Hardware-aware Fine-tuning Of Spiking Q-networks On The Spinnaker2 Neuromorphic Platform

Abstract

Spiking Neural Networks (SNNs) promise orders-of-magnitude lower power consumption and low-latency inference on neuromorphic hardware for a wide range of robotic tasks. In this work, we present an energy-efficient implementation of a reinforcement learning (RL) algorithm using quantized SNNs to solve two classical control tasks. The network is trained using the Q-learning algorithm, then fine-tuned and quantized to low-bit (8-bit) precision for embedded deployment on the SpiNNaker2 neuromorphic chip. To evaluate the comparative advantage of SpiNNaker2 over conventional computing platforms, we analyze inference latency, dynamic power consumption, and energy cost per inference for our SNN models, comparing performance against a GTX 1650 GPU baseline. Our results demonstrate SpiNNaker2's strong potential for scalable, low-energy neuromorphic computing, achieving up to 32x reduction in energy consumption. Inference latency remains on par with GPU-based execution, with improvements observed

Stats

• citations0
• S2 citations—
• github stars0
• HF likes0
• heat score0.00
• arxiv keyarfa2025hardware

Related papers

• Deep Reinforcement Learning With Spiking Q-learning (2022)0.00
• Learning First-to-spike Policies For Neuromorphic Control Using Policy Gradients (2018)8.60
• A Dual-memory Architecture For Reinforcement Learning On Neuromorphic Platforms (2021)6.34
• A Low Latency Adaptive Coding Spiking Framework For Deep Reinforcement Learning (2022)7.16
• Human-level Control Through Directly-trained Deep Spiking Q-networks (2021)12.40
• Adaptive Surrogate Gradients For Sequential Reinforcement Learning In Spiking Neural Networks (2025)0.00
• Neuromorphic Dreaming: A Pathway To Efficient Learning In Artificial Agents (2024)0.00
• Fully Spiking Actor Network With Intra-layer Connections For Reinforcement Learning (2024)0.00