AI Glossary

Policy in reinforcement learning

Also called RL policy

What does “Policy in reinforcement learning” mean?

Policy in reinforcement learning: A rule or model that chooses actions from observations or states.

Policy in reinforcement learning visual guide: A rule or model that chooses actions from observations or states.
Visual guide Open full size (new tab)

What is an example of “Policy in reinforcement learning”?

A game-playing policy chooses a move after reading the board.

Keep learning

See also

Reinforcement learningTermReward modelTermReward hackingTermValue functionTermDiscount factorTerm

Same topic

Pooling layerTermParameter-efficient fine-tuningTermPre-trainingTermOversamplingTermPreference datasetTerm