Skip to main content
Data Science

Return to Question

Link provided in comments
Source Link
Neil Slater
Neil Slater
  • 29.2k
  • 5
  • 81
  • 100

How to get rid of the expectation in Monte Carlo Policy Gradient method  ?

Taken from Policy Gradient lecture notes, slide 16 onward:

enter image description here

Here in the David Silver Lecture series I perfectly understand how he took the expectation value in the theorem part by combining the following equation .

enter image description here

But how he removed the expectation part when talking stochastic gradient decent ?

How to get rid of the expectation in Monte Carlo Policy Gradient method  ?

enter image description here

Here in the David Silver Lecture series I perfectly understand how he took the expectation value in the theorem part by combining the following equation .

enter image description here

But how he removed the expectation part when talking stochastic gradient decent ?

How to get rid of the expectation in Monte Carlo Policy Gradient method?

Taken from Policy Gradient lecture notes, slide 16 onward:

enter image description here

Here in the David Silver Lecture series I perfectly understand how he took the expectation value in the theorem part by combining the following equation .

enter image description here

But how he removed the expectation part when talking stochastic gradient decent ?

Source Link
Shamane Siriwardhana
Shamane Siriwardhana
  • 827
  • 1
  • 8
  • 25

How to get rid of the expectation in Monte Carlo Policy Gradient method ?

enter image description here

Here in the David Silver Lecture series I perfectly understand how he took the expectation value in the theorem part by combining the following equation .

enter image description here

But how he removed the expectation part when talking stochastic gradient decent ?