What is Reinforcement learning (RL)?

Reinforcement learning (RL)

Reinforcement learning (RL): Training an agent to make decisions by rewarding good actions and penalising bad ones as it interacts with an environment.

Used in these stories

OpenAI pauses training again as agents reach US government sites28 September 2026

Related terms

Inverse reinforcement learning
Model-based reinforcement learning
Offline reinforcement learning
Reinforcement learning environment (RL environment)
Reinforcement learning from AI feedback (RLAIF)
Reinforcement learning from human feedback (RLHF)
Reinforcement learning with verifiable rewards (RLVR)
Automated machine learning (AutoML)

Browse the full glossary →