YingxiaoKong

Are the vae and lstm models independent from each other?

2

Hi, I have went through your codes and I'm still a little bit confused about the structures of theses two models (I'm not very good at reading codes, forgive me):...

莫凡你好， 我想问一下，如果我的每个episode的长度不一样该怎么办呢？ 比如，我的每个episode都是以agent到达目的地结束，但是到达目的地的步数是不一样的。这种情况下该如何把他们变成一样的呢？

使用DDPG探索范围很小

4

Hi 莫凡，非常感谢你的视频，我的程序终于运行了。但是我发现state 的范围很大的时候，agent 并不能学习很好。 我要解决的问题是： 在一个N*N 的空间内，一个小车从【N，N】 出发，想要走到【0，0】，速度可取值范围是【0，0】。速度是水平和竖直方向的。 当N为5的时候，学习到的概率很大，当N过大的时候，他的学习就很难了，很容易陷入局部最优。我把它探索的所有的位置都画出来了。   然后后来我又换了另外一套速度： 角度和速度。水平和竖直方向的速度就成了速度的分量。但是这一种表现更差。最优的方式是45度，但我的角度可取值范围是【-90，90】，然后它每次都会取极值，不会取中间值。 是不是DDPG不太适合做这种学习？用PPO会不会好一些？

Hi I don't understand why we still need to define the action space as it is supposed to be infinite when using DDPG.

Hello, I'm wondering whether the uncertainty captured here is epistemic or aleatoric uncertainty? Or both?

all data got the same scores with too much training epochs

3

Hello Daniel, Thank you for sharing your code. I tested it on a very simple dataset. The normal data are generated from a gaussian distribution with mean as 0 and...

all data points will be classified as normal given enough training epochs

6

Hello, I tried to implement the LSTM-OCNN on my own dataset, and it seems that the results depends heavily on the number of training epochs: if the training epochs are...

Hello Raghavendra, Thank you for sharing your code! The normal data are generated from a gaussian distribution with mean as 0 and std as 1 and the sample size is...