A true man can play a palo one hundred time

题目说明

Question Now you have a balance palo.You can move it left or right.
Just play hundred time on it.

Description Get request receive two params 1. move, 0 or 1
2. id, just your token Observation 1. pole position x
2. a value depend on x 3. pole deviate from center θ 4. a value depend on θ Why you failed θ or x > a certain value

总而言之就是个玩棒子的游戏(雾。
之所以出现在最后一道请去问关卡规则的设计者。
因为ctf本来不应该出现这种问题,所以我有意把这题设计得简单了一点,但是,ctf真是不讲道理,也导致这道题被少量非预期。

其实就是一个非常非常简单的强化学习的问题,甚至不需要强化学习去解。

DQN网络结构定义

import numpy as np
import tensorflow as tf
import requests
import math

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.train.SummaryWriter soon be deprecated, use following
            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, n_l1, w_initializer, b_initializer = \
                ['eval_net_params', tf.GraphKeys.GLOBAL_VARIABLES], 10, \
                tf.random_normal_initializer(0., 0.3), tf.constant_initializer(0.1)  # config of layers

            # 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)

        # 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

学习迭代

x_threshold = 2.4
theta_threshold_radians = 1/15*math.pi

RL = DeepQNetwork(n_actions=2,
                  n_features=4,
                  learning_rate=0.01, e_greedy=0.9,
                  replace_target_iter=100, memory_size=2000,
                  e_greedy_increment=0.001,)

total_steps = 0

for i_episode in range(100):
    json_req = requests.get(url=url, params={'id': token, 'move': 0}).json()
    observation = json_req['observation']
    ep_r = 0

    while True:
        action = RL.choose_action(np.array(observation))

        json_req = requests.get(url=url, params={'id': token, 'move': action}).json()
        try:  observation_ = json_req['observation']
        except KeyError:
            pass
        print(observation)
        done = not json_req['status']

        # the smaller theta and closer to center the better
        x, x_dot, theta, theta_dot = observation_
        r1 = (x_threshold - abs(x))/x_threshold - 0.8
        r2 = (theta_threshold_radians - abs(theta))/theta_threshold_radians - 0.5
        reward = r1 + r2

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

        ep_r += reward
        if total_steps > 1000:
            RL.learn()

        if done:
            count = json_req['count']
            if count == 100:
                print(json_req['flag'])
            else:
                print('count:', json_req['count'])
            break

        observation = observation_
        total_steps += 1

本文章首发在 网安wangan.com 网站上。

上一篇 下一篇
讨论数量: 0
只看当前版本


暂无话题~