Wish to build scaling laws for RL but not sure how to scale? Or what scales? Or would RL even scale predictably?
We introduce: The Art of Scaling Reinforcement Learning Compute for LLMs
Devvrit
@Devvrit_Khatri
Founding Member at @Mirendil, GradStudent @UTCompSci. Past: StudentResearcher at Meta and Google. Post-training - RL, Distillation, et al.
Joined December 2019
