AI engineering glossary · Reinforcement learning
What is return?
Return (also called Cumulative reward, Discounted return): The total future score from a given moment onward, usually with later scores weighted down by a factor between 0 and 1. It is what the learner really tries to maximise. Formula: G_t = r_(t+1) + gamma * r_(t+2) + gamma^2 * r_(t+3) + ...
Return: an example
With gamma = 0.9 and future scores 1, 1, 10, the return is 1 + 0.9*1 + 0.81*10 = 10.
Related terms
More Reinforcement learning terms
- Reward
- Reward function
- Reward shaping
- Sample efficiency
- SARSA
- Score function estimator
- Self-play
- Sim-to-real transfer
Where you learn it
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.