We will be using numpy, gym, matplotlib, keras, tensorflow and the keras-rl package in this segment of the exercise. Here, Tensorflow will be used as the backend for Keras. You can install these packages with pip.

import numpy as np
import gym
from keras.models import Sequential
from keras.layers import Dense, Activation, Flatten
from keras.optimizers import Adam
from rl.agents import SARSAAgent
from rl.policy import EpsGreedyQPolicy