Policy evaluation is the process of estimating the value of a policy. This unit will introduce the key concepts and algorithms for policy evaluation in reinforcement learning, including Monte Carlo methods and temporal difference learning. Üben mit sofortiger Rückmeldung, kostenlos und ohne Anmeldung.

Weitere Themen

• What is Reinforcement Learning?
• The Reinforcement Learning Cycle
• Types of Reinforcement Learning
• Value Functions
• Bellman Equations
• Value Iteration
• Policies
• Policy Improvement