We're in development. Going live soon.

Actor-Critic Methods - Policy-Based Methods | OneNoughtOne

Loading content...

Machine Learning0/328 completed

1.Policy Gradient Theorem 2.REINFORCE Algorithm 3.Variance Reduction 4.Actor-Critic Methods 5.Advantage Functions

Intra-Group Advantage Normalization for Policy Training
Unbiased Policy Divergence Estimation for Regularized Optimization

Course overview & roadmap

101OneNoughtOne

0/328

Actor-Critic Methods

Sign in with a free account to read every lesson and save your progress.

Read the first lesson sample