AI engineering glossary · LLM training alignment
What is RLVR (reinforcement learning with verifiable rewards)?
Reinforcement learning with verifiable rewards (also called RLVR): Reinforcement learning where the reward comes from an automatic, checkable rule rather than a learned preference model, such as whether a maths answer matches the key or code passes unit tests. It gives cheap, hard-to-game feedback and is used to train reasoning behaviour.
Reinforcement learning with verifiable rewards: an example
A model gets reward 1 if its final answer to a JEE-style numerical problem equals the known answer, else 0.
Related terms
More LLM training alignment terms
- Rejection sampling fine-tuning
- Reward hacking
- Reward model
- Safety fine-tuning
- Scalable oversight
- Scaling laws
- Self-instruct
- Self-rewarding language models
Where you learn it
Reinforcement learning with verifiable rewards is part of the AI Engineering Program, which teaches it with notes, a hands-on lab and an exam. The first lesson is free.