class DQNAgent:
        def __init__(self, state_size, action_size):
            self.state_size = state_size
            self.action_size = action_size
            self.memory = deque(maxlen=2000)
            self.gamma = GAMMA
            self.epsilon = START_EPSILON
            self.epsilon_min = EPSILON_MIN
            self.epsilon_decay = EPSILON_DECAY
            self.learning_rate = LEARNING_RATE
            self.model = self.build_model()
            self.target_model = self.build_model()

        def build_model(self):
            model = Sequential()
            model.add(Dense(16, input_dim=self.state_size, activation='relu'))
            model.add(Dense(32, activation='relu'))
            model.add(Dense(self.action_size, activation='linear'))
            model.compile(loss='mse',optimizer=Adam(lr=self.learning_rate))
            return model

        def remember(self, state, action, reward, next_state, done):
            self.memory.append((state, action, reward, next_state, done))

        def act(self, state):
            if np.random.rand() <= self.epsilon:
                return random.randrange(self.action_size)
            self.model.set_weights(self.target_model.get_weights())
            act_values = self.model.predict(state)
            return np.argmax(act_values[0])

        def replay(self, batch_size):
            minibatch = random.sample(self.memory, batch_size)
            for state, action, reward, next_state, done in minibatch:
                action_t = np.argmax(self.model.predict(state)[0])
                target = reward
                if not done:
                    target = (reward + self.gamma *
                              (self.target_model.predict(next_state)[0][action_t]))
                target_f = self.target_model.predict(state)
                target_f[0][action] = target
                self.target_model.fit(state, target_f, epochs=1, verbose=0)
            if self.epsilon > self.epsilon_min:
                self.epsilon *= self.epsilon_decay