AI engineering glossary · Reinforcement learning
What is policy evaluation?
Policy evaluation (also called Prediction problem): The task of computing how good a given decision rule is, i.e. its value in every situation. It is done by repeatedly applying the Bellman equation until values stop changing, or by averaging sampled experience.
Policy evaluation: an example
Starting with all values 0 and sweeping a 16-state grid until the largest change is below 0.001.
Related terms
More Reinforcement learning terms
- Policy gradient theorem
- Policy improvement
- Policy iteration
- Potential-based reward shaping
- Prioritised experience replay
- Q-learning
- Q-table
- Rainbow
Where you learn it
Policy evaluation is part of the AI Engineering Program, which teaches it with notes, a hands-on lab and an exam. The first lesson is free.