AI Glossary

Reward shaping

What does “Reward shaping” mean?

Reward shaping: Adding useful feedback to guide learning toward the desired outcome.

Reward shaping visual guide: Adding useful feedback to guide learning toward the desired outcome.
Visual guide Open full size (new tab)

What is an example of “Reward shaping”?

A navigation task rewards getting closer to the goal as well as reaching it.

Keep learning

See also

Reinforcement learningTermReward modelTermReward hackingTermQ-learningTermTemporal difference learningTerm

Same topic

RMS normalizationTermScaling lawsTermResidual connectionTermSoft prompt tuningTermReinforcement learning from verifiable rewardsTerm