Bella Nicholson
Bella Nicholson
Bio
Blog
Experience
Projects
Talks
CV
Blog
Reinforcement Learning: Investigating Gradient Stability in Policy Based Methods
How does the gradient stability differ between REINFORCE, G(PO)MDP, G(PO)MDP+ whitening during policy learning?
Bella Nicholson
,
Bob Borsboom
,
Tim Van Loenhout
,
Jochem Hölscher
Oct 13, 2020
18 min read
«
Cite
×
