Sathishruw

# -*- coding: utf-8 -*-
import tensorflow as tf
import threading
import numpy as np

import signal
import random
import math
import os
import time

Sathishruw

import numpy as np
from numpy.linalg import inv

x_observations = np.array([4000, 4260, 4550, 4860, 5110])
v_observations = np.array([280, 282, 285, 286, 290])

z = np.c_[x_observations, v_observations]

# Initial Conditions
a = 2  # Acceleration

Sathishruw

import gym
from gym import wrappers
import numpy as np

env = gym.make("FrozenLake-v0")
env = wrappers.Monitor(env, "./results", force=True)

Q = np.zeros([env.observation_space.n, env.action_space.n])
n_s_a = np.zeros([env.observation_space.n, env.action_space.n])

Sathishruw

import gym
import numpy 
impoort time
#Function for a random policy
def randomPolicy():
    return numpy.random.choice(4, size=((16)))
#Execution
def execute(env, policy, episode_len=100, render=False):
    reward = 0
    obs = env.reset()