Ubuntu安装Pyenv+Anaconda2+PyCharm+OpenAI-gym+Cuda+TensorFlow (四)

八. 测试

1. 测试Cuda
  该部分主要参考南墙已破简书中的cuda测试内容
  在/home/gh目录下下载cuda测试集源代码:

$ cuda-install-samples-8.0.sh ~

这里写图片描述

  进入到这个文件夹进行编译:

$ cd ~/NVIDIA_CUDA-8.0_Samples
$ make

  编译完成后运行deviceQuery.py和bandwidthTest.py两个脚本:

Ubuntu安装Pyenv+Anaconda2+PyCharm+OpenAI-gym+Cuda+TensorFlow (四)_第1张图片
这里写图片描述

可以看到已经检测到显卡Device 0: “GeForce GT 650m”,并且最后一行运行结果Result = PASS。
  这里我刚安完cuda和cuDNN之后进行测试同样遇到了脚本运行失败的结果,关于这个问题博主南墙已破给出了重启的解决方案,我是直接注销了下,然后再回来也行。

2. 测试TensorFlow和gym
  打开PyCharm,新建一个叫做test的工程,python解释器选择anaconda下带有tensorflow环境的那个:

Ubuntu安装Pyenv+Anaconda2+PyCharm+OpenAI-gym+Cuda+TensorFlow (四)_第2张图片

  在PyCharm编辑栏File中选择Settings——Project:test——Project Interpreter,在右侧可以看到在这个python解释器下已经安装了的所有功能包,我们可以看到gym和tensorflow都已经安装在了这个tensorflow的虚拟环境中,此外还有很多其它常用的功能包。

Ubuntu安装Pyenv+Anaconda2+PyCharm+OpenAI-gym+Cuda+TensorFlow (四)_第3张图片
Ubuntu安装Pyenv+Anaconda2+PyCharm+OpenAI-gym+Cuda+TensorFlow (四)_第4张图片

至此,可以确定gym和tensorflow安装无误。

3. 跑一个DQN的例子
  该部分代码全部来自于知乎专栏—智能单元中Flood Sung的150行代码实现DQN算法,这个专栏对深度学习和增强学习有不少不错的科普贴,这里安利一下:P
  在上面的新建工程test下,新建一个python脚本dqn,复制如下代码:

#!/usr/bin/env python    # encoding: utf-8  

""" 
    @author: GH
    @contact: [email protected] 
    @file: dqn.py 
    @time: 16-12-28 下午3:32 
    """


import gym
import tensorflow as tf
import numpy as np
import random
from collections import deque

# Hyper Parameters for DQN
GAMMA = 0.9 # discount factor for target Q
INITIAL_EPSILON = 0.5 # starting value of epsilon
FINAL_EPSILON = 0.01 # final value of epsilon
REPLAY_SIZE = 10000 # experience replay buffer size
BATCH_SIZE = 32 # size of minibatch

class DQN():
  # DQN Agent
  def __init__(self, env):
    # init experience replay
    self.replay_buffer = deque()
    # init some parameters
    self.time_step = 0
    self.epsilon = INITIAL_EPSILON
    self.state_dim = env.observation_space.shape[0]
    self.action_dim = env.action_space.n

    self.create_Q_network()
    self.create_training_method()

    # Init session
    self.session = tf.InteractiveSession()
    self.session.run(tf.initialize_all_variables())

  def create_Q_network(self):
    # network weights
    W1 = self.weight_variable([self.state_dim,20])
    b1 = self.bias_variable([20])
    W2 = self.weight_variable([20,self.action_dim])
    b2 = self.bias_variable([self.action_dim])
    # input layer
    self.state_input = tf.placeholder("float",[None,self.state_dim])
    # hidden layers
    h_layer = tf.nn.relu(tf.matmul(self.state_input,W1) + b1)
    # Q Value layer
    self.Q_value = tf.matmul(h_layer,W2) + b2

  def create_training_method(self):
    self.action_input = tf.placeholder("float",[None,self.action_dim]) # one hot presentation
    self.y_input = tf.placeholder("float",[None])
    Q_action = tf.reduce_sum(tf.mul(self.Q_value,self.action_input),reduction_indices = 1)
    self.cost = tf.reduce_mean(tf.square(self.y_input - Q_action))
    self.optimizer = tf.train.AdamOptimizer(0.0001).minimize(self.cost)

  def perceive(self,state,action,reward,next_state,done):
    one_hot_action = np.zeros(self.action_dim)
    one_hot_action[action] = 1
    self.replay_buffer.append((state,one_hot_action,reward,next_state,done))
    if len(self.replay_buffer) > REPLAY_SIZE:
      self.replay_buffer.popleft()

    if len(self.replay_buffer) > BATCH_SIZE:
      self.train_Q_network()

  def train_Q_network(self):
    self.time_step += 1
    # Step 1: obtain random minibatch from replay memory
    minibatch = random.sample(self.replay_buffer,BATCH_SIZE)
    state_batch = [data[0] for data in minibatch]
    action_batch = [data[1] for data in minibatch]
    reward_batch = [data[2] for data in minibatch]
    next_state_batch = [data[3] for data in minibatch]

    # Step 2: calculate y
    y_batch = []
    Q_value_batch = self.Q_value.eval(feed_dict={self.state_input:next_state_batch})
    for i in range(0,BATCH_SIZE):
      done = minibatch[i][4]
      if done:
        y_batch.append(reward_batch[i])
      else :
        y_batch.append(reward_batch[i] + GAMMA * np.max(Q_value_batch[i]))

    self.optimizer.run(feed_dict={
      self.y_input:y_batch,
      self.action_input:action_batch,
      self.state_input:state_batch
      })

  def egreedy_action(self,state):
    Q_value = self.Q_value.eval(feed_dict = {
      self.state_input:[state]
      })[0]
    if random.random() <= self.epsilon:
      return random.randint(0,self.action_dim - 1)
    else:
      return np.argmax(Q_value)

    self.epsilon -= (INITIAL_EPSILON - FINAL_EPSILON)/10000

  def action(self,state):
    return np.argmax(self.Q_value.eval(feed_dict = {
      self.state_input:[state]
      })[0])

  def weight_variable(self,shape):
    initial = tf.truncated_normal(shape)
    return tf.Variable(initial)

  def bias_variable(self,shape):
    initial = tf.constant(0.01, shape = shape)
    return tf.Variable(initial)
# ---------------------------------------------------------
# Hyper Parameters
ENV_NAME = 'CartPole-v0'
EPISODE = 10000 # Episode limitation
STEP = 300 # Step limitation in an episode
TEST = 10 # The number of experiment test every 100 episode

def main():
  # initialize OpenAI Gym env and dqn agent
  env = gym.make(ENV_NAME)
  agent = DQN(env)

  for episode in xrange(EPISODE):
    # initialize task
    state = env.reset()
    # Train
    for step in xrange(STEP):
      action = agent.egreedy_action(state) # e-greedy action for train
      next_state,reward,done,_ = env.step(action)
      # Define reward for agent
      reward_agent = -1 if done else 0.1
      agent.perceive(state,action,reward,next_state,done)
      state = next_state
      if done:
        break
    # Test every 100 episodes
    if episode % 100 == 0:
      total_reward = 0
      for i in xrange(TEST):
        state = env.reset()
        for j in xrange(STEP):
          env.render()
          action = agent.action(state) # direct action for test
          state,reward,done,_ = env.step(action)
          total_reward += reward
          if done:
            break
      ave_reward = total_reward/TEST
      print 'episode: ',episode,'Evaluation Average Reward:',ave_reward
      if ave_reward == 200:
        break

if __name__ == '__main__':
  main()

  在PyCharm编辑栏Run条目下选择Edit Configuration,定义一个name,Scrips选择刚才新建的dqn.py,点击OK确定。
  现在按下编辑栏上绿色小三角按钮就可以运行啦!

Ubuntu安装Pyenv+Anaconda2+PyCharm+OpenAI-gym+Cuda+TensorFlow (四)_第5张图片

到此为止整个tensorflow+gym的框架就搭好啦,之后就可以自己写算法利用gym平台进行测试啦。





全文参考:
[1]. 南墙已破的简书http://www.jianshu.com/p/c89b97d052b7
[2]. TensorFlow官网https://www.tensorflow.org/get_started/os_setup#anaconda_installation
[3]. OpenAI-gym官网https://gym.openai.com/docs
[4]. 知乎专栏-智能单元https://zhuanlan.zhihu.com/intelligentunit
[5]. super的博客园http://www.cnblogs.com/super-d2/p/4725818.html


个人理解,如有错误请指出

       

(转载请注明作者和出处: http://blog.csdn.net/gh234505 未经允许请勿用于商业用途)

你可能感兴趣的:(Ubuntu)