Curiosity-Critic: Cumulative Prediction Error Improvement as a Tractable Intrinsic Reward for World Model Training
Curiosity-Critic：累积预测误差改进作为世界模型训练的可处理内在奖励
机构 * Department of Computer Science, University of Toronto, Toronto, Canada（多伦多大学计算机科学系）
AI总结 提出Curiosity-Critic方法，通过可处理的每步替代项（当前预测误差与渐近误差基线的差值）作为内在奖励，利用共训练的评论家在线估计误差基线，有效分离可约与不可约预测误差，在随机网格世界实验中优于现有方法。
Comments Accepted to ICML 2026 Workshop on Epistemic Intelligence in Machine Learning (EIML@ICML 2026). Code: https://github.com/vinbhaskara/Curiosity-Critic
