Mask World Model: Predicting What Matters for Robust Robot Policy Learning
遮罩世界模型:为鲁棒机器人策略学习预测重要的内容
机构 * Peking University, Beijing, China ; State Key Laboratory of Multimedia Information Processing, School of Computer Science, Peking University ; Beijing Academy of Artificial Intelligence, Beijing, China ; National University of Singapore, Singapore ; The Hong Kong University of Science ; Nanjing University, Nanjing, China
专题命中 机器人学习 :world model(title,summary_cn);robot policy(title,abstract);分类 cs.RO
AI总结 本文提出Mask World Model,通过预测语义遮罩而非像素,提升机器人策略学习的鲁棒性与泛化能力,实验证明其在仿真和现实任务中均优于现有方法。
Comments 16 pages,5 figures