Evolving-to-Learn Reinforcement Learning Tasks with Spiking Neural Networks

02/24/2022
by   J. Lu, et al.
0

Inspired by the natural nervous system, synaptic plasticity rules are applied to train spiking neural networks with local information, making them suitable for online learning on neuromorphic hardware. However, when such rules are implemented to learn different new tasks, they usually require a significant amount of work on task-dependent fine-tuning. This paper aims to make this process easier by employing an evolutionary algorithm that evolves suitable synaptic plasticity rules for the task at hand. More specifically, we provide a set of various local signals, a set of mathematical operators, and a global reward signal, after which a Cartesian genetic programming process finds an optimal learning rule from these components. Using this approach, we find learning rules that successfully solve an XOR and cart-pole task, and discover new learning rules that outperform the baseline rules from literature.

READ FULL TEXT

page 1

page 2

page 3

page 4

research
01/05/2017

Membrane-Dependent Neuromorphic Learning Rule for Unsupervised Spike Pattern Detection

Several learning rules for synaptic plasticity, that depend on either sp...
research
02/08/2021

Evolving Neuronal Plasticity Rules using Cartesian Genetic Programming

We formulate the search for phenomenological models of synaptic plastici...
research
09/20/2022

A Spiking Neural Network Learning Markov Chain

In this paper, the question how spiking neural network (SNN) learns and ...
research
02/10/2020

Novelty Producing Synaptic Plasticity

A learning process with the plasticity property often requires reinforce...
research
02/04/2019

A Spiking Neural Network with Local Learning Rules Derived From Nonnegative Similarity Matching

The design and analysis of spiking neural network algorithms will be acc...
research
05/17/2015

Evolving Spiking Networks with Variable Resistive Memories

Neuromorphic computing is a brainlike information processing paradigm th...
research
08/31/2015

A Cognitive Architecture Based on a Learning Classifier System with Spiking Classifiers

Learning Classifier Systems (LCS) are population-based reinforcement lea...

Please sign up or login with your details

Forgot password? Click here to reset