SZH1230456

DDPG中的损失函数是不是和原文中不一致？

I am confused about the train and test process, why do you use c^t_d, c^t_p, c^t_m to predict c^t_m?https://github.com/sjy1203/GAMENet/blob/da695b4fc9390882f3a681c82115e81291ae6380/code/train_GAMENet.py#L46-L53 I guess you got the wrong number when you sliced them.

Hi, Tianhe. Could you please release the hiv dataset buffer by SAC agent?  Thanks a lot.

I think the code in the agent training process https://github.com/keon/policy-gradient/blob/b83f050b70fd0af3358a0f2748743d30c0e7462f/pg.py#L56 has some errors. The calculation process can not get right result. You can figure it out and refer: https://github.com/gabrielgarza/openai-gym-policy-gradient/blob/master/policy_gradient_layers.py#

I am confused about the VAE network, could you please explain it? Just to pre-train and obtain the distribution of behavior policy? https://github.com/aviralkumar2907/BEAR/blob/f2e31c1b5f81c4fb0e692a34949c7d8b48582d8f/algos.py#L395-L398

Hello, I am confused about the KL loss function in the training process. In your paper VRNMT, you have mentioned that the z_j is integrated into the decoder network, did...

plot mortality rate wit expected return fig

1

could you please share your code to calculate the relation between the mortality rate with expected return ? Thank you.

dataset

5

I have read the DeepSurv paper but find some differences in the datasets. In WHAS, I run the code finding that there are 6 features to be used but 5...

Predicted Time calculation

8

Hi, I am confused with the predicted time calculation in Equation (13) as follows:  I see it in the code, you just replace the predicted time with v^{t}.h_j, could...

The action_mat.txt file is the transition matrix, which contains the transition from diseases to symptoms, from symptoms to diseases, from diseases to diseases, and from symptoms to symptoms. How did...