Skip to content
NeurIPS 2026 planner

Poster · Atlanta

SAMPPO: Structure-Aware Mirror Proximal Policy Optimization

When
Fri 11 Dec 2026, 16:30–19:30 EST
Where
Hall C1, Georgia World Congress Center
Session
Atlanta Poster Session 6
Authors
Corinna Cortes, Mehryar Mohri, Yutao Zhong
Organisations
Google, Courant Institute of Mathematical Sciences
QRS classification
Reinforcement learning, Language models

Open in scheduleOfficial page