Glossary · Term

verl

← all terms

Definition

An open-source training framework for reinforcement learning on language models.

A distributed RL training framework for LLMs commonly used in agent post-training pipelines, notable for FSDP-based sharding rather than DeepSpeed.

Mentioned in 1 episode

  1. 009
    How Two Silent Library Bugs Quietly Invalidated a Wave of Reasoning Papers