AI engineering glossary · Reinforcement learning
What is bootstrapping?
Bootstrapping: Updating an estimate using another estimate rather than a final observed outcome. It lets learning happen before a run ends and lowers variance, but can introduce bias and, combined with other features, instability.
Bootstrapping: an example
Updating V(s) toward r + 0.9*V(s') uses the guess V(s') instead of waiting for the true return.
Related terms
More Reinforcement learning terms
- Conservative Q-learning
- Contextual bandit
- Continuing task
- Count-based exploration
- Credit assignment
- Curiosity-driven exploration
- DAgger
- Deadly triad
Where you learn it
Bootstrapping is part of the AI Engineering Program, which teaches it with notes, a hands-on lab and an exam. The first lesson is free.