Enregistré dans:
Détails bibliographiques
Auteurs principaux: Ambrosini, Irene, Blakowski, Ingo, Zendrikov, Dmitrii, Capone, Cristiano, Gava, Luna, Indiveri, Giacomo, De Luca, Chiara, Bartolozzi, Chiara
Format: Preprint
Publié: 2026
Sujets:
Accès en ligne:https://arxiv.org/abs/2601.21548
Tags: Ajouter un tag
Pas de tags, Soyez le premier à ajouter un tag!
_version_ 1866917231397437440
author Ambrosini, Irene
Blakowski, Ingo
Zendrikov, Dmitrii
Capone, Cristiano
Gava, Luna
Indiveri, Giacomo
De Luca, Chiara
Bartolozzi, Chiara
author_facet Ambrosini, Irene
Blakowski, Ingo
Zendrikov, Dmitrii
Capone, Cristiano
Gava, Luna
Indiveri, Giacomo
De Luca, Chiara
Bartolozzi, Chiara
contents Air hockey demands split-second decisions at high puck velocities, a challenge we address with a compact network of spiking neurons running on a mixed-signal analog/digital neuromorphic processor. By co-designing hardware and learning algorithms, we train the system to achieve successful puck interactions through reinforcement learning in a remarkably small number of trials. The network leverages fixed random connectivity to capture the task's temporal structure and adopts a local e-prop learning rule in the readout layer to exploit event-driven activity for fast and efficient learning. The result is real-time learning with a setup comprising a computer and the neuromorphic chip in-the-loop, enabling practical training of spiking neural networks for robotic autonomous systems. This work bridges neuroscience-inspired hardware with real-world robotic control, showing that brain-inspired approaches can tackle fast-paced interaction tasks while supporting always-on learning in intelligent machines.
format Preprint
id arxiv_https___arxiv_org_abs_2601_21548
institution arXiv
publishDate 2026
record_format arxiv
spellingShingle Training slow silicon neurons to control extremely fast robots with spiking reinforcement learning
Ambrosini, Irene
Blakowski, Ingo
Zendrikov, Dmitrii
Capone, Cristiano
Gava, Luna
Indiveri, Giacomo
De Luca, Chiara
Bartolozzi, Chiara
Robotics
Artificial Intelligence
Emerging Technologies
Air hockey demands split-second decisions at high puck velocities, a challenge we address with a compact network of spiking neurons running on a mixed-signal analog/digital neuromorphic processor. By co-designing hardware and learning algorithms, we train the system to achieve successful puck interactions through reinforcement learning in a remarkably small number of trials. The network leverages fixed random connectivity to capture the task's temporal structure and adopts a local e-prop learning rule in the readout layer to exploit event-driven activity for fast and efficient learning. The result is real-time learning with a setup comprising a computer and the neuromorphic chip in-the-loop, enabling practical training of spiking neural networks for robotic autonomous systems. This work bridges neuroscience-inspired hardware with real-world robotic control, showing that brain-inspired approaches can tackle fast-paced interaction tasks while supporting always-on learning in intelligent machines.
title Training slow silicon neurons to control extremely fast robots with spiking reinforcement learning
topic Robotics
Artificial Intelligence
Emerging Technologies
url https://arxiv.org/abs/2601.21548