single mention · post-training
End-to-end GRPO on agentic tasks
Applies GRPO end to end on executable agentic tasks.
The sources on this page only mention it in passing. The line above is the extraction's one-line gloss. See reinforcement learning algorithm for the methods filed beside it.
Also called full end to end GRPO on agentic tasks.
Filed under post-training › reinforcement learning algorithm