Texonom
Texonom/
Engineering
Engineering/Data Engineering/Artificial Intelligence/Machine Learning/Reinforcement Learning/Reinforcement Learning Method/Reward model/Reasoning Reward model/
Chunked reward model
Search

Chunked reward model

Creator
Creator
Seonglae ChoSeonglae Cho
Created
Created
2025 Mar 21 16:52
Editor
Editor
Seonglae ChoSeonglae Cho
Edited
Edited
2025 Mar 21 16:53
Refs
Refs
not whole results of output with single-horizon
  • token-level reward model
    • hidden state
  • window-based
 
 
 
 
 
 
 
 

Recommendations

Texonom
Texonom/
Engineering
Engineering/Data Engineering/Artificial Intelligence/Machine Learning/Reinforcement Learning/Reinforcement Learning Method/Reward model/Reasoning Reward model/
Chunked reward model