User tryingtolearn

13 votes

1 answer

15k views

Actor-critic loss function in reinforcement learning

asked Jan 2, 2018 at 19:17

7 votes

1 answer

10k views

Q-learning vs. Value Iteration

asked Dec 7, 2017 at 11:06

6 votes

0 answers

4k views

How the Hessian matrix is used in optimization if you can't invert it

asked Sep 24, 2018 at 18:20

4 votes

1 answer

133 views

Do neural networks compute functions or compute parameters of a defined function

asked Sep 21, 2017 at 16:16

3 votes

0 answers

262 views

REINFORCE calculating the log policy gradient for a continuous action space

asked Feb 11, 2019 at 16:47

2 votes

1 answer

507 views

understanding natural policy gradient

asked Sep 12, 2018 at 15:51

2 votes

2 answers

101 views

What ARMA model is this?

asked May 10, 2017 at 11:53

1 vote

1 answer

486 views

ICA - independence of coefficients and maximizing independence

asked Mar 26, 2017 at 12:13

1 vote

0 answers

503 views

PCA is an autoencoder with linear transfer functions [duplicate]

asked Mar 30, 2017 at 17:03

1 vote

1 answer

974 views

RL - Policy Proximal Optimization and clipping

asked Aug 6, 2018 at 13:14

1 vote

1 answer

151 views

Do neural networks with binary output learn representations that are linearly separable?

asked Dec 4, 2018 at 14:14

0 votes

0 answers

100 views

ARIMA Model (2,1,0) [duplicate]

asked Apr 20, 2017 at 14:30

0 votes

0 answers

46 views

Show that this process is an ARIMA(p,d,q) process for some values of p, d, and q

asked May 10, 2017 at 12:47

Stack Exchange Network

13 Questions

Actor-critic loss function in reinforcement learning

Q-learning vs. Value Iteration

How the Hessian matrix is used in optimization if you can't invert it

Do neural networks compute functions or compute parameters of a defined function

REINFORCE calculating the log policy gradient for a continuous action space

understanding natural policy gradient

What ARMA model is this?

ICA - independence of coefficients and maximizing independence

PCA is an autoencoder with linear transfer functions [duplicate]

RL - Policy Proximal Optimization and clipping

Do neural networks with binary output learn representations that are linearly separable?

ARIMA Model (2,1,0) [duplicate]

Show that this process is an ARIMA(p,d,q) process for some values of p, d, and q