# Learning to Control Dynamical Agents via Spiking Neural Networks and Metropolis-Hastings Sampling

arXiv: https://arxiv.org/abs/2507.09540 · HTML: https://mlsanity.com/paper/2507.09540/

## 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 9 of its 30 references that are in the map.
- First posted on arXiv 13 Jul 2025.

## Placed in

- Deep reinforcement learning methods / [Spiking and neuromorphic RL](https://mlsanity.com/deeprl/spiking-and-neuromorphic-rl/)

## Builds on (most cited first, 9 of 9)

- [Proximal Policy Optimization Algorithms](https://mlsanity.com/paper/1707.06347/) (2017)
- [OpenAI Gym](https://mlsanity.com/paper/1606.01540/) (2016)
- [Surrogate Gradient Learning in Spiking Neural Networks](https://mlsanity.com/paper/1901.09948/) (2019)
- [Hands-on Bayesian Neural Networks -- a Tutorial for Deep Learning Users](https://mlsanity.com/paper/2007.06823/) (2020)
- [Deep Learning in Spiking Neural Networks](https://mlsanity.com/paper/1804.08150/) (2018)
- [Reinforcement learning](https://mlsanity.com/paper/2405.10369/) (2024)
- [SuperSpike: Supervised learning in multi-layer spiking neural networks](https://mlsanity.com/paper/1705.11146/) (2017)
- [Reinforcement Learning with Feedback-modulated TD-STDP](https://mlsanity.com/paper/2008.13044/) (2020)
- [Towards Chip-in-the-loop Spiking Neural Network Training via Metropolis-Hastings Sampling](https://mlsanity.com/paper/2402.06284/) (2024)

## Abstract (arXiv)

Spiking Neural Networks (SNNs) offer biologically inspired, energy-efficient alternatives to traditional Deep Neural Networks (DNNs) for real-time control systems. However, their training presents several challenges, particularly for reinforcement learning (RL) tasks, due to the non-differentiable nature of spike-based communication. In this work, we introduce what is, to our knowledge, the first framework that employs Metropolis-Hastings (MH) sampling, a Bayesian inference technique, to train SNNs for dynamical agent control in RL environments without relying on gradient-based methods. Our approach iteratively proposes and probabilistically accepts network parameter updates based on accumulated reward signals, effectively circumventing the limitations of backpropagation while enabling direct optimization on neuromorphic platforms. We evaluated this framework on two standard control benchmarks: AcroBot and CartPole. The results demonstrate that our MH-based approach outperforms conventional Deep Q-Learning (DQL) baselines and prior SNN-based RL approaches in terms of maximizing the accumulated reward while minimizing network resources and training episodes.