Kolibri-1
Aleph AlphaAll environments grade a sequence with a verifiable reward in [0, 1], except for the Hallucination Reduction environments, whose signed rewards lie in [−1, 1].
general family · filed under post-training
Trains policies using rewards determined by verifiable task outcomes rather than relying solely on subjective judgments.
The sources on this page only mention it in passing. The line above is the extraction's one-line gloss. See reward modelling for the methods filed beside it.
Also called Verifiable-reward reinforcement learning, verifiable reward, Verifiable rewards for RL environments.
5 quotes from 5 sources, one card per model, each opening with its strongest.
All environments grade a sequence with a verifiable reward in [0, 1], except for the Hallucination Reduction environments, whose signed rewards lie in [−1, 1].
Reinforcement learning with verifiable rewards, reinforcement learning from human feedback, and specialized teacher training
Reinforcement learning with verifiable rewards
Use reinforcement learning with verifiable rewards to adapt NVIDIA Nemotron for specific domains and workflows
reproduce-then-patch tasks use a verifiable reward, so it fits with RL environments that could be used to further RL smaller security models.