Module 06: Policy Gradients & Actor-Critic

Coming soon.

Instead of learning values and deriving a policy, what if we just learned the policy directly?

Learning Objectives

• Derive the policy gradient theorem
• Implement REINFORCE with baseline subtraction
• Build an Actor-Critic agent
• Understand variance reduction techniques

Concept Explanation

Coming soon.

Code Examples

Coming soon.

Exercises

Coming soon.