Deep Reinforcement Learning with Population-Coded Spiking Neural Network for Continuous Control

TL;DR

This paper introduces a population-coded spiking neural network trained with deep reinforcement learning for energy-efficient continuous control in robotics, demonstrating comparable performance to traditional methods with significantly reduced energy consumption on neuromorphic hardware.

Contribution

It presents a novel hybrid training approach for spiking neural networks using population coding and deep reinforcement learning, enabling scalable and energy-efficient control for real-world robotic tasks.

Findings

PopSAN achieves similar performance to deep networks on OpenAI gym tasks.

Loihi neuromorphic chip implementation reduces energy consumption by 140 times.

Hybrid RL enhances the scalability and robustness of spiking neural networks.

Abstract

The energy-efficient control of mobile robots is crucial as the complexity of their real-world applications increasingly involves high-dimensional observation and action spaces, which cannot be offset by limited on-board resources. An emerging non-Von Neumann model of intelligence, where spiking neural networks (SNNs) are run on neuromorphic processors, is regarded as an energy-efficient and robust alternative to the state-of-the-art real-time robotic controllers for low dimensional control tasks. The challenge now for this new computing paradigm is to scale so that it can keep up with real-world tasks. To do so, SNNs need to overcome the inherent limitations of their training, namely the limited ability of their spiking neurons to represent information and the lack of effective learning algorithms. Here, we propose a population-coded spiking actor network (PopSAN) trained in conjunction with a deep critic network using deep reinforcement learning (DRL). The population coding scheme dramatically increased the representation capacity of the network and the hybrid learning combined the training advantages of deep networks with the energy-efficient inference of spiking networks. To show the general applicability of our approach, we integrated it with a spectrum of both on-policy and off-policy DRL algorithms. We deployed the trained PopSAN on Intel's Loihi neuromorphic chip and benchmarked our method against the mainstream DRL algorithms for continuous control. To allow for a fair comparison among all methods, we validated them on OpenAI gym tasks. Our Loihi-run PopSAN consumed 140 times less energy per inference when compared against the deep actor network on Jetson TX2, and had the same level of performance. Our results support the efficiency of neuromorphic controllers and suggest our hybrid RL as an alternative to deep learning, when both energy-efficiency and robustness are important.