Adaptive Surrogate Gradients for Sequential Reinforcement Learning in Spiking Neural Networks
NeurIPSOral2025
TL;DR
We improve training of spiking neural networks for energy-efficient robotic control by analyzing surrogate gradient slopes and introducing a privileged policy-guided method, achieving a 2.1× performance boost and strong real-world results.
Opening excerpt from the authors’ abstract. source
Read the paper
Topics
reinforcement learning efficient control