dqn代码 tensorflow

以下是一个DQN算法的TensorFlow代码示例：

import tensorflow as tf
import numpy as np
import gym

# 神经网络类
class DQN:
    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):
        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

        self.learn_step_counter = 0
        self.memory = np.zeros((self.memory_size, n_features * 2 + 2))
        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()
        self.sess.run(tf.global_variables_initializer())
        self.cost_his = []

    # 建立神经网络
    def build_net(self):
        self.s = tf.placeholder(tf.float32, [None, self.n_features], name='s')
        self.q_target = tf.placeholder(tf.float32, [None, self.n_actions], name='Q_target')
        with tf.variable_scope('eval_net'):
            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)
            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)

            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)

        self.s_ = tf.placeholder(tf.float32, [None, self.n_features], name='s_')
        with tf.variable_scope('target_net'):
            c_names = ['target_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)
            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)

            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

    # 记忆
    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_))
        index = self.memory_counter % self.memory_size
        self.memory[index, :] = transition
        self.memory_counter += 1

    # 选择动作
    def choose_action(self, observation):
        observation = observation[np.newaxis, :]
        if np.random.uniform() < self.epsilon:
            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

    # 学习
    def learn(self):
        if self.learn_step_counter % self.replace_target_iter == 0:
            self.sess.run(self.replace_target_op)
            print('\ntarget_params_replaced\n')

        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_eval4next = self.sess.run(
            [self.q_next, self.q_eval],
            feed_dict={
                self.s_: batch_memory[:, -self.n_features:],
                self.s: batch_memory[:, :self.n_features],
            })
        q_eval = self.sess.run(self.q_eval, {self.s: batch_memory[:, :self.n_features]})

        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)
        _, 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)

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

# 训练网络
def main():
    env = gym.make('CartPole-v0')
    env = env.unwrapped
    n_actions = env.action_space.n
    n_features = env.observation_space.shape[0]

    dqn = DQN(n_actions=n_actions, n_features=n_features, learning_rate=0.01, reward_decay=0.9, e_greedy=0.9, replace_target_iter=100, memory_size=2000, e_greedy_increment=0.001, )

    for i_episode in range(400):
        observation = env.reset()
        ep_r = 0
        while True:
            env.render()
            action = dqn.choose_action(observation)

            observation_, reward, done, info = env.step(action)

            x, x_dot, theta, theta_dot = observation_
            r1 = (env.x_threshold - abs(x)) / env.x_threshold - 0.8
            r2 = (env.theta_threshold_radians - abs(theta)) / env.theta_threshold_radians - 0.5
            reward = r1 + r2

            dqn.store_transition(observation, action, reward, observation_)

            ep_r += reward
            if dqn.memory_counter > dqn.memory_size:
                dqn.learn()
                if done:
                    print('episode: ', i_episode, 'ep_r: ', round(ep_r, 2), ' epsilon: ', round(dqn.epsilon, 2))
            if done:
                break
            observation = observation_

    print('game over')
    env.close()

if __name__ == '__main__':
    main()

这个代码演示了如何使用DQN算法来解决CartPole-v0游戏。在代码中，定义了一个DQN类，其中包含了神经网络的构建，记忆的存储，动作的选择和学习。在主函数中，创建了CartPole-v0环境，并使用DQN算法进行训练。