Texonom
Texonom/
Engineering
Engineering/Data Engineering/Artificial Intelligence/Machine Learning/Machine Learning Theory/Reinforcement Learning/Reinforcement Learning Method/Model based RL/Reward model/
Critic based reward model
Search

Critic based reward model

Creator
Creator
Seonglae ChoSeonglae Cho
Created
Created
2024 May 18 9:29
Editor
Editor
Seonglae ChoSeonglae Cho
Edited
Edited
2024 May 18 9:30
Refs
Refs

critique is easier than generate

rank
  • RLHF    : Reward modeling → generate that maximize reward like PPO
 
 
 
 
 
 
 
 
 

Recommendations

Texonom
Texonom/
Engineering
Engineering/Data Engineering/Artificial Intelligence/Machine Learning/Machine Learning Theory/Reinforcement Learning/Reinforcement Learning Method/Model based RL/Reward model/
Critic based reward model