retrain.py

def retrain(self, batch_size):
    minibatch = random.sample(self.expirience_replay, batch_size)

    for state, action, reward, next_state, terminated in minibatch:

        state = np.expand_dims(np.asarray(state).astype(np.float64), axis=0)
        next_state = np.expand_dims(np.asarray(next_state).astype(np.float64), axis=0)

        target = self.q_network.predict(state)

        if terminated:
            target[0][action] = reward
        else:
            t = self.target_network.predict(next_state)
            target[0][action] = reward + self.gamma * np.amax(t)

        self.q_network.fit(state, target, epochs=1, verbose=0)