All On-Board: Fully On-Chip Neuromorphic Q-Learning with Embedded CartPole Simulation
On the map: Deep reinforcement learning methods → Spiking and neuromorphic RL
Abstract (arXiv)
As AI models grow in size and usage, their energy demands increase dramatically, raising sustainability and economic concerns. Neuromorphic hardware, inspired by the energy efficiency of the brain, seeks to address this challenge by offering low-power, fast-processing alternatives to conventional computing. Such hardware is particularly well-suited to control systems deployed in resource-constrained environments, which are best trained via reinforcement learning (RL). This contribution presents the design and implementation of a fully on-chip, closed-loop Loihi 2 RL agent. Our neuromorphic circuit consists of a fully embedded Q-learning algorithm and an on-chip simulation of the CartPole-v0 environment on Loihi 2. Our Q-learning algorithm trained the same number of successful agents as the CPU implementation in only half the execution time and with two orders of magnitude less dynamic power. These findings demonstrate the viability of RL on neuromorphic hardware and highlight its promise for building energy-efficient, real-time, embedded AI systems.
Key facts. No citing papers in the map yet (data through 14 Oct 2026). Placed in Spiking and neuromorphic RL, one of 15 directions in Deep reinforcement learning methods. Builds on 16 of its 52 references that are in the map. First posted on arXiv 26 Sep 2026.
Builds on
16 of 52 references.
References · 16
- 2015Deep Compression: Compressing Deep Neural Networks with Pruning, Trained Quantization and Huffman Codingcited by 2,329
- 2020Deep Reinforcement Learning for Autonomous Driving: A Surveycited by 721
- 2019Green AIcited by 627
- 2017In-Datacenter Performance Analysis of a Tensor Processing Unitcited by 618
- 2016Quantized Neural Networks: Training Neural Networks with Low Precision Weights and Activationscited by 426
- 2016Safe, Multi-Agent, Reinforcement Learning for Autonomous Drivingcited by 311
- 2022The Carbon Footprint of Machine Learning Training Will Plateau, Then Shrinkcited by 184
- 2020Carbontracker: Tracking and Predicting the Carbon Footprint of Training Deep Learning Modelscited by 169
- 2021Multi-Agent Reinforcement Learning for Active Voltage Control on Power Distribution Networkscited by 54
- 2020Deep Reinforcement Learning with Population-Coded Spiking Neural Network for Continuous Controlcited by 49
- 2020Reinforcement co-Learning of Deep and Spiking Neural Networks for Energy-Efficient Mapless Navigation with Neuromorphic Hardwarecited by 36
- 2021Event-driven Vision and Control for UAVs on a Neuromorphic Chipcited by 34
4 more
- 2021The Backpropagation Algorithm Implemented on Spiking Neuromorphic Hardwarecited by 19
- 2024Safe Reinforcement Learning for Power System Control: A Reviewcited by 3
- 2015Graded, Dynamically Routable Information Processing with Synfire-Gated Synfire Chainscited by 2
- 2023A Neuromorphic Architecture for Reinforcement Learning from Real-Valued Observationscited by 2
Built on by
Not cited yet.
Similar, not cited
Close in wording, no citation either way
- 2025Hardware-Aware Fine-Tuning of Spiking Q-Networks on the SpiNNaker2 Neuromorphic Platform
- 2025Autonomous Reinforcement Learning Robot Control with Intel's Loihi 2 Neuromorphic Hardware
- 2025Bellman Memory Units: A neuromorphic framework for synaptic reinforcement learning with an evolving network topology
- 2024Neuromorphic force-control in an industrial task: validating energy and latency benefits ↗
- 2025Enabling Efficient Processing of Spiking Neural Networks with On-Chip Learning on Commodity Neuromorphic Processors for Edge AI Systems
- 2024Neuromorphic dreaming: A pathway to efficient learning in artificial agents
- 2026Training slow silicon neurons to control extremely fast robots with spiking reinforcement learning
- 2024NeuroNAS: Enhancing Efficiency of Neuromorphic In-Memory Computing for Intelligent Mobile Agents through Hardware-Aware Spiking Neural Architecture Search