About this document
Actor-Critic Methods in Reinforcement Learning by Hadia Ramzan is a document available to read on EtoBox.
The document outlines a lecture on Actor-Critic Methods and its variants, including the Advantage Actor Critic (A2C). It recaps previous topics such as the Monte Carlo REINFORCE Policy Gradient Algorithm and discusses methods for reducing variance and estimating action-value functions. The lecture also covers the application of critics and actors at different time-scales and summarizes policy gradient algorithms.
- Author
- Hadia Ramzan
- Language
- EN