log4j_learn...

log4j.propoties

 perfect blog : Here...

 

 

log4j.xml

   config info -> Here ...

   config log file path -> Here ...

 

===========================================================

base technology:

ConversionPattern参数的格式含义 :

格式名    含义 
%c 输出日志信息所属的类的全名 
%d 输出日志时间点的日期或时间,默认格式为ISO8601,也可以在其后指定格式,比如:%d{yyy-MM-dd HH:mm:ss },输出类似:2002-10-18- 22:10:28 
%f 输出日志信息所属的类的类名 
%l 输出日志事件的发生位置,即输出日志信息的语句处于它所在的类的第几行 
%m 输出代码中指定的信息,如log(message)中的message 
%n 输出一个回车换行符,Windows平台为“rn”,Unix平台为“n” 
%p 输出优先级,即DEBUG,INFO,WARN,ERROR,FATAL。如果是调用debug()输出的,则为DEBUG,依此类推 
%r 输出自应用启动到输出该日志信息所耗费的毫秒数 
%t 输出产生该日志事件的线程名

c: full name class   f: only class name

d: date                  l: line

m:message           n: enter line

p: priority              r:    毫秒                        t:thread name

 

Log4j建议只使用四个级别,优先级从高到低分别是ERROR、WARN、INFO、DEBUG 
#这里定义能显示到的最低级别,若定义到INFO级别,则看不到DEBUG级别的信息了~! 

 

log4j.xml

 

<?xml version="1.0" encoding="UTF-8"?>
<!DOCTYPE log4j:configuration PUBLIC "-//log4j/log4j Configuration//EN" "log4j.dtd">
<log4j:configuration xmlns:log4j='http://jakarta.apache.org/log4j/'>

    <appender name="stdout" class="org.apache.log4j.ConsoleAppender">
        <layout class="org.apache.log4j.PatternLayout">
            <param name="ConversionPattern"
                value="%d{yyyy/MM/dd HH:mm:ss.sss} [%-5p] %c.%M:%L - %m%n"/>
        </layout>
    </appender>

    <appender name="traceLog4Debug" class="org.apache.log4j.RollingFileAppender">
        <param name="File" value="c:/log/traceLog4Debug.log"/>
        <param name="maxFileSize" value="2000KB"/>
        <param name="maxBackupIndex" value="20"/>
        <layout class="org.apache.log4j.PatternLayout">
            <param name="ConversionPattern"
                value="%d{yyyy/MM/dd HH:mm:ss.sss} [%-5p] %c.%M:%L - %m%n"/>
        </layout>
    </appender>

    <appender name="debugLog" class="org.apache.log4j.RollingFileAppender">
        <param name="File" value="c:/log/debug.log"/>
        <param name="maxFileSize" value="2000KB"/>
        <param name="maxBackupIndex" value="10"/>
        <layout class="org.apache.log4j.PatternLayout">
            <param name="ConversionPattern"
                value="%d{yyyy/MM/dd HH:mm:ss.sss} [%-5p] %c.%M:%L - %m%n"/>
        </layout>
       <filter class="org.apache.log4j.varia.LevelRangeFilter">
                <param name="LevelMax" value="DEBUG" />
                <param name="LevelMin" value="DEBUG" />
       </filter>
    </appender>

    <appender name="infoLog" class="org.apache.log4j.RollingFileAppender">
        <param name="File" value="c:/log/info.log"/>
        <param name="maxFileSize" value="2000KB"/>
        <param name="maxBackupIndex" value="10"/>
        <!-- Append : is Add log message blow to the old one trace? -->
        <param name="Append" value="false" />
        <layout class="org.apache.log4j.PatternLayout">
            <param name="ConversionPattern"
                value="%d{yyyy/MM/dd HH:mm:ss.sss} [%-5p] %c.%M:%L - %m%n"/>
        </layout>
         <filter class="org.apache.log4j.varia.LevelRangeFilter">
                    <param name="LevelMax" value="INFO" />
                    <param name="LevelMin" value="INFO" />
        </filter>

    </appender>

    <appender name="warnLog" class="org.apache.log4j.RollingFileAppender">
        <param name="File" value="c:/log/warn.log"/>
        <param name="maxFileSize" value="2000KB"/>
        <param name="maxBackupIndex" value="10"/>
        <layout class="org.apache.log4j.PatternLayout">
            <param name="ConversionPattern"
                value="%d{yyyy/MM/dd HH:mm:ss.sss} [%-5p] %c.%M:%L - %m%n"/>
        </layout>
        <filter class="org.apache.log4j.varia.LevelRangeFilter">
                    <param name="LevelMax" value="WARN" />
                    <param name="LevelMin" value="WARN" />
            </filter>
    </appender>

    <appender name="errorLog" class="org.apache.log4j.RollingFileAppender">
        <param name="File" value="c:/log/error.log"/>
        <param name="maxFileSize" value="2000KB"/>
        <param name="maxBackupIndex" value="10"/>
        <layout class="org.apache.log4j.PatternLayout">
            <param name="ConversionPattern"
                value="%d{yyyy/MM/dd HH:mm:ss.sss} [%-5p] %c.%M:%L - %m%n"/>
        </layout>
        <filter class="org.apache.log4j.varia.LevelRangeFilter">
                    <param name="LevelMax" value="ERROR" />
                    <param name="LevelMin" value="ERROR" />
            </filter>
    </appender>

    <!-- log all  message in {name} package -->
    <logger name="com.mark.core.test">
        <level value="ALL"/>
         <appender-ref ref="stdout"/>
        <appender-ref ref="traceLog4Debug"/>
        <appender-ref ref="debugLog"/>
        <appender-ref ref="infoLog"/>
        <appender-ref ref="warnLog"/>
        <appender-ref ref="errorLog"/>
    </logger>

   <logger name="com.opensymphony">
        <level value="ERROR" />
        <appender-ref ref="traceLog4Debug"/>
    </logger>

    <logger name="org.apache.struts2">
         <level value="ERROR" />
         <appender-ref ref="traceLog4Debug"/>
    </logger>

    <logger name="org.hibernate.SQL">
        <level value="DEBUG"/>
        <appender-ref ref="traceLog4Debug"/>
        <appender-ref ref="stdout"/>
    </logger>

    <logger name="org.hibernate">
        <level value="error"/>
        <appender-ref ref="traceLog4Debug"/>
        <appender-ref ref="stdout"/>
    </logger>

    <logger name="org.springframework">
        <level value="error"/>
        <appender-ref ref="traceLog4Debug"/>
        <!-- <appender-ref ref="stdout"/>-->
    </logger>

</log4j:configuration>
 

 

package com.mark.core.test;

import org.apache.log4j.Logger;

/**
 * @author mark.lin
 *
 */

public class TestLog4j {

    private static final Logger log = Logger.getLogger(TestLog4j.class);
    /**
     * 测试log4j不同级别日志分文件记录
     *
     */

    public static void main(String[] args) {
        log.debug("debug...");
        log.info("info...xxx");
        log.warn("warn...");
        log.error("error...");

    }

}
 

 

以下是基于TensorFlow构建的最大熵SAC强化学习算法的代码示例: ``` import tensorflow as tf import numpy as np import gym # 定义常量 LR_A = 0.001 # actor的learning rate LR_C = 0.002 # critic的learning rate GAMMA = 0.9 # 折扣因子 TAU = 0.01 # 软更新的参数 MEMORY_CAPACITY = 10000 # 记忆库的大小 BATCH_SIZE = 32 # 批处理的大小 MAX_EPISODES = 200 # 最大的训练次数 MAX_EP_STEPS = 200 # 每次训练步数的最大值 # 定义Actor网络 class Actor(object): def __init__(self, sess, n_features, n_actions, lr=0.001): self.sess = sess self.s = tf.placeholder(tf.float32, [None, n_features], 'state') self.a = tf.placeholder(tf.float32, [None, n_actions], 'action') self.td_error = tf.placeholder(tf.float32, None, 'td_error') l1 = tf.layers.dense(self.s, 30, activation=tf.nn.relu) mu = tf.layers.dense(l1, n_actions, activation=tf.nn.tanh) sigma = tf.layers.dense(l1, n_actions, activation=tf.nn.softplus) global_step = tf.Variable(0, trainable=False) self.mu, self.sigma = tf.squeeze(mu*2), tf.squeeze(sigma+0.1) self.normal_dist = tf.distributions.Normal(self.mu, self.sigma) # 最大熵 self.log_prob = self.normal_dist.log_prob(self.a) self.exp_v = self.log_prob * self.td_error self.entropy = self.normal_dist.entropy() self.loss = -(self.exp_v + 0.01*self.entropy) self.train_op = tf.train.AdamOptimizer(lr).minimize(self.loss, global_step=global_step) def learn(self, s, a, td): self.sess.run(self.train_op, {self.s: s, self.a: a, self.td_error: td}) def choose_action(self, s): s = s[np.newaxis, :] return self.sess.run(self.normal_dist.sample(), {self.s: s})[0] # 定义Critic网络 class Critic(object): def __init__(self, sess, n_features, lr=0.002): self.sess = sess self.s = tf.placeholder(tf.float32, [None, n_features], 'state') self.v_ = tf.placeholder(tf.float32, [None, 1], 'v_next') self.r = tf.placeholder(tf.float32, None, 'r') l1 = tf.layers.dense(self.s, 30, activation=tf.nn.relu) self.v = tf.layers.dense(l1, 1, activation=None) td = tf.reduce_mean(self.r + GAMMA * self.v_ - self.v) self.td_error = tf.reduce_mean(tf.square(td)) self.train_op = tf.train.AdamOptimizer(lr).minimize(self.td_error) def learn(self, s, r, s_): v_ = self.sess.run(self.v, {self.s: s_}) td_error, _ = self.sess.run([self.td_error, self.train_op], {self.s: s, self.v_: v_, self.r: r}) return td_error # 经验回放 class Memory(object): def __init__(self, capacity, dims): self.capacity = capacity self.data = np.zeros((capacity, dims)) self.pointer = 0 def store_transition(self, s, a, r, s_): transition = np.hstack((s, a, r, s_)) index = self.pointer % self.capacity self.data[index, :] = transition self.pointer += 1 def sample(self, n): assert self.pointer >= self.capacity, '记忆库数据不够多' indices = np.random.choice(self.capacity, size=n) return self.data[indices, :] # 主函数 if __name__ == "__main__": env = gym.make('Pendulum-v0') env.seed(1) np.random.seed(1) tf.set_random_seed(1) sess = tf.Session() # 创建actor和critic网络 actor = Actor(sess, env.observation_space.shape[0], env.action_space.shape[0], LR_A) critic = Critic(sess, env.observation_space.shape[0], LR_C) sess.run(tf.global_variables_initializer()) # 创建记忆库 memory = Memory(MEMORY_CAPACITY, dims=env.observation_space.shape[0] * 2 + env.action_space.shape[0] + 1) # 记录训练过程中的奖励和误差 reward_list = [] td_error_list = [] for i in range(MAX_EPISODES): s = env.reset() ep_reward = 0 ep_td_error = 0 for j in range(MAX_EP_STEPS): env.render() # actor选择动作 a = actor.choose_action(s) # 执行动作,得到下一个状态和奖励 s_, r, done, info = env.step(a) # 存储经验 memory.store_transition(s, a, r/10, s_) # 如果记忆库数据够多,开始训练 if memory.pointer > MEMORY_CAPACITY: # 抽取记忆库数据 batch_memory = memory.sample(BATCH_SIZE) # 更新critic网络 td_error = critic.learn(batch_memory[:, :env.observation_space.shape[0]], batch_memory[:, -env.observation_space.shape[0]:], batch_memory[:, -env.observation_space.shape[0]-1:-1]) ep_td_error += td_error # 更新actor网络 actor.learn(batch_memory[:, :env.observation_space.shape[0]], batch_memory[:, env.observation_space.shape[0]:env.observation_space.shape[0] + env.action_space.shape[0]], td_error) # 状态更新 s = s_ ep_reward += r # 如果一次训练结束,输出信息 if j == MAX_EP_STEPS-1: print('Episode:', i, ' Reward: %i' % int(ep_reward), ' TD Error: %.4f' % float(ep_td_error/BATCH_SIZE)) reward_list.append(ep_reward) td_error_list.append(ep_td_error/BATCH_SIZE) break # 关闭环境 env.close() sess.close() ``` 这段代码实现了一个简单的Pendulum-v0任务的最大熵SAC强化学习算法,其中Actor和Critic网络均采用了单层神经网络,可以根据需要进行修改。在训练过程中,会输出每一次训练的奖励和TD误差。
评论
添加红包

请填写红包祝福语或标题

红包个数最小为10个

红包金额最低5元

当前余额3.43前往充值 >
需支付:10.00
成就一亿技术人!
领取后你会自动成为博主和红包主的粉丝 规则
hope_wisdom
发出的红包
实付
使用余额支付
点击重新获取
扫码支付
钱包余额 0

抵扣说明:

1.余额是钱包充值的虚拟货币,按照1:1的比例进行支付金额的抵扣。
2.余额无法直接购买下载,可以购买VIP、付费专栏及课程。

余额充值