AI engineering glossary · Reinforcement learning
What is CQL (Conservative Q-learning)?
Conservative Q-learning (also called CQL): An offline method that adds a penalty which pushes down value estimates of actions not well supported by the dataset. This prevents the learner from choosing actions that look good only because of extrapolation errors.
Conservative Q-learning: an example
Q values for actions never seen in the logs are lowered so they are not preferred over well-tested ones.
Related terms
More Reinforcement learning terms
- Contextual bandit
- Continuing task
- Count-based exploration
- Credit assignment
- Curiosity-driven exploration
- DAgger
- Deadly triad
- Deep deterministic policy gradient
Where you learn it
Conservative Q-learning is part of the AI Engineering Program, which teaches it with notes, a hands-on lab and an exam. The first lesson is free.