Reinforcement Learning

A subfield of AI where models learn patterns from data to make predictions or decisions, improving with experience ra...

Formal framework for sequential decision-making under uncertainty.

Strategy mapping states to actions.

Expected cumulative reward from a state or state-action pair.

A system that perceives state, selects actions, and pursues goals—often combining LLM reasoning with tools and memory.

A high-priority instruction layer setting overarching behavior constraints for a chat model.

Rules and controls around generation (filters, validators, structured outputs) to reduce unsafe or invalid behavior.

RL without explicit dynamics model.

RL using learned or known environment models.