Reinforcement Learning Method

Editor
Creator
Creator
Seonglae ChoSeonglae Cho
Created
Created
2023 Sep 10 7:51
Edited
Edited
2025 Jan 14 12:3

Classification itself is not that helpful for understanding; it's more important to identify the key elements that divide abstraction

  • Efficient learning requires controlling distribution shift
  • Learned functions can be exploited when optimized against
Reinforcement Learning Methods
 
 
You can choose policy function or value function or both to optimize
You can choose policy function or value function or both to optimize
notion image
notion image
 
 
 
 

 

Recommendations