Dynamic Action Selection in OpenAI using Spiking Neural Networks

The 32nd International Florida Artificial Intelligence Research Society Conference, 2019

Chad Peters, Terrence C. Stewart, Robert L. West, Babak Esfandiari

Abstract

Modelling biologically-plausible neural structures for intelligent agents presents a unique challenge when operating in real-time domains. Neurons in our brains have different response properties, firing rates, and propagation lengths, creating noise that cannot be reliably decoded. This research explores the strengths and limitations of LIF spiking neuron ensembles for application in OpenAI virtual environments. Topics discussed include how we represent arbitrary environmental signals from multiple senses, choosing between equally viable actions in a given scenario, and how one can create a generic model that can learn and operate in a verity of situations.

Full text links

 External link

Conference Proceedings

Booktitle
The 32nd International Florida Artificial Intelligence Research Society Conference
Organization
FLAIRS

Cite

Plain text

BibTeX