Skip to main content
Artificial Intelligence

Return to Question

Bumped by Community user
Bumped by Community user
Bumped by Community user
Bumped by Community user
Bumped by Community user
Bumped by Community user
Bumped by Community user
I included a screenshot of the algorithm for reproducibility.
Source Link
nbro
nbro
  • 41.4k
  • 12
  • 114
  • 205

Problem with a step of the In Deep Deterministic Policy Gradient, are all weights of the policy gradient algorithmnetwork updated with the same or different value?

I'm trying to understand the DDPG algorithm shown at this page. I don't know what should be the result of the gradient at step 14: is be.

enter image description here

Is it a scalar that I have to use to update all the weights (so all weights are updated with the same value)? Or is it a list with a different values to use for updating for each weight? I'm used to working with loss functions and an $y$ target, but here I don't have them so I'm quite confused.

Problem with a step of the Deep Deterministic policy gradient algorithm

I'm trying to understand the DDPG algorithm shown at this page. I don't know what should be the result of the gradient at step 14: is it a scalar that I have to use to update all the weights (so all weights are updated with the same value)? Or is it a list with a different values to use for updating for each weight? I'm used to working with loss functions and an $y$ target, but here I don't have them so I'm quite confused.

In Deep Deterministic Policy Gradient, are all weights of the policy network updated with the same or different value?

I'm trying to understand the DDPG algorithm shown at this page. I don't know what should the result of the gradient at step 14 be.

enter image description here

Is it a scalar that I have to use to update all the weights (so all weights are updated with the same value)? Or is it a list with a different values to use for updating for each weight? I'm used to working with loss functions and an $y$ target, but here I don't have them so I'm quite confused.

added 2 characters in body
Source Link
nbro
nbro
  • 41.4k
  • 12
  • 114
  • 205

I'm trying to understand the DDPG algorithm shown at this page. I don't know what should be the result of the gradient at step 14: is it a scalar that I have to use to update all the weights (so all weights are updated with the same value)? Or is it a list with a different values to use for updating for each weightsweight? I'm used to working with loss functions and an y$y$ target, but here I don't have them so I'm quite confused.

I'm trying to understand the DDPG algorithm shown at this page. I don't know what should be the result of the gradient at step 14: is it a scalar that I have to use to update all the weights (so all weights are updated with the same value)? Or is it a list with a different values to use for updating for each weights? I'm used to working with loss functions and an y target, but here I don't have them so I'm quite confused

I'm trying to understand the DDPG algorithm shown at this page. I don't know what should be the result of the gradient at step 14: is it a scalar that I have to use to update all the weights (so all weights are updated with the same value)? Or is it a list with a different values to use for updating for each weight? I'm used to working with loss functions and an $y$ target, but here I don't have them so I'm quite confused.

Source Link
unter_983
unter_983
  • 331
  • 1
  • 7

Problem with a step of the Deep Deterministic policy gradient algorithm

I'm trying to understand the DDPG algorithm shown at this page. I don't know what should be the result of the gradient at step 14: is it a scalar that I have to use to update all the weights (so all weights are updated with the same value)? Or is it a list with a different values to use for updating for each weights? I'm used to working with loss functions and an y target, but here I don't have them so I'm quite confused