HMVC on real and synthetic instances where the SNN-based QUBO solver often failed, while consuming measurably less energy than global solvers on CPU.

Abstract-- W e present an end-to-end pipeline for deploying reinforcement learning (RL) trained Artificial Neural Networks (ANNs) on neuromorphic hardware by converting them into spiking Sigma-Delta Neural Networks (SDNNs). W e demonstrate that an ANN policy trained entirely in simulation can be transformed into an SDNN compatible with Intel's Loihi 2 architecture, enabling low-latency and energy-efficient inference. As a test case, we use an RL policy for controlling the Astrobee free-flying robot, similar to a previously hardware in space-validated controller. The policy, trained with Rectified Linear Units (ReLUs), is converted to an SDNN and deployed on Intel's Loihi 2, then evaluated in NVIDIA's Omniverse Isaac Lab simulation environment for closed-loop control of Astrobee's motion. W e compare execution performance between GPU and Loihi 2. The results highlight the feasibility of using neuromorphic platforms for robotic control and establish a pathway toward energy-efficient, real-time neuromorphic computation in future space and terrestrial robotics applications.

Spiking neural networks (SNNs) promise energy-efficient artificial intelligence on neuromorphic hardware but struggle with tasks requiring both fast adaptation and long-term memory, especially in continual learning. We propose Local Timescale Gating (LT-Gate), a neuron model that combines dual time-constant dynamics with an adaptive gating mechanism. Each spiking neuron tracks information on a fast and a slow timescale in parallel, and a learned gate locally adjusts their influence. This design enables individual neurons to preserve slow contextual information while responding to fast signals, addressing the stability-plasticity dilemma. We further introduce a variance-tracking regularization that stabilizes firing activity, inspired by biological homeostasis. Empirically, LT-Gate yields significantly improved accuracy and retention in sequential learning tasks: on a challenging temporal classification benchmark it achieves about 51 percent final accuracy, compared to about 46 percent for a recent Hebbian continual-learning baseline and lower for prior SNN methods. Unlike approaches that require external replay or expensive orthogonalizations, LT-Gate operates with local updates and is fully compatible with neuromorphic hardware. In particular, it leverages features of Intel's Loihi chip (multiple synaptic traces with different decay rates) for on-chip learning. Our results demonstrate that multi-timescale gating can substantially enhance continual learning in SNNs, narrowing the gap between spiking and conventional deep networks on lifelong-learning tasks.

We have also shown scaling of the developmental algorithm with the network size in supplementary (S5).

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 in certain task settings, reinforcing SpiNNaker2's viability for real-time neuromorphic control and making the neuromorphic approach a compelling direction for efficient deep Q-learning.

Neuromorphic computing (NC) introduces a novel algorithmic paradigm representing a major shift from traditional digital computing of Von Neumann architectures. NC emulates or simulates the neural dynamics of brains in the form of Spiking Neural Networks (SNNs). Much of the research in NC has concentrated on machine learning applications and neuroscience simulations. This paper investigates the modelling and implementation of optimization algorithms and particularly metaheuristics using the NC paradigm as an alternative to Von Neumann architectures, leading to breakthroughs in solving optimization problems. Neuromorphic-based metaheuristics (Nheuristics) are supposed to be characterized by low power, low latency and small footprint. Since NC systems are fundamentally different from conventional Von Neumann computers, several challenges are posed to the design and implementation of Nheuristics. A guideline based on a classification and critical analysis is conducted on the different families of metaheuristics and optimization problems they address. We also discuss future directions that need to be addressed to expand both the development and application of Nheuristics.