DP-Stochastic Motion.ipynb

{
 "cells": [
  {
   "cell_type": "code",
   "execution_count": 33,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "[471.9397246855924, 274.85364957758316, 161.5599867065471, 0]\n",
      "[334.05159958720344, 230.9574434590965, 183.69314862430264, 176.69517762501977]\n",
      "[398.3517867450282, 277.5898270101976, 246.09263437756917, 335.3944132514738]\n",
      "[700.1758933725141, 1000, 1000, 668.697206625737]\n",
      "['>', 'v', 'v', '*']\n",
      "['>', '>', '^', '<']\n",
      "['>', '^', '^', '<']\n",
      "['^', ' ', ' ', '^']\n"
     ]
    }
   ],
   "source": [
    "# --------------\n",
    "# USER INSTRUCTIONS\n",
    "#\n",
    "# Write a function called stochastic_value that \n",
    "# returns two grids. The first grid, value, should \n",
    "# contain the computed value of each cell as shown \n",
    "# in the video. The second grid, policy, should \n",
    "# contain the optimum policy for each cell.\n",
    "#\n",
    "# --------------\n",
    "# GRADING NOTES\n",
    "#\n",
    "# We will be calling your stochastic_value function\n",
    "# with several different grids and different values\n",
    "# of success_prob, collision_cost, and cost_step.\n",
    "# In order to be marked correct, your function must\n",
    "# RETURN (it does not have to print) two grids,\n",
    "# value and policy.\n",
    "#\n",
    "# When grading your value grid, we will compare the\n",
    "# value of each cell with the true value according\n",
    "# to this model. If your answer for each cell\n",
    "# is sufficiently close to the correct answer\n",
    "# (within 0.001), you will be marked as correct.\n",
    "\n",
    "delta = [[-1, 0 ], # go up\n",
    "         [ 0, -1], # go left\n",
    "         [ 1, 0 ], # go down\n",
    "         [ 0, 1 ]] # go right\n",
    "\n",
    "delta_name = ['^', '<', 'v', '>'] # Use these when creating your policy grid.\n",
    "\n",
    "# ---------------------------------------------\n",
    "#  Modify the function stochastic_value below\n",
    "# ---------------------------------------------\n",
    "\n",
    "def stochastic_value(grid,goal,cost_step,collision_cost,success_prob):\n",
    "    failure_prob = (1.0 - success_prob)/2.0 # Probability(stepping left) = prob(stepping right) = failure_prob\n",
    "    value = [[collision_cost for col in range(len(grid[0]))] for row in range(len(grid))]\n",
    "    policy = [[' ' for col in range(len(grid[0]))] for row in range(len(grid))]\n",
    "    change = True\n",
    "    while change:\n",
    "        change = False\n",
    "        for x in range(len(grid)):\n",
    "            for y in range(len(grid[0])):\n",
    "                if x == goal[0] and y == goal[1]:\n",
    "                    if value[x][y] > 0:     \n",
    "                        value[x][y] = 0     \n",
    "                        policy[x][y] = '*' \n",
    "                        change = True\n",
    "\n",
    "                elif grid[x][y] == 0:\n",
    "                    for i in range(len(delta)):\n",
    "                        v2 = cost_step\n",
    "                        for j in range(-1,2):\n",
    "                            adj = (i + j) % 4\n",
    "                            x2 = x + delta[adj][0]\n",
    "                            y2 = y + delta[adj][1]\n",
    "                            if j == 0:\n",
    "                                p2 = success_prob\n",
    "                            else:\n",
    "                                p2 = failure_prob\n",
    "                            if x2 >= 0 and x2 < len(grid) and y2 >=0 and y2 < len(grid[0]) and grid[x2][y2] == 0:\n",
    "                                v2 += p2 * value[x2][y2] \n",
    "                            else:\n",
    "                                v2 += p2 * collision_cost\n",
    "                        if v2 < value [x][y]:\n",
    "                            value[x][y] = v2\n",
    "                            policy[x][y] = delta_name[i]\n",
    "                            change = True\n",
    "    return value, policy\n",
    "\n",
    "# ---------------------------------------------\n",
    "#  Use the code below to test your solution\n",
    "# ---------------------------------------------\n",
    "\n",
    "grid = [[0, 0, 0, 0],\n",
    "        [0, 0, 0, 0],\n",
    "        [0, 0, 0, 0],\n",
    "        [0, 1, 1, 0]]\n",
    "goal = [0, len(grid[0])-1] # Goal is in top right corner\n",
    "cost_step = 1\n",
    "collision_cost = 1000\n",
    "success_prob = 0.5\n",
    "\n",
    "value,policy = stochastic_value(grid,goal,cost_step,collision_cost,success_prob)\n",
    "for row in range(len(value)):\n",
    "    print (value[row])\n",
    "for row in range(len(policy)):\n",
    "    print (policy[row])\n",
    "\n",
    "# Expected outputs:\n",
    "#\n",
    "#[471.9397246855924, 274.85364957758316, 161.5599867065471, 0],\n",
    "#[334.05159958720344, 230.9574434590965, 183.69314862430264, 176.69517762501977], \n",
    "#[398.3517867450282, 277.5898270101976, 246.09263437756917, 335.3944132514738], \n",
    "#[700.1758933725141, 1000, 1000, 668.697206625737]\n",
    "\n",
    "\n",
    "#\n",
    "# ['>', 'v', 'v', '*']\n",
    "# ['>', '>', '^', '<']\n",
    "# ['>', '^', '^', '<']\n",
    "# ['^', ' ', ' ', '^']\n"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": []
  }
 ],
 "metadata": {
  "kernelspec": {
   "display_name": "Python 3.9.12 ('base')",
   "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": "3.9.12"
  },
  "orig_nbformat": 4,
  "vscode": {
   "interpreter": {
    "hash": "e572caa66b9d49951af5480c4e65bd874b4d163b9e077ed4369f2912d83d117b"
   }
  }
 },
 "nbformat": 4,
 "nbformat_minor": 2
}