Policy Gradient Methods

Javier Abellán Abenza
Neurosapiens
Published in
1 min readJan 5, 2019
Photo by Jordan Sanchez on Unsplash

Learn about techniques such as Generalized Advantage Estimation (GAE) for lowering the variance of policy gradient methods. Explore policy optimization methods such as Trust Region Policy Optimization (TRPO) and Proximal Policy Optimization (PPO).

--

--

Javier Abellán Abenza
Neurosapiens

M.S. Computer Science student interested in deep learning