AI engineering glossary · Reinforcement learning
What is n-step return?
n-step return: A target for updates that adds up n actual scores and then the estimated value of the situation reached after n steps. It sits between one-step and full-run methods, trading bias against variance. Formula: G = r1 + gamma*r2 + ... + gamma^(n-1)*rn + gamma^n * V(s_n).
n-step return: an example
With n = 3, gamma = 0.9, scores 1, 0, 2 and V(s_3) = 5: G = 1 + 0 + 0.81*2 + 0.729*5 = 6.27.
Related terms
More Reinforcement learning terms
- Nash equilibrium
- Natural policy gradient
- Noisy networks
- Off-policy
- Off-policy evaluation
- Offline reinforcement learning
- On-policy
- Optimal policy
Where you learn it
n-step return is part of the AI Engineering Program, which teaches it with notes, a hands-on lab and an exam. The first lesson is free.