NMZivkovic

def __init__(self, enviroment, optimizer):      
  # Initialize atributes
  self._state_size = enviroment.observation_space.n
  self._action_size = enviroment.action_space.n
  self._optimizer = optimizer

  self.expirience_replay = deque(maxlen=2000)

  # Initialize discount and exploration rate
  self.gamma = 0.6

NMZivkovic

class Agent:
    def __init__(self, enviroment, optimizer):
        
        # Initialize atributes
        self._state_size = enviroment.observation_space.n
        self._action_size = enviroment.action_space.n
        self._optimizer = optimizer
        
        self.expirience_replay = deque(maxlen=2000)
        

NMZivkovic

enviroment = gym.make("Taxi-v2").env
enviroment.render()

print('Number of states: {}'.format(enviroment.observation_space.n))
print('Number of actions: {}'.format(enviroment.action_space.n))

NMZivkovic

import numpy as np
import random
from IPython.display import clear_output
from collections import deque
import progressbar

import gym

from tensorflow.keras import Model, Sequential
from tensorflow.keras.layers import Dense, Embedding, Reshape

NMZivkovic

total_epochs = 0
total_penalties = 0
num_of_episodes = 100

for _ in range(num_of_episodes):
    state = enviroment.reset()
    epochs = 0
    penalties = 0
    reward = 0
    

NMZivkovic

num_of_episodes = 100000

for episode in range(0, num_of_episodes):
    # Reset the enviroment
    state = enviroment.reset()

    # Initialize variables
    reward = 0
    terminated = False
    

NMZivkovic

alpha = 0.1
gamma = 0.6
epsilon = 0.1
q_table = np.zeros([enviroment.observation_space.n, enviroment.action_space.n])

NMZivkovic

enviroment = gym.make("Taxi-v2").env
enviroment.render()

print('Number of states: {}'.format(enviroment.observation_space.n))
print('Number of actions: {}'.format(enviroment.action_space.n))

NMZivkovic

import numpy as np
import random
from IPython.display import clear_output
import gym

NMZivkovic

corrMatt = data.corr()
mask = np.array(corrMatt)
mask[np.tril_indices_from(mask)] = False
fig,ax= plt.subplots()
fig.set_size_inches(20,10)
sb.heatmap(corrMatt, cmap="Greens", mask=mask,vmax=.8, square=True,annot=True)