AI engineering glossary · Reinforcement learning
What is sparse reward?
Sparse reward: A feedback signal that is zero almost everywhere and non-zero only when a rare goal is reached. Learning is hard because random behaviour seldom finds the goal, so methods such as shaping, curiosity or hindsight relabelling are used.
Sparse reward: an example
A robot task that gives 1 only when a peg is fully inserted and 0 otherwise.
Related terms
More Reinforcement learning terms
- State
- Stochastic policy
- Target network
- TD error
- TD(0)
- TD(lambda)
- Temporal-difference learning
- Terminal state
Where you learn it
Sparse reward is part of the AI Engineering Program, which teaches it with notes, a hands-on lab and an exam. The first lesson is free.