Expected Return Causes Outcome-Level Mode Collapse in Reinforcement Learning and How to Fix It with Inverse Probability Scaling

arXiv:2601.21669 · cs.LG, cs.AI · Submitted 2026-01-29 · Read on arXiv

cs.LG, cs.AI

Submitted: 2026-01-29

Updated: 2026-01-29

Terminology

• GRPO — 3× in this paper · explained in 6 episodes
• Mode Collapse — 3× in this paper · explained in 2 episodes
• Regularization — 2× in this paper · explained in 3 episodes
• Reinforcement Learning — 2× in this paper · explained in 4 episodes
• Group Relative Policy Optimization — 1× in this paper
• Group Relative Policy Optimization (GRPO) — 1× in this paper · explained in 5 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