Demonstrates that Hebbian plasticity can induce emergent attractor dynamics in robot controllers, enabling rapid adaptation without backpropagation.
March 25, 2026
Original Paper
Hebbian Attractor Networks for Robot Locomotion
arXiv · 2603.22512
The Takeaway
This moves away from 'frozen' weights or expensive online gradient updates, allowing robots to adapt their locomotion patterns to new terrains in real-time. It provides a biologically plausible path for high-dimensional embodied systems to self-modify through experience.
From the abstract
Biological neural networks continuously adapt and modify themselves in response to experiences throughout their lifetime - a capability largely absent in artificial neural networks. Hebbian plasticity offers a promising path toward rapid adaptation in changing environments. Here, we introduce Hebbian Attractor Networks (HAN), a class of plastic neural networks in which local weight update normalization induces emergent attractor dynamics. Unlike prior approaches, HANs employ dual-timescale plast