arXiv subjects

Nathaniel Virgo

Publications and source records attributed to Nathaniel Virgo.

16 recordsLinked to original sources

arXiv2026

Towards chemistries in dynamical systems

Chemistry describes aspects of the universe in terms of molecules and their reactions. In this exploratory work we present a way to describe aspects of any dynamical system in similar terms. To describe a dynamical system in this way three decisions have to be made. The first is how many different "places" there are at which molecules or chemical species can occur; the second is how to determine the species present (or not) at each place; and the third is the set of transitions and reactions that can occur between the species in the various places. For these choices to be compatible with the state update of the dynamical system each state must be able to determine transitions that take the currently occurring molecules to those occurring in the updated state. We also propose an additional requirement that there is always a unique way to choose the least amount of transitions occurring during state updates. We discuss gliders in the game of life cellular and argue that when following their definition of according to Randall Beer they satisfy the additional criterion as well. We also point out some issues with the approach.

cs.DM↗

arXiv2026

Bayesian updates from coalgebraic determinisation

The powerset construction is the classical determinisation procedure for nondeterministic finite automata. In the coalgebraic setting, this construction has been generalised to structured coalgebras, which are coalgebras equipped with extra data. For stochastic Moore machines over the distribution monad, a type of structured coalgebra, the determinisation construction induces a semantics assigning to each finite input word a distribution on the current output. This semantics is appropriate when only the current output matters, but it is too coarse for settings in which intermediate observations must also be taken into account, as is typical for agents solving POMDPs in control theory and reinforcement learning. In these contexts, agents need to condition on all realised observations, not just the final one, so to better plan for the future. This has been addressed from a category theoretic perspective through a procedure called ``unifilarisation'', which (in our context) takes a stochastic Mealy machine and produces a machine whose states are priors over the original state space and whose transitions are given by Bayesian filtering. Here we show that unifilarisation is an instance of coalgebraic determinisation. We work with Mealy machines over monads equipped with extra structure generalising the notion of the support of a distribution. We show that in this setting, unifilarisation arises from the general determinisation procedure. We then compare the resulting final coalgebra semantics with the Moore-style one. Instead of assigning only a distribution on current outputs to each finite input word, it yields causal stochastic behaviours, that is, families mapping input words to distributions on output words compatible with the ``causality'' constraint that outputs cannot depend on future inputs.

cs.LO↗

arXiv2025

A "good regulator theorem" for embodied agents

In a classic paper, Conant and Ashby claimed that "every good regulator of a system must be a model of that system." Artificial Life has produced many examples of systems that perform tasks with apparently no model in sight; these suggest Conant and Ashby's theorem doesn't easily generalise beyond its restricted setup. Nevertheless, here we show that a similar intuition can be fleshed out in a different way: whenever an agent is able to perform a regulation task, it is possible for an observer to interpret it as having "beliefs" about its environment, which it "updates" in response to sensory input. This notion of belief updating provides a notion of model that is more sophisticated than Conant and Ashby's, as well as a theorem that is more broadly applicable. However, it necessitates a change in perspective, in that the observer plays an essential role in the theory: models are not a mere property of the system but are imposed on it from outside. Our theorem holds regardless of whether the system is regulating its environment in a classic control theory setup, or whether it's regulating its own internal state; the model is of its environment either way. The model might be trivial, however, and this is how the apparent counterexamples are resolved.

cs.AI↗

arXiv2025

A Bayesian Interpretation of the Internal Model Principle

The internal model principle, originally proposed in the theory of control of linear systems, nowadays represents a more general class of results in control theory and cybernetics. The central claim of these results is that, under suitable assumptions, if a system (a controller) can regulate against a class of external inputs (from the environment), it is because the system contains a model of the system causing these inputs, which can be used to generate signals counteracting them. Similar claims on the role of internal models appear also in cognitive science, especially in modern Bayesian treatments of cognitive agents, often suggesting that a system (a human subject, or some other agent) models its environment to adapt against disturbances and perform goal-directed behaviour. It is however unclear whether the Bayesian internal models discussed in cognitive science bear any formal relation to the internal models invoked in standard treatments of control theory. Here, we first review the internal model principle and present a precise formulation of it using concepts inspired by categorical systems theory. This leads to a formal definition of ``model'' generalising its use in the internal model principle. Although this notion of model is not a priori related to the notion of Bayesian reasoning, we show that it can be seen as a special case of possibilistic Bayesian filtering. This result is based on a recent line of work formalising, using Markov categories, a notion of ``interpretation'', describing when a system can be interpreted as performing Bayesian filtering on an outside world in a consistent way.

math.OC↗

arXiv2025

Formalising the intentional stance 2: a coinductive approach

Given a stochastic process with inputs and outputs, how might its behaviour be related to pursuit of a goal? We model this using 'transducers', objects that capture only the external behaviour of a system and not its internal state. A companion paper summarises our results for cognitive scientists; the current paper gives formal definitions and proofs. To formalise the concept of a system that behaves as if it were pursuing a goal, we consider what happens when a transducer (a 'policy') is coupled to another transducer that comes equipped with a success condition (a 'teleo-environment'). An optimal policy is identified with a transducer that behaves as if it were perfectly rational in the pursuit of a goal; our framework also allows us to model constrained rationality. Optimal policies obey a version of Bellman's principle: a policy that's optimal in one time step will again be optimal in the next time step, but with respect to a different teleo-environment (obtained from the original one by a modified version of Bayesian filtering). This property sometimes also applies to the bounded-rational case; we give a sufficient condition. A policy is deterministic if and only if there exists a teleo-environment for which it is uniquely optimal among the set of all policies; we relate this to classical representation theorems from decision theory. This result need not hold in the bounded-rational case; we give an example related to the absent-minded driver problem. The formalism is defined using coinduction, following the style proposed by Czajka.

math.OC↗

arXiv2024

Formalising the intentional stance 1: attributing goals and beliefs to stochastic processes

This article presents a formalism inspired by Dennett's notion of the intentional stance. Whereas Dennett's treatment of these concepts is informal, we aim to provide a more formal analogue. We introduce a framework based on stochastic processes with inputs and outputs, in which we can talk precisely about *interpreting* systems as having *normative-epistemic states*, which combine belief-like and desire-like features. Our framework is based on optimality but nevertheless allows us to model some forms of bounded cognition. One might expect that the systems that can be described in normative-epistemic terms would be some special subset of all systems, but we show that this is not the case: every system admits a (possibly trivial) normative-epistemic interpretation, and those that can be *uniquely specified* by a normative-epistemic description are exactly the deterministic ones. Finally, we show that there is a suitable notion of Bayesian updating for normative-epistemic states, which we call *value-laden filtering*, since it involves both normative and epistemic elements. For unbounded cognition it is always permissible to attribute beliefs that update in this way. This is not always the case for bounded cognition, but we give a sufficient condition under which it is. This paper gives an overview of our framework aimed at cognitive scientists, with a formal mathematical treatment given in a companion paper.

math.OC↗

arXiv2023

Unifilar Machines and the Adjoint Structure of Bayesian Filtering

We elucidate the mathematical structure of Bayesian filtering, and Bayesian inference more broadly, by applying recent work on category theoretical probability, specifically the concept of a strongly representable Markov category. We show that filtering, along with related concepts such as conjugate priors, arise from an adjunction: the process of taking a hidden Markov process is right adjoint to a forgetful functor. This has an interesting consequence. In practice, filtering is usually implemented using parametrised families of distributions. The Kalman filter is a particularly important example, which uses Gaussians. Rather than calculating a new posterior each time, the implementation only needs to udpate the parameters. This structure arises naturally from our adjunction; the correctness of such a model is witnessed by a map from the model into the system being modelled. Conjugate priors arise from this construction as a special case. In showing this we define a notion of unifilar machine, which has its origins in the literature on epsilon-machines. Unifilar machines are useful as models of the "observable behaviour" of stochastic systems; we show additionally that in the Kleisli category of the distribution monad there is a terminal unifilar machine, and its elements are controlled stochastic processes, mapping sequences of the input alphabet probabilistically to sequences of the output alphabet.

math.PR↗

arXiv2022

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

Under what circumstances can a system be said to have beliefs and goals, and how do such agency-related features relate to its physical state? Recent work has proposed a notion of interpretation map, a function that maps the state of a system to a probability distribution representing its beliefs about an external world. Such a map is not completely arbitrary, as the beliefs it attributes to the system must evolve over time in a manner that is consistent with Bayes' theorem, and consequently the dynamics of a system constrain its possible interpretations. Here we build on this approach, proposing a notion of interpretation not just in terms of beliefs but in terms of goals and actions. 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. An agent is then a system together with an interpretation of this system as a POMDP solution. Although POMDPs are not the only possible formulation of what it means to have a goal, this nevertheless represents a step towards a more general formal definition of what it means for a system to be an agent.

cs.AI↗

arXiv2021

Interpreting Dynamical Systems as Bayesian Reasoners

A central concept in active inference is that the internal states of a physical system parametrise probability measures over states of the external world. These can be seen as an agent's beliefs, expressed as a Bayesian prior or posterior. Here we begin the development of a general theory that would tell us when it is appropriate to interpret states as representing beliefs in this way. We focus on the case in which a system can be interpreted as performing either Bayesian filtering or Bayesian inference. We provide formal definitions of what it means for such an interpretation to exist, using techniques from category theory.

cs.AI↗

arXiv2019

Information Decomposition based on Cooperative Game Theory

We offer a new approach to the information decomposition problem in information theory: given a 'target' random variable co-distributed with multiple 'source' variables, how can we decompose the mutual information into a sum of non-negative terms that quantify the contributions of each random variable, not only individually but also in combination? We derive our composition from cooperative game theory. It can be seen as assigning a "fair share" of the mutual information to each combination of the source variables. Our decomposition is based on a different lattice from the usual 'partial information decomposition' (PID) approach, and as a consequence our decomposition has a smaller number of terms: it has analogs of the synergy and unique information terms, but lacks terms corresponding to redundancy. Because of this, it is able to obey equivalents of the axioms known as 'local positivity' and 'identity', which cannot be simultaneously satisfied by a PID measure.

cs.IT↗

arXiv2018

On the potential for open-endedness in neural networks

Natural evolution gives the impression of leading to an open-ended process of increasing diversity and complexity. If our goal is to produce such open-endedness artificially, this suggests an approach driven by evolutionary metaphor. On the other hand, techniques from machine learning and artificial intelligence are often considered too narrow to provide the sort of exploratory dynamics associated with evolution. 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. We then show how these problems map onto similar issues in the machine learning approach, and discuss how the same insights and solutions which alleviated those barriers in evolutionary approaches can be ported over. At the same time, the form these issues take in the machine learning formulation suggests new ways to analyze and resolve barriers to open-endedness. Ultimately, we hope to inspire researchers to be able to interchangeably use evolutionary and gradient-descent-based machine learning methods to approach the design and creation of open-ended systems.

nlin.AO↗

arXiv2018

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

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. The space is structured towards answering a particular distribution of questions, which are used in a supervised way to train the attentional neural network. We find that in a 2d exploration task, the structure of the space successfully encodes local sensory-motor contingencies such that even a greedy local `do the most novel action' policy with no reinforcement learning or evolution can explore the space quickly. We also apply this to a high/low number guessing game task, and find that guessing according to the learned attention profile performs active inference and can discover the correct number more quickly than an exact but passive approach.

cs.AI↗

arXiv2018

Chemical Heredity as Group Selection at the Molecular Level

Many examples of cooperation exist in biology. In chemical systems however, which can sometimes be quite complex, we do not appear to observe intricate cooperative interactions. A key question for the origin of life, is then how can molecular cooperation first arise in an abiotic system prior to the emergence of biological replication. We postulate that selection at the molecular level is a driving force behind the complexification of chemical systems, particularly during the origins of life. In the theory of multilevel selection the two selective forces are: within-group and between-group, where the former tends to favor "selfish" replication of individuals and the latter favor cooperation between individuals enhancing the replication of the group as a whole. These forces can be quantified using the Price equation, which is a standard tool used in evolutionary biology to quantify evolutionary change. Our central claim is that replication and heredity in chemical systems are subject to selection, and quantifiable using the multilevel Price equation. We demonstrate this using the Graded Autocatalysis Replication Domain computer model, describing simple protocell composed out of molecules and its replication, which respectively analogue to the group and the individuals. In contrast to previous treatments of this model, we treat the lipid molecules themselves as replicating individuals and the protocells they form as groups of individuals. Our goal is to demonstrate how evolutionary biology tools and concepts can be applied in chemistry and we suggest that molecular cooperation may arise as a result of group selection. Further, the biological relation of parent-progeny is proposed to be analogue to the reactant-product relation in chemistry, thus allowing for tools from evolutionary biology to be applied to chemistry and would deepen the connection between chemistry and biology.

q-bio.PE↗

arXiv2017

Selection first path to the origin of life

We propose an alternative to the prevailing two origin of life narratives, one based on a replicator first hypothesis, and one based on a metabolism first hypothesis. Both hypotheses have known difficulties: All known evolvable molecular replicators such as RNA require complex chemical (enzymatic) machinery for the replication process. Likewise, contemporary cellular metabolisms require several enzymatically catalyzed steps, and it is difficult to identify a non-enzymatic path to their realization. We propose that there must have been precursors to both replication and metabolism that enable a form of selection to take place through action of simple chemical and physical processes. We model a concrete example of such a process, repeated sequestration of binary molecular combinations after exposure to an environment with a broad distribution of chemical components, as might be realized experimentally in in a repeated wet-dry cycle. We show that the repeated sequestration dynamics results in a selective amplification of a very small subset of molecular species present in the environment, thus providing a candidate primordial selection process.

q-bio.PE↗

arXiv2016

Permutation-equivariant neural networks applied to dynamics prediction

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. In comparison, there are a number of problems in which there are a number of different inputs which are all 'of the same type' --- multiple particles, multiple agents, multiple stock prices, etc. The corresponding symmetry to this is permutation symmetry, in that the algorithm should not depend on the specific ordering of the input data. We discuss a permutation-invariant neural network layer in analogy to convolutional layers, and show the ability of this architecture to learn to predict the motion of a variable number of interacting hard discs in 2D. In the same way that convolutional layers can generalize to different image sizes, the permutation layer we describe generalizes to different numbers of objects.

cs.CV↗

arXiv2013

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

Due to recent advances in synthetic biology and artificial life, the origin of life is currently a hot topic of research. We review the literature and argue that the two traditionally competing "replicator-first" and "metabolism-first" approaches are merging into one integrated theory of individuation and evolution. We contribute to the maturation of this more inclusive approach by highlighting some problematic assumptions that still lead to an impoverished conception of the phenomenon of life. In particular, we argue that the new consensus has so far failed to consider the relevance of intermediate timescales. We propose that an adequate theory of life must account for the fact that all living beings are situated in at least four distinct timescales, which are typically associated with metabolism, motility, development, and evolution. On this view, self-movement, adaptive behavior and morphological changes could have already been present at the origin of life. In order to illustrate this possibility we analyze a minimal model of life-like phenomena, namely of precarious, individuated, dissipative structures that can be found in simple reaction-diffusion systems. Based on our analysis we suggest that processes in intermediate timescales could have already been operative in prebiotic systems. They may have facilitated and constrained changes occurring in the faster- and slower-paced timescales of chemical self-individuation and evolution by natural selection, respectively.

cs.AI↗