AI engineering glossary · Reinforcement learning
What is policy gradient theorem?
Policy gradient theorem: A result showing that the gradient of expected return with respect to the decision-rule parameters can be written as an expectation involving the gradient of the log-probability of actions times the value of those actions, without differentiating through the world's dynamics. It underlies most modern policy-based methods.
Policy gradient theorem: an example
Because of it, we can estimate the gradient from sampled runs alone, even when transitions are unknown.
Related terms
More Reinforcement learning terms
- Policy improvement
- Policy iteration
- Potential-based reward shaping
- Prioritised experience replay
- Q-learning
- Q-table
- Rainbow
- Regret
Where you learn it
Policy gradient theorem is part of the AI Engineering Program, which teaches it with notes, a hands-on lab and an exam. The first lesson is free.