Error Amplification Limits ANN-to-SNN Conversion in Continuous Control

TL;DR

This paper identifies error amplification as a key challenge in converting ANNs to SNNs for continuous control tasks and proposes CRPI to mitigate this issue, significantly improving performance.

Contribution

The paper introduces CRPI, a lightweight, training-free method to reduce error amplification in ANN-to-SNN conversion for continuous control.

Findings

CRPI effectively reduces error amplification in SNNs.

Performance on continuous control benchmarks improves with CRPI.

ANN-to-SNN conversion is feasible for complex control tasks with error mitigation.

Abstract

Spiking Neural Networks (SNNs) can achieve competitive performance by converting already existing well-trained Artificial Neural Networks (ANNs), avoiding further costly training. This property is particularly attractive in Reinforcement Learning (RL), where training through environment interaction is expensive and potentially unsafe. However, existing conversion methods perform poorly in continuous control, where suitable baselines are largely absent. We identify error amplification as the key cause: small action approximation errors become temporally correlated across decision steps, inducing cumulative state distribution shift and severe performance degradation. To address this issue, we propose Cross-Step Residual Potential Initialization (CRPI), a lightweight training-free mechanism that carries over residual membrane potentials across decision steps to suppress temporally correlated errors. Experiments on continuous control benchmarks with both vector and visual observations demonstrate that CRPI can be integrated into existing conversion pipelines and substantially recovers lost performance. Our results highlight continuous control as a critical and challenging benchmark for ANN-to-SNN conversion, where small errors can be strongly amplified and impact performance.