Skip to content
NeurIPS 2026 planner

Poster · Sydney

Rollout Pass-Rate Control: Steering Binary-Reward RL Toward Its Most Informative Regime

When
Wed 9 Dec 2026, 17:00–20:00 AEDT
Where
Hall 1-4, ICC Sydney
Exhibition Centre, Level 1
Session
Sydney Poster Session 4
Authors
Tianshu Zhu, Wenyu Zhang, Xiaoying Zuo, Tianlun, Haotian Zhao, yucheng-zeng, Jingnan gu, Daxiang Dong, Jianmin Wu
Organisations
Ant Group, Baidu, Tencent, Xiaohongshu
QRS classification
Reinforcement learning

Open in scheduleOfficial page