paper-with-me

홈 › Papers

Spiking Decision Transformers: Local Plasticity, Phase-Coding, and Dendritic Routing for Low-Power Sequence Control

2025-08-29 · Vishal Pandey, Debasmita Biswas arxiv

Reinforcement learning agents based on Transformer architectures have achieved impressive performance on sequential decision-making tasks, but their reliance on dense matrix operations makes them ill-suited for energy-constrained, edge-oriented platforms. Spiking neural networks promise ultra-low-power, event-driven inference, yet no prior work has seamlessly merged spiking dynamics with return-conditioned sequence modeling. We present the Spiking Decision Transformer (SNN-DT), which embeds Leaky Integrate-and-Fire neurons into each self-attention block, trains end-to-end via surrogate gradients, and incorporates biologically inspired three-factor plasticity, phase-shifted spike-based positional encodings, and a lightweight dendritic routing module. Our implementation matches or exceeds standard Decision Transformer performance on classic control benchmarks (CartPole-v1, MountainCar-v0, Acrobot-v1, Pendulum-v1) while emitting fewer than ten spikes per decision, an energy proxy suggesting over four orders-of-magnitude reduction in per inference energy. By marrying sequence modeling with neuromorphic efficiency, SNN-DT opens a pathway toward real-time, low-power control on embedded and wearable devices.

📄 PDF Abstract BibTeX arXiv:2508.21505

Code (0)

등록된 구현이 없습니다.

Tasks

Reinforcement Learning

Similar Papers 제목 키워드 기반

Synchrony-Gated Plasticity with Dopamine Modulation for Spiking Neural Networks

2025-12-08 · Yuchen Tian, Samuel Tensingh, Jason Eshraghian, Nhan Duy Truong 외 arxiv

While surrogate backpropagation proves useful for training deep spiking neural networks (SNNs), incorporating biologically inspired local signals on a large scale remains challenging. This difficulty stems primarily from…

CoLaNET -- A Spiking Neural Network with Columnar Layered Architecture for Classification

2024-09-02 · Mikhail Kiselev

In the present paper, I describe a spiking neural network (SNN) architecture which, can be used in wide range of supervised learning classification tasks. It is assumed, that all participating signals (the classified obj…

Model-based Reinforcement Learning

Fluctuation-driven plasticity allows for flexible rewiring of neuronal assemblies

2022-03-09 · Federico Devalle, Alex Roxin

Synaptic connections in neuronal circuits are modulated by pre- and post-synaptic spiking activity. Heuristic models of this process of synaptic plasticity can provide excellent fits to results from in-vitro experiments …

Local learning through propagation delays in spiking neural networks

2022-10-27 · Jørgen Jensen Farner, Ola Huse Ramstad, Stefano Nichele, Kristine Heiney

We propose a novel local learning rule for spiking neural networks in which spike propagation times undergo activity-dependent plasticity. Our plasticity rule aligns pre-synaptic spike times to produce a stronger and mor…

Towards deep learning with spiking neurons in energy based models with contrastive Hebbian plasticity

2016-12-09 · Thomas Mesnard, Wulfram Gerstner, Johanni Brea

In machine learning, error back-propagation in multi-layer neural networks (deep learning) has been impressively successful in supervised and reinforcement learning tasks. As a model for learning in the brain, however, d…

Deep LearningGeneral ClassificationregressionReinforcement Learning+1