AI engineering glossary · Reinforcement learning
What is off-policy?
Off-policy: Describes a learning method that learns about one decision rule, usually the best one, while following a different rule to gather data. It allows reuse of stored experience and learning from other sources, but can be less stable.
Off-policy: an example
Q-learning and DQN learn the greedy rule while actually behaving with epsilon-greedy exploration or from logged data.
Related terms
More Reinforcement learning terms
- Off-policy evaluation
- Offline reinforcement learning
- On-policy
- Optimal policy
- Options framework
- Overestimation bias
- Partially observable Markov decision process
- Policy evaluation
Where you learn it
Off-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.