RLVR
Named by 7 kept items in this workspace.
Search every workspace for RLVR. It matches the name as written, so it can find other things that share it.
The items that name it 7
Reinforcement Learning with Verifiable Rewards
Reinforcement Learning with Verifiable Rewards
verifiable-reward RL
Training LLMs directly against the real world, offered as one explanation for the shift from no discoveries to many.
Reinforcement Learning from Verifiable Rewards
reinforcement learning from verifiable rewards
All techniques in this workspace.