AI engineering glossary · Reinforcement learning
What is on-policy?
On-policy: Describes a learning method that improves and evaluates the very same decision rule that is generating the experience, including its exploratory choices. It is simpler and often more stable, but cannot reuse old data collected by earlier rules.
On-policy: an example
SARSA and PPO are on-policy: after each update, the data gathered under the older rule is discarded or corrected.
Related terms
More Reinforcement learning terms
- Optimal policy
- Options framework
- Overestimation bias
- Partially observable Markov decision process
- Policy evaluation
- Policy gradient theorem
- Policy improvement
- Policy iteration
Where you learn it
On-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.