Showing 2026Show all
3 papers · 1 filter
cs.LG2026
MIPS: Mitigating Mode Collapse in Reinforcement Learning for Large Outcome Spaces
Armaan Sandhu, Abhijeet Sinha, Dianbo Liu
Expected-reward maximization in reinforcement learning concentrates probability mass on a few outcomes, even in tasks that require many distinct, high-quality solutions, a failure…
cs.LG2026
Data-DPO: Direct Preference Optimization for Target Model Data Selection in LLM Post-Training
Peng Sun, Yi Yang, Antong Zhang +7
Data selection in supervised fine-tuning aims to select a small set of effective samples from large-scale candidate data, reducing training cost while preserving model performance.…
cs.LG2026
Expected Return Causes Outcome-Level Mode Collapse in Reinforcement Learning and How to Fix It with Inverse Probability Scaling
Abhijeet Sinha, Sundari Elango, Dianbo Liu
Many reinforcement learning (RL) problems admit multiple terminal solutions of comparable quality, where the goal is not to identify a single optimum but to represent a diverse set…