Policy Gradients
Artificial Intelligence · Further Education · Machine Learning Algorithms
Policy Gradients are a reinforcement learning algorithm that learns the optimal policy for a given task by updating the policy parameters in the direction of the gradient of the expected reward. This unit will introduce the concepts and techniques of Policy Gradients and their applications in various domains.
What's included
- Introduction to Policy Gradients
- Policy Gradient Theorem
- Policy Parameterization
- Policy Gradient Algorithms
- Applications of Policy Gradients
Keywords
- Policy Gradients
- Reinforcement Learning
- Policy Optimization
- Expected Reward
- Gradient Ascent