A Dual-Memory Architecture for Reinforcement Learning on Neuromorphic Platforms

TL;DR

This paper presents a flexible, energy-efficient dual-memory architecture for reinforcement learning on neuromorphic platforms, demonstrating its effectiveness through implementation on an Intel processor for various tasks.

Contribution

It introduces a novel dual-memory architecture tailored for neuromorphic hardware, enabling efficient reinforcement learning in real-world applications.

Findings

Successfully implemented on Intel neuromorphic processor

Solves a variety of RL tasks using spiking dynamics

Demonstrates energy-efficient RL solutions

Abstract

Reinforcement learning (RL) is a foundation of learning in biological systems and provides a framework to address numerous challenges with real-world artificial intelligence applications. Efficient implementations of RL techniques could allow for agents deployed in edge-use cases to gain novel abilities, such as improved navigation, understanding complex situations and critical decision making. Towards this goal, we describe a flexible architecture to carry out reinforcement learning on neuromorphic platforms. This architecture was implemented using an Intel neuromorphic processor and demonstrated solving a variety of tasks using spiking dynamics. Our study proposes a usable energy efficient solution for real-world RL applications and demonstrates applicability of the neuromorphic platforms for RL problems.