SCOPE-RL: Stable and Quantitative Control of Policy Entropy in RL Post-Training

arXiv:2510.08141 · cs.LG · Submitted 2025-10-09 · Read on arXiv

cs.LG

Submitted: 2025-10-09

Updated: 2026-10-21

Terminology

• Entropy Collapse — 3× in this paper · explained in 2 episodes
• GRPO — 1× in this paper · explained in 6 episodes
• Group Relative Policy Optimization (GRPO) — 1× in this paper · explained in 8 episodes
• Language Models (LLMs) — 1× in this paper · explained in 2 episodes
• Large Language Models (LLMs) — 1× in this paper · explained in 8 episodes
• Regularization — 1× in this paper · explained in 3 episodes
• Reinforcement Learning — 1× in this paper · explained in 4 episodes
• Reinforcement Learning (RL) — 1× in this paper · explained in 25 episodes

Related papers

• Polynomial-Augmented Neural Networks (PANNs) with Weak Orthogonality Constraints for Enhanced Function and PDE Approximation
• AIRL-S: Unifying Reinforcement Learning and Search-Based Test-Time Scaling via Adversarial Inverse Reinforcement Learning
• Transformers as Bayesian In-Context Experimenters: Smoothness-Adaptive Efficient ATE Estimation
• Convergence issues in Relational Concept Analysis based on AOC-posets
• Beliefs Beyond Posteriors: The Predictive Cost of ELBO Binding
• Understanding Diffusion Models via Ratio-Based Function Approximation with SignReLU Networks