Search Results for author: Nathaniel Virgo

Found 6 papers, 2 papers with code

Interpreting systems as solving POMDPs: a step towards a formal understanding of agency

no code implementations4 Sep 2022 Martin Biehl, Nathaniel Virgo

To do this we make use of the existing theory of partially observable Markov processes (POMDPs): we say that a system can be interpreted as a solution to a POMDP if it not only admits an interpretation map describing its beliefs about the hidden state of a POMDP but also takes actions that are optimal according to its belief state.

Interpreting Dynamical Systems as Bayesian Reasoners

no code implementations27 Dec 2021 Nathaniel Virgo, Martin Biehl, Simon McGregor

A central concept in active inference is that the internal states of a physical system parametrise probability measures over states of the external world.

Bayesian Inference

On the potential for open-endedness in neural networks

no code implementations12 Dec 2018 Nicholas Guttenberg, Nathaniel Virgo, Alexandra Penn

In this paper, we hope to bridge that gap by reviewing common barriers to open-endedness in the evolution-inspired approach and how they are dealt with in the evolutionary case - collapse of diversity, saturation of complexity, and failure to form new kinds of individuality.

BIG-bench Machine Learning Diversity

Being curious about the answers to questions: novelty search with learned attention

1 code implementation1 Jun 2018 Nicholas Guttenberg, Martin Biehl, Nathaniel Virgo, Ryota Kanai

We investigate the use of attentional neural network layers in order to learn a `behavior characterization' which can be used to drive novelty search and curiosity-based policies.

Permutation-equivariant neural networks applied to dynamics prediction

2 code implementations14 Dec 2016 Nicholas Guttenberg, Nathaniel Virgo, Olaf Witkowski, Hidetoshi Aoki, Ryota Kanai

The introduction of convolutional layers greatly advanced the performance of neural networks on image tasks due to innately capturing a way of encoding and learning translation-invariant operations, matching one of the underlying symmetries of the image domain.


Motility at the origin of life: Its characterization and a model

no code implementations11 Nov 2013 Tom Froese, Nathaniel Virgo, Takashi Ikegami

On this view, self-movement, adaptive behavior and morphological changes could have already been present at the origin of life.

Artificial Life

Cannot find the paper you are looking for? You can Submit a new open access paper.