AI engineering glossary · Reinforcement learning
What is reward shaping?
Reward shaping: Adding extra hint scores to the original feedback to guide the learner more quickly toward the goal, especially when the true score is rare. Badly chosen hints can change what is optimal and cause unintended behaviour.
Reward shaping: an example
In a navigation task, add +0.1 for each step that reduces distance to the goal, alongside +10 for arriving.
Related terms
More Reinforcement learning terms
- Sample efficiency
- SARSA
- Score function estimator
- Self-play
- Sim-to-real transfer
- Softmax exploration
- Sparse reward
- State
Where you learn it
Reward shaping is part of the AI Engineering Program, which teaches it with notes, a hands-on lab and an exam. The first lesson is free.