1 citations · 1 across the 2 of their papers we have counts for
3 papers
Test-Time Self-Play: Scaling without a Verifier
Akira Yoshiyama, Akmal Ashirmatov, Jonas Hübotter +2
Test-time scaling methods spend additional compute at deployment to improve a large language model's performance on a hard target problem. Most methods rely on a verifier that scor…
Reinforcement Learning via Self-Distillation
Jonas Hübotter, Frederike Lübeck, Lejs Behric +8
Large language models are increasingly post-trained with reinforcement learning in verifiable domains such as code and math. Yet, current methods for reinforcement learning with ve…
Tuning Legged Locomotion Controllers via Safe Bayesian Optimization
Daniel Widmer, Dongho Kang, Bhavya Sukhija +3
This paper presents a data-driven strategy to streamline the deployment of model-based controllers in legged robotic hardware platforms. Our approach leverages a model-free safe le…