 382, score=-16.254 (best= 45.090) pos=-1.75 0.0 0.0\n",
      "Ep= 383, score= -5.929 (best= 45.090) pos=-0.84 0.0 0.0\n",
      "Ep= 384, score=-17.278 (best= 45.090) pos=1.8 0.0 0.0\n",
      "Ep= 385, score= -8.368 (best= 45.090) pos=0.85 0.0 0.0\n",
      "Ep= 386, score=-12.304 (best= 45.090) pos=-0.71 -0.0 0.0\n",
      "Ep= 387, score=-22.743 (best= 45.090) pos=-2.03 0.0 0.0\n",
      "Ep= 388, score=-89.127 (best= 45.090) pos=-6.69 -0.69 0.0\n",
      "Ep= 389, score= -3.122 (best= 45.090) pos=0.03 -0.0 0.0\n",
      "Ep= 390, score=  2.708 (best= 45.090) pos=-0.0 0.0 0.0\n",
      "Ep= 391, score= -2.656 (best= 45.090) pos=-0.01 -0.0 0.0\n",
      "Ep= 392, score=  2.708 (best= 45.090) pos=0.0 0.0 0.0\n",
      "Ep= 393, score=  2.708 (best= 45.090) pos=0.0 0.0 0.0\n",
      "Ep= 394, score= -4.379 (best= 45.090) pos=0.1 -0.0 0.0\n",
      "Ep= 395, score= -5.436 (best= 45.090) pos=0.02 -0.0 0.0\n",
      "Ep= 396, score= -9.499 (best= 45.090) pos=-0.17 -0.0 0.0\n",
      "Ep= 397, score= -1.832 (best= 45.090) pos=0.18 -0.0 0.0\n",
      "Ep= 398, score= -7.235 (best= 45.090) pos=0.23 -0.0 0.0\n",
      "Ep= 399, score=  2.708 (best= 45.090) pos=0.0 0.0 0.0\n",
      "Ep= 400, score= -6.947 (best= 45.090) pos=0.23 0.0 0.0"
     ]
    }
   ],
   "source": [
    "## TODO: Train your agent here.\n",
    "import sys\n",
    "import pandas as pd\n",
    "from agents.agent import DDPG\n",
    "from task import Task\n",
    "import random\n",
    "import tensorflow as tf\n",
    "from collections import deque\n",
    "\n",
    "num_episodes = 400\n",
    "target_pos = np.array([0., 0., 10.])\n",
    "task = Task(target_pos=target_pos)\n",
    "agent = DDPG(task)\n",
    "batch_size = 32\n",
    "\n",
    "\n",
    "best_total_reward = 0\n",
    "reward_labels = ['episode', 'reward']\n",
    "reward_results = {x : [] for x in reward_labels}\n",
    "for i_episode in range(1, num_episodes+1):\n",
    "    state = agent.reset_episode() # start a new episode\n",
    "    total_reward = 0\n",
    "    while True:\n",
    "        action = agent.act(state) \n",
    "        next_state, reward, done = task.step(action)\n",
    "        agent.step(action=rotor_speeds, reward=reward, next_state=next_state, done=done)\n",
    "        total_reward += reward\n",
    "        if total_reward > best_total_reward:\n",
    "            best_total_reward = total_reward\n",
    "        #agent.remember(state, action, reward, next_state, done)\n",
    "        state = next_state\n",
    "        if done:\n",
    "            #rewards.append(agent.score)\n",
    "            print(\"\\r\\nEp={:4d}, score={:7.3f} (best={:7.3f}) pos={} {} {}\".format(\n",
    "                i_episode,\n",
    "                total_reward,\n",
    "                best_total_reward,\n",
    "                round(task.sim.pose[:3][0],2),\n",
    "                round(task.sim.pose[:3][1],2),\n",
    "                round(task.sim.pose[:3][2],2)), end=\"\")  # [debug]\n",
    "            break\n",
    "#         if len(agent.memory) > batch_size:\n",
    "#             agent.replay(batch_size)\n",
    "    reward_results['episode'].append(i_episode)\n",
    "    reward_results['reward'].append(total_reward)\n",
    "    sys.stdout.flush()"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {
    "collapsed": true
   },
   "source": [
    "## Plot the Rewards\n",
    "\n",
    "Once you are satisfied with your performance, plot the episode rewards, either from a single run, or averaged over multiple runs. "
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 22,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "image/png": "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\n",
      "text/plain": [
       "<matplotlib.figure.Figure at 0x7fea2503bb70>"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    }
   ],
   "source": [
    "\n",
    "plt.plot(reward_results['episode'], reward_results['reward'], label='reward/episode')\n",
    "plt.legend()\n",
    "_ = plt.ylim()"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {
    "collapsed": true
   },
   "source": [
    "## Reflections\n",
    "\n",
    "**Question 1**: Describe the task that you specified in `task.py`.  How did you design the reward function?\n",
    "\n",
    "**Answer**:\n",
    "i was inspeired by mutiple projects in github, i desined and takeout, so the quadcopter will start at the point 0,0,0 and it should end at 0,0,10. for the reward i used this funcation:\n",
    "\n",
    "1.-.3*(abs(self.sim.pose[:3] - self.target_pos)).sum()"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "**Question 2**: Discuss your agent briefly, using the following questions as a guide:\n",
    "\n",
    "- What learning algorithm(s) did you try? What worked best for you?\n",
    "- What was your final choice of hyperparameters (such as $\\alpha$, $\\gamma$, $\\epsilon$, etc.)?\n",
    "- What neural network architecture did you use (if any)? Specify layers, sizes, activation functions, etc.\n",
    "\n",
    "**Answer**:\n",
    "I tried to use several algorithm which i failed to implement and get good result, so i used the one sugested by udacity which is DDPG and i used the same gamma epsilon and alpha that is provided, and the result is much better than anything that i tried , I used the following layers for citicts : \n",
    "\n",
    "        net_states = layers.Dense(units=64, activation='relu')(states)\n",
    "        net_states = layers.Dense(units=64, activation='relu')(net_states)\n",
    "        net_actions = layers.Dense(units=32, activation='relu')(actions)\n",
    "        net_actions = layers.Dense(units=64, activation='relu')(net_actions)\n",
    "\n",
    "        net_states = layers.BatchNormalization()(net_states)\n",
    "        net_states = layers.Activation(\"relu\")(net_states)\n",
    "        net = layers.Add()([net_states, net_actions])\n",
    "        net = layers.Activation('relu')(net)\n",
    "\n",
    "        net = layers.Activation(\"relu\")(net)\n",
    "        net = layers.Dense(units=400,kernel_regularizer=layers.regularizers.l2(1e-6))(net)\n",
    "        net = layers.BatchNormalization()(net)\n",
    "I used for the actor the following layers : \n",
    "\n",
    "        net = layers.Dense(units=32, activation='relu')(states)\n",
    "        net = layers.Dense(units=400,kernel_regularizer=layers.regularizers.l2(1e-6))(states)\n",
    "        \n",
    "        net = layers.Dense(units=64, activation='relu')(net)\n",
    "        net = layers.Dense(units=32, activation='relu')(net)\n",
    "        net = layers.BatchNormalization()(net)\n"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "**Question 3**: Using the episode rewards plot, discuss how the agent learned over time.\n",
    "\n",
    "- Was it an easy task to learn or hard?\n",
    "- Was there a gradual learning curve, or an aha moment?\n",
    "- How good was the final performance of the agent? (e.g. mean rewards over the last 10 episodes)\n",
    "\n",
    "**Answer**:\n",
    "it the begainning it was hard to know what went worng as everytime i run the plot i got diffrent result but i understood why it did happiend, and you can see clearly from the result that i got improved with more episode, it could understand that the cloesest to x to 0 the better the result. with the last episodes you can see the result is becaming steady in terms of rewards and mean."
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "**Question 4**: Briefly summarize your experience working on this project. You can use the following prompts for ideas.\n",
    "\n",
    "- What was the hardest part of the project? (e.g. getting started, plotting, specifying the task, etc.)\n",
    "- Did you find anything interesting in how the quadcopter or your agent behaved?\n",
    "\n",
    "**Answer**:\n",
    "will to be honest here, i did not like this project to the fact that i wasted multiple days trying to implments buffers and how did interact with my project from the internet and i did not notice that there is an implemention here to replay buffer. there is some part that should be implemented better. i did not know how to start, defining task was very easy and direct but the implemnetion to DDPG was not, i tried to implement Q learning from my knowledge and i could not. however once i learned how it eveything is working it became very easy. anyhow, one of the most intresting thing to me was that i noticed that even when it did learning how to reach the target there was 1/10 perest that it should try diffrent aproch to maybe get better result meaning that when x-axis was almost 0 and y-axis is almost 0 it keept trying higher number even through the score was the highest."
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "the resource that i used :\n",
    "\n",
    "    https://github.com/hamzaben86/RL-Quadcopter-Project\n",
    "    https://github.com/harshitandro/RL-Quadcopter/blob/master/Quadcopter_Project.ipynb\n",
    "    https://github.com/harshitw/Quadcopter-project-/blob/master/Quadcopter_Project.ipynb\n",
    "    "
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": []
  }
 ],
 "metadata": {
  "anaconda-cloud": {},
  "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": "3.6.3"
  }
 },
 "nbformat": 4,
 "nbformat_minor": 2
}