AI engineering glossary · Reinforcement learning
What is baseline (policy gradient)?
Baseline (policy gradient): A number subtracted from the return in a policy gradient update to reduce variance without changing the expected gradient. The best common choice is the state value, which leads to the advantage function.
Baseline (policy gradient): an example
Instead of weighting by a return of 100, weight by 100 - 95 = 5 when the typical value is 95.
Related terms
More Reinforcement learning terms
- Behavioural cloning
- Belief state
- Bellman backup
- Bellman equation
- Bellman optimality equation
- Bootstrapping
- Conservative Q-learning
- Contextual bandit
Where you learn it
Baseline (policy gradient) is part of the AI Engineering Program, which teaches it with notes, a hands-on lab and an exam. The first lesson is free.