AI engineering glossary · Reinforcement learning
What is optimal policy?
Optimal policy: A decision rule whose expected return in every situation is at least as high as that of any other rule. At least one always exists in a finite sequential decision model, and it can be read off by acting greedily on the optimal action values.
Optimal policy: an example
If Q*(s, left) = 4 and Q*(s, right) = 7, the optimal rule in state s chooses right.
Related terms
More Reinforcement learning terms
- Options framework
- Overestimation bias
- Partially observable Markov decision process
- Policy evaluation
- Policy gradient theorem
- Policy improvement
- Policy iteration
- Potential-based reward shaping
Where you learn it
Optimal policy is part of the AI Engineering Program, which teaches it with notes, a hands-on lab and an exam. The first lesson is free.