Deep Q-Network (DQN)理解

DQN（Deep Q-Network）是深度强化学习（Deep Reinforcement Learning）的开山之作，将深度学习引入强化学习中，构建了 Perception 到 Decision 的 End-to-end 架构。DQN 最开始由 DeepMind 发表在 NIPS 2013，后来将改进的版本发表在 Nature 2015。

NIPS 2013: Playing Atari with Deep Reinforcement Learning
Nature 2015: Human-level control through deep reinforcement learning

DQN 面临着几个挑战：

深度学习需要大量带标签的训练数据；
强化学习从 scalar reward 进行学习，但是 reward 经常是 sparse, noisy, delayed；
深度学习假设样本数据是独立同分布的，但是强化学习中采样的数据是强相关的

因此，DQN 采用经验回放（Experience Replay）机制，将训练过的数据进行储存到 Replay Buffer 中，以便后续从中随机采样进行训练，好处就是：1. 数据利用率高；2. 减少连续样本的相关性，从而减小方差（variance）。

class DeepQNetwork:
def init(
self,
n_actions,
n_features,
learning_rate=0.01,
reward_decay=0.9,
e_greedy=0.9,
replace_target_iter=300,
memory_size=500,
batch_size=32,
e_greedy_increment=None,
output_graph=False,
):
self.n_actions = n_actions
self.n_features = n_features
self.lr = learning_rate
self.gamma = reward_decay
self.epsilon_max = e_greedy
self.replace_target_iter = replace_target_iter
self.memory_size = memory_size
self.batch_size = batch_size
self.epsilon_increment = e_greedy_increment
self.epsilon = 0 if e_greedy_increment is not None else self.epsilon_max

    # total learning step
    self.learn_step_counter = 0

    # initialize zero memory [s, a, r, s_]
    self.memory = np.zeros((self.memory_size, n_features * 2 + 2))

    # consist of [target_net, evaluate_net]
    self._build_net()
    t_params = tf.get_collection('target_net_params')
    e_params = tf.get_collection('eval_net_params')
    self.replace_target_op = [tf.assign(t, e) for t, e in zip(t_params, e_params)]

    self.sess = tf.Session()

    if output_graph:
        # $ tensorboard --logdir=logs
        tf.summary.FileWriter("logs/", self.sess.graph)

    self.sess.run(tf.global_variables_initializer())
    self.cost_his = []

def _build_net(self):
    # ------------------ build evaluate_net ------------------
    self.s = tf.placeholder(tf.float32, [None, self.n_features], name='s')  # input
    self.q_target = tf.placeholder(tf.float32, [None, self.n_actions], name='Q_target')  # for calculating loss
    with tf.variable_scope('eval_net'):
        # c_names(collections_names) are the collections to store variables
        c_names = ['eval_net_params', tf.GraphKeys.GLOBAL_VARIABLES] 
        n_l1 = 10
        w_initializer = tf.random_normal_initializer(0., 0.3)
        b_initializer = tf.constant_initializer(0.1)

        # first layer. collections is used later when assign to target net
        with tf.variable_scope('l1'):
            w1 = tf.get_variable('w1', [self.n_features, n_l1], initializer=w_initializer, collections=c_names)
            b1 = tf.get_variable('b1', [1, n_l1], initializer=b_initializer, collections=c_names)
            l1 = tf.nn.relu(tf.matmul(self.s, w1) + b1)

        # second layer. collections is used later when assign to target net
        with tf.variable_scope('l2'):
            w2 = tf.get_variable('w2', [n_l1, self.n_actions], initializer=w_initializer, collections=c_names)
            b2 = tf.get_variable('b2', [1, self.n_actions], initializer=b_initializer, collections=c_names)
            self.q_eval = tf.matmul(l1, w2) + b2

    with tf.variable_scope('loss'):
        self.loss = tf.reduce_mean(tf.squared_difference(self.q_target, self.q_eval))
    with tf.variable_scope('train'):
        self._train_op = tf.train.RMSPropOptimizer(self.lr).minimize(self.loss)

    # ------------------ build target_net ------------------
    self.s_ = tf.placeholder(tf.float32, [None, self.n_features], name='s_')    # input
    with tf.variable_scope('target_net'):
        # c_names(collections_names) are the collections to store variables
        c_names = ['target_net_params', tf.GraphKeys.GLOBAL_VARIABLES]

        # first layer. collections is used later when assign to target net
        with tf.variable_scope('l1'):
            w1 = tf.get_variable('w1', [self.n_features, n_l1], initializer=w_initializer, collections=c_names)
            b1 = tf.get_variable('b1', [1, n_l1], initializer=b_initializer, collections=c_names)
            l1 = tf.nn.relu(tf.matmul(self.s_, w1) + b1)

        # second layer. collections is used later when assign to target net
        with tf.variable_scope('l2'):
            w2 = tf.get_variable('w2', [n_l1, self.n_actions], initializer=w_initializer, collections=c_names)
            b2 = tf.get_variable('b2', [1, self.n_actions], initializer=b_initializer, collections=c_names)
            self.q_next = tf.matmul(l1, w2) + b2

def store_transition(self, s, a, r, s_):
    if not hasattr(self, 'memory_counter'):
        self.memory_counter = 0

    transition = np.hstack((s, [a, r], s_))

    # replace the old memory with new memory
    index = self.memory_counter % self.memory_size
    self.memory[index, :] = transition

    self.memory_counter += 1

def choose_action(self, observation):
    # to have batch dimension when feed into tf placeholder
    observation = observation[np.newaxis, :]

    if np.random.uniform() < self.epsilon:
        # forward feed the observation and get q value for every actions
        actions_value = self.sess.run(self.q_eval, feed_dict={self.s: observation})
        action = np.argmax(actions_value)
    else:
        action = np.random.randint(0, self.n_actions)
    return action

def learn(self):
    # check to replace target parameters
    if self.learn_step_counter % self.replace_target_iter == 0:
        self.sess.run(self.replace_target_op)
        print('\ntarget_params_replaced\n')

    # sample batch memory from all memory
    if self.memory_counter > self.memory_size:
        sample_index = np.random.choice(self.memory_size, size=self.batch_size)
    else:
        sample_index = np.random.choice(self.memory_counter, size=self.batch_size)
    batch_memory = self.memory[sample_index, :]

    q_next, q_eval = self.sess.run(
        [self.q_next, self.q_eval],
        feed_dict={
            self.s_: batch_memory[:, -self.n_features:],  # fixed params
            self.s: batch_memory[:, :self.n_features],  # newest params
        })

    # change q_target w.r.t q_eval's action
    q_target = q_eval.copy()

    batch_index = np.arange(self.batch_size, dtype=np.int32)
    eval_act_index = batch_memory[:, self.n_features].astype(int)
    reward = batch_memory[:, self.n_features + 1]

    q_target[batch_index, eval_act_index] = reward + self.gamma * np.max(q_next, axis=1)

    """
    For example in this batch I have 2 samples and 3 actions:
    q_eval =
    [[1, 2, 3],
     [4, 5, 6]]

    q_target = q_eval =
    [[1, 2, 3],
     [4, 5, 6]]

    Then change q_target with the real q_target value w.r.t the q_eval's action.
    For example in:
        sample 0, I took action 0, and the max q_target value is -1;
        sample 1, I took action 2, and the max q_target value is -2:
    q_target =
    [[-1, 2, 3],
     [4, 5, -2]]

    So the (q_target - q_eval) becomes:
    [[(-1)-(1), 0, 0],
     [0, 0, (-2)-(6)]]

    We then backpropagate this error w.r.t the corresponding action to network,
    leave other action as error=0 cause we didn't choose it.
    """

    # train eval network
    _, self.cost = self.sess.run([self._train_op, self.loss],
                                 feed_dict={self.s: batch_memory[:, :self.n_features],
                                            self.q_target: q_target})
    self.cost_his.append(self.cost)

    # increasing epsilon
    self.epsilon = self.epsilon + self.epsilon_increment if self.epsilon < self.epsilon_max else self.epsilon_max
    self.learn_step_counter += 1

在DQN中增强学习Q-Learning算法和深度学习的SGD训练是同步进行的！

通过Q-Learning获取无限量的训练样本，然后对神经网络进行训练。

样本的获取关键是计算y，也就是标签。