Papers with Code paper Sep 29

EasyPPO: Stabilizing the Critic Is Key

A key strength of Proximal Policy Optimization (PPO) is its learned critic, which uses historical trajectories collected during reinforcement learning to estimate expected returns ...

Papers with Code paper Sep 28

Rubric Rewards from Item Response Theory

Many language tasks have no single answer that can be checked automatically. Rubrics provide criteria for judging responses to these tasks. For reinforcement learning, the resultin...

Papers with Code paper Sep 28

Nereus: Adaptive Parallelism for LLM Post-Training

Reinforcement learning (RL) post-training for large language models (LLMs) coordinates multiple models across generation, inference, and training on GPU clusters. Several factors m...