Policy Gradient Methods
Machine Learning · Further Education · Machine Learning Applications
Policy Gradient Methods are a class of reinforcement learning algorithms used to learn a policy that maximizes the expected long-term reward. This unit will provide an overview of Policy Gradient Methods, including their advantages, disadvantages, and applications.
What's included
- Introduction to Policy Gradient Methods
- Policy Gradient Theorem
- Actor-Critic Methods
- Natural Policy Gradient
- Trust Region Policy Optimization
- Proximal Policy Optimization
Keywords
- Policy Gradient Methods
- Reinforcement Learning
- Value Function