Attentive Feature Aggregation or: How Policies Learn to Stop Worrying about Robustness and Attend to Task-Relevant Visual Cues
关注特征聚合或:政策如何学会停止担心鲁棒性并关注任务相关的视觉线索
机构 * University of Edinburgh(爱丁堡大学) ; UCL(伦敦大学学院) ; Samsung AI Center - Cambridge, UK(三星AI研究中心-剑桥,英国)
AI总结 本文提出AFA方法,通过注意力机制提升视觉-运动策略在扰动环境下的鲁棒性和泛化能力。
Comments This paper stems from a split of our earlier work "When Pre-trained Visual Representations Fall Short: Limitations in Visuo-Motor Robot Learning." While "The Temporal Trap" replaces the original and focuses on temporal entanglement, this companion study examines policy robustness and task-relevant visual cue selection. arXiv admin note: text overlap with arXiv:2502.03270