Search results

Create the page "Gradient Descent" on this wiki! See also the search results found.

• Allen's Reinforcement Learning Notes
  ...iate objective with respect to the optimal theta and then perform gradient descent ...e value function or q-function of current policy, and find a better policy gradient
  5 KB (891 words) - 23:55, 24 May 2024
• Allen's REINFORCE notes
  Based on the loss, use a gradient descent policy to update weights Now we want to find the gradient of <math> J (\theta) </math>, namely
  5 KB (852 words) - 01:23, 26 May 2024
• Dennis' Optimization Notes
  Notes of various riffs on Gradient Descent from a perspective of neural networks. [[Category: Gradient Descent]]
  9 KB (1,469 words) - 04:57, 25 May 2024