AI Chat AI Image Generator AI Video Text to Speech

Info-Evo: Using Information Geometry to Guide Evolutionary Program Learning

02/20/2021

∙

by Ben Goertzel, et al.

∙

∙

A novel optimization strategy, Info-Evo, is described, in which natural gradient search using nonparametric Fisher information is used to provide ongoing guidance to an evolutionary learning algorithm, so that the evolutionary process preferentially moves in the directions identified as "shortest paths" according to the natural gradient. Some specifics regarding the application of this approach to automated program learning are reviewed, including a strategy for integrating Info-Evo into the MOSES program learning framework.

research

∙ 08/15/2022

Cooperative guidance of multiple missiles: a hybrid co-evolutionary approach

Cooperative guidance of multiple missiles is a challenging task with rig...

0 Junda Chen, et al. ∙

research

∙ 07/16/2020

CoNES: Convex Natural Evolutionary Strategies

We present a novel algorithm – convex natural evolutionary strategies (C...

6 Sushant Veer, et al. ∙

research

∙ 09/27/2021

Self-Replicating Neural Programs

In this work, a neural network is trained to replicate the code that tra...

0 Samuel Schmidgall, et al. ∙

research

∙ 10/02/2022

Natural Gradient Ascent in Evolutionary Games

We study evolutionary games with a continuous trait space in which repli...

0 Vladimir Jaćimović, et al. ∙

research

∙ 04/13/2023

Learning by Viewing: Generating Test Inputs for Games by Integrating Human Gameplay Traces in Neuroevolution

Although automated test generation is common in many programming domains...

0 Patric Feldmeier, et al. ∙

research

∙ 06/26/2018

Guided evolutionary strategies: escaping the curse of dimensionality in random search

Many applications in machine learning require optimizing a function whos...

2 Niru Maheswaranathan, et al. ∙

research

∙ 08/27/2011

Providing information can be a stable non-cooperative evolutionary strategy

Human language is still an embarrassment for evolutionary theory, as the...

0 Jean-Louis Dessalles, et al. ∙