<?xml version="1.0" encoding="utf-8" ?><rss version="2.0"><channel><title><![CDATA[GUFighting的博客]]></title><description><![CDATA[]]></description><link>https://blog.youkuaiyun.com/GUFighting</link><language>zh-cn</language><generator>https://blog.youkuaiyun.com/</generator><copyright><![CDATA[Copyright &copy; GUFighting]]></copyright><item><title><![CDATA[2020-12-05]]></title><link>https://blog.youkuaiyun.com/GUFighting/article/details/110727356</link><guid>https://blog.youkuaiyun.com/GUFighting/article/details/110727356</guid><author>GUFighting</author><pubDate>Sat, 05 Dec 2020 21:24:44 +0800</pubDate><description><![CDATA[python代码运行问题
当python运行时遇到这种情况该怎么解决：
TypeError: cannot unpack non-iterable NoneType object

]]></description><category></category></item><item><title><![CDATA[DDPG训练问题]]></title><link>https://blog.youkuaiyun.com/GUFighting/article/details/109412831</link><guid>https://blog.youkuaiyun.com/GUFighting/article/details/109412831</guid><author>GUFighting</author><pubDate>Sun, 01 Nov 2020 11:20:56 +0800</pubDate><description><![CDATA[使用DDPG算法时，我的critic网络损失函数是(((r+gammaQ_target)-Q)^2)，actor网络的损失函数是Q，critic网络的参数更新公式是Wq=Wq-αdQ/dWq，critic网络的参数更新公式是uWu=Wu-β*(dQ/da*du/dWu)，根据以上参数更新公式进行训练时，Q值是递减的，损失函数的变化也与奖励值有些不对应，请问大家出现这种情况的解决办法。

...]]></description><category></category></item><item><title><![CDATA[2020-09-16]]></title><link>https://blog.youkuaiyun.com/GUFighting/article/details/108631377</link><guid>https://blog.youkuaiyun.com/GUFighting/article/details/108631377</guid><author>GUFighting</author><pubDate>Wed, 16 Sep 2020 21:48:10 +0800</pubDate><description><![CDATA[造成DDPG算法loss函数不收敛的原因有哪些？
已经确认自己的算法框架是对的，参数更新公式完全是参考的一篇博士论文。即使这样在代码训练过程中也会出现损失函数不收敛的情况，特此向各位请教。

...]]></description><category></category></item><item><title><![CDATA[2020-08-28]]></title><link>https://blog.youkuaiyun.com/GUFighting/article/details/108283059</link><guid>https://blog.youkuaiyun.com/GUFighting/article/details/108283059</guid><author>GUFighting</author><pubDate>Fri, 28 Aug 2020 16:58:04 +0800</pubDate><description><![CDATA[用matlab软件实现DDPG算法时，自己的代码步骤严格按照算法步骤，为什么自己的代码运行时会出现Loss越来越大情况。请大家指教。

]]></description><category></category></item><item><title><![CDATA[强化学习]]></title><link>https://blog.youkuaiyun.com/GUFighting/article/details/104406897</link><guid>https://blog.youkuaiyun.com/GUFighting/article/details/104406897</guid><author>GUFighting</author><pubDate>Thu, 20 Feb 2020 11:02:33 +0800</pubDate><description><![CDATA[强化学习的Q矩阵和R矩阵是不是都必须为方阵

]]></description><category></category></item><item><title><![CDATA[多智能体强化学习]]></title><link>https://blog.youkuaiyun.com/GUFighting/article/details/103568254</link><guid>https://blog.youkuaiyun.com/GUFighting/article/details/103568254</guid><author>GUFighting</author><pubDate>Mon, 16 Dec 2019 19:10:37 +0800</pubDate><description><![CDATA[请问大家学习多智能体强化学习有什么好的参考资料可以辅助自己学习

]]></description><category></category></item><item><title><![CDATA[matlab中调用interp函数时出现使用 griddedInterpolant 网格矢量未定义与给定值匹配的点网格时怎么处理。]]></title><link>https://blog.youkuaiyun.com/GUFighting/article/details/103534176</link><guid>https://blog.youkuaiyun.com/GUFighting/article/details/103534176</guid><author>GUFighting</author><pubDate>Fri, 13 Dec 2019 22:16:39 +0800</pubDate><description><![CDATA[matlab中调用interp1函数时出现使用 griddedInterpolant 网格矢量未定义与给定值匹配的点网格时怎么处理？求大神解答
在这里插入代码片
```drv_pwr_dmd_simu=drv_ctrl_pwr_dmd_simu
 prb.W{1}=interp1(sch_cycle(:,1),drv_pwr_dmd_simu,0:prb.N/prb.Ts);
prb.W{2}= ...]]></description><category></category></item><item><title><![CDATA[动态规划]]></title><link>https://blog.youkuaiyun.com/GUFighting/article/details/102904807</link><guid>https://blog.youkuaiyun.com/GUFighting/article/details/102904807</guid><author>GUFighting</author><pubDate>Mon, 04 Nov 2019 20:25:55 +0800</pubDate><description><![CDATA[动态规划（DP）函数在matlab中该调用哪个函数？

]]></description><category></category></item><item><title><![CDATA[调用了newrb函数后输出的神经元数和误差均为零怎么解决，出现错误的情况有哪些。]]></title><link>https://blog.youkuaiyun.com/GUFighting/article/details/102748791</link><guid>https://blog.youkuaiyun.com/GUFighting/article/details/102748791</guid><author>GUFighting</author><pubDate>Fri, 25 Oct 2019 19:40:54 +0800</pubDate><description><![CDATA[调用了newrb函数后输出的神经元数和误差均为零怎么解决，出现错误的情况有哪些。

]]></description><category></category></item></channel></rss>