Learning First-to-spike Policies For Neuromorphic Control Using Policy Gradients

Abstract

Artificial Neural Networks (ANNs) are currently being used as function approximators in many state-of-the-art Reinforcement Learning (RL) algorithms. Spiking Neural Networks (SNNs) have been shown to drastically reduce the energy consumption of ANNs by encoding information in sparse temporal binary spike streams, hence emulating the communication mechanism of biological neurons. Due to their low energy consumption, SNNs are considered to be important candidates as co-processors to be implemented in mobile devices. In this work, the use of SNNs as stochastic policies is explored under an energy-efficient first-to-spike action rule, whereby the action taken by the RL agent is determined by the occurrence of the first spike among the output neurons. A policy gradient-based algorithm is derived considering a Generalized Linear Model (GLM) for spiking neurons. Experimental results demonstrate the capability of online trained SNNs as stochastic policies to gracefully trade energy consumption

Stats

• citations13
• S2 citations—
• github stars0
• HF likes0
• heat score8.60
• arxiv keyrosenfeld2018learning

Related papers

• Deep Reinforcement Learning With Spiking Q-learning (2022)0.00
• Fully Spiking Actor Network With Intra-layer Connections For Reinforcement Learning (2024)0.00
• Adaptive Surrogate Gradients For Sequential Reinforcement Learning In Spiking Neural Networks (2025)0.00
• S2act: Simple Spiking Actor (2026)0.00
• Learning To Control Dynamical Agents Via Spiking Neural Networks And Metropolis-hastings Sampling (2025)0.00
• Scalable Multi-task Learning Through Spiking Neural Networks With Adaptive Task-switching Policy For Intelligent Autonomous Agents (2025)0.00
• Biologically Plausible Variational Policy Gradient With Spiking Recurrent Winner-take-all Networks (2022)0.00
• Learning Fast Changing Slow In Spiking Neural Networks (2024)3.58