SOURCE-LINKED INTELLIGENCE

Memory Anchors for Continual Robot Learning

arXiv · AI, language, vision and robotics · article · Aug 27, 2026 · UTC

Robot policies deployed in the wild should have the capability to continually learn new tasks without forgetting existing behaviors. A common approach to combat such catastrophic forgetting is to train on new task data with a replay buffer of previously learned task data. Although this buffer is commonly sampled randomly from all prior experiences, we show that a small set of these experiences contributes greatly in anchoring past performance. We call these experiences Memory Anchors. We identify Memory Anchors in regions where representations of new-task observations collapse onto those of ol

Read original source ↗ Open in workspace

recordType

paper

region

Global