A multi-agent evolutionary robotics framework to train spiking neural networks

12/07/2020
by   Souvik Das, et al.
0

A novel multi-agent evolutionary robotics (ER) based framework, inspired by competitive evolutionary environments in nature, is demonstrated for training Spiking Neural Networks (SNN). The weights of a population of SNNs along with morphological parameters of bots they control in the ER environment are treated as phenotypes. Rules of the framework select certain bots and their SNNs for reproduction and others for elimination based on their efficacy in capturing food in a competitive environment. While the bots and their SNNs are given no explicit reward to survive or reproduce via any loss function, these drives emerge implicitly as they evolve to hunt food and survive within these rules. Their efficiency in capturing food as a function of generations exhibit the evolutionary signature of punctuated equilibria. Two evolutionary inheritance algorithms on the phenotypes, Mutation and Crossover with Mutation, are demonstrated. Performances of these algorithms are compared using ensembles of 100 experiments for each algorithm. We find that Crossover with Mutation promotes 40 significant margin.

READ FULL TEXT

page 1

page 2

page 3

page 4

research
12/16/2022

Emergent communication enhances foraging behaviour in evolved swarms controlled by Spiking Neural Networks

Social insects such as ants communicate via pheromones which allows them...
research
12/21/2011

Evolution of sustained foraging in 3D environments with physics

Artificially evolving foraging behavior in simulated legged animals has ...
research
12/20/2021

Evolutionary Hierarchical Harvest Schedule Optimization for Food Waste Prevention

In order to avoid disadvantages of monocropping for soil and environment...
research
09/21/2020

A multi-agent model for growing spiking neural networks

Artificial Intelligence has looked into biological systems as a source o...
research
02/21/2015

Reinforcement Learning in a Neurally Controlled Robot Using Dopamine Modulated STDP

Recent work has shown that dopamine-modulated STDP can solve many of the...
research
02/18/2023

Eco-evolutionary Dynamics of Non-episodic Neuroevolution in Large Multi-agent Environments

Neuroevolution (NE) has recently proven a competitive alternative to lea...
research
07/27/2022

Towards the Neuroevolution of Low-level Artificial General Intelligence

In this work, we argue that the search for Artificial General Intelligen...

Please sign up or login with your details

Forgot password? Click here to reset