作者位次 #2/4ICML 2026Poster· Deep Learning / Large Language Models
Shrinking the Variance: Shrinkage Baselines for Reinforcement Learning with Verifiable Rewards
Guanning Zeng · Zhaoyi Zhou · Daman Arora · Andrea Zanette
强化学习与后训练OpenReview
首次获取该候选人的完整档案及 StartLux 评估共 20 积分；每位用户单独解锁，之后查看免费。主动刷新 20 积分。
实时查找电子邮箱，费用不超过20积分；未找到邮箱不扣费。
Guanning Zeng · Zhaoyi Zhou · Daman Arora · Andrea Zanette