Skip to content
NeurIPS 2026 planner

Poster · Sydney

RL Excursions during Pre-training: How early is too early for on-policy learning?

When
Thu 10 Dec 2026, 10:00–13:00 AEDT
Where
Hall 1-4, ICC Sydney
Exhibition Centre, Level 1
Session
Sydney Poster Session 5
Authors
Rachit Bansal, Clara Mohri, Tian Qin, David Alvarez-Melis, Sham Kakade
Organisations
Harvard University, Microsoft, Amazon
QRS classification
Reinforcement learning, Language models

Open in scheduleOfficial page