小编Lec*_*eNi的帖子

与此问题类似，我正在运行异步强化学习算法，并且需要在多个线程中运行模型预测以更快地获取训练数据。我的代码基于GitHub 上的DDPG-keras，其神经网络基于Keras＆Tensorflow构建。我的代码片段如下所示：

• 异步线程的创建和加入：

  for roundNo in xrange(self.param['max_round']):
      AgentPool = [AgentThread(self.getEnv(), self.actor, self.critic, eps, self.param['n_step'], self.param['gamma'])]
      for agent in AgentPool:
          agent.start()
      for agent in AgentPool:
          agent.join()
  

  Run Code Online (Sandbox Code Playgroud)

• 代理线程代码

  """Agent Thread for collecting data"""
  def __init__(self, env_, actor_, critic_, eps_, n_step_, gamma_):
      super(AgentThread, self).__init__()
      self.env = env_         # type: Environment
      self.actor = actor_     # type: ActorNetwork
      # TODO: use Q(s,a)
      self.critic = critic_   # type: CriticNetwork
      self.eps = eps_         # type: float
      self.n_step = n_step_   # type: …

  Run Code Online (Sandbox Code Playgroud)

我正在构建一些复杂的神经网络模型,其中2个网络共享一些层.我的实现是创建2个张量流图并在其间共享层/变量.然而,在创建网络的过程中发现了错误.

import tensorflow as tf
def create_network(self):
    self.state_tensor = tf.placeholder(tf.float64, [None, self.state_size], name="state")
    self.action_tensor = tf.placeholder(tf.float64, [None, self.action_size], name="action")
    self.actor_graph = tf.Graph()
    with self.actor_graph.as_default():
        print tf.get_variable_scope()
        state_h1 = tf.layers.dense(inputs=self.state_tensor, units=64, activation=tf.nn.relu, name="state_h1",
                                   reuse=True)
        state_h2 = tf.layers.dense(inputs=state_h1, units=32, activation=tf.nn.relu, name="state_h2", reuse=True)
        self.policy_tensor = tf.layers.dense(inputs=state_h2, units=self.action_size, activation=tf.nn.softmax,
                                             name="policy")

    self.critic_graph = tf.Graph()
    with self.critic_graph.as_default():
        print tf.get_variable_scope()
        state_h1 = tf.layers.dense(inputs=self.state_tensor, units=64, activation=tf.nn.relu, name="state_h1",
                                   reuse=True)
        state_h2 = tf.layers.dense(inputs=state_h1, units=32, activation=tf.nn.relu, name="state_h2", reuse=True)
        action_h1 = tf.layers.dense(inputs=self.action_tensor, units=64, activation=tf.nn.relu, name="action_h1")
        action_h2 = tf.layers.dense(inputs=action_h1, units=32, activation=tf.nn.relu, name="action_h2")
        fc …

我是Go的新手,我正在研究它的界面功能.

这是代码:

package main

import (
        "fmt"
        "reflect"
)

type Integer int

func (a Integer) Less(b Integer) bool {
        return a < b
}

func (a *Integer) Add(b Integer) {
        *a += b
}

type LessAdder interface {
        Less(b Integer) bool
        Add(b Integer)
}

var a Integer = 1

var b LessAdder = &a

func main() {
        fmt.Println(reflect.TypeOf(b))
        fmt.Println(b.Less(2))
        b.Add(a)
        fmt.Println(a)

}

它将输出以下内容:

*main.Integer
true
2

嗯,这很好用.

要点是:如何var b LessAdder = &a运作.指针自动取消引用是在这里发生,还是在b调用成员方法时？

输出*main.Integer告诉我们b是指向类型的指针Integer,因此它是第二种情况.

然后棘手的事情来了:当我添加 …