12. Evolutionary Strategies for RL

Activity 12.01: Cart-Pole Activity

1. Import the required packages as follows:

   import gym 
   import numpy as np 
   import math 
   import tensorflow as tf
   from matplotlib import pyplot as plt
   from random import randint
   from statistics import median, mean

2. Initialize the environment and the state and action space shapes:

   env = gym.make('CartPole-v0')
   no_states = env.observation_space.shape[0]
   no_actions = env.action_space.n

3. Create a function to generate randomly selected initial network parameters:

   def initial(run_test):
       #initialize arrays
       i_w = []
       i_b = []
       h_w = []
       o_w = []
       no_input_nodes = 8
       no_hidden_nodes = 4
       
       for r in range(run_test):
           input_weight = np.random.rand(no_states...