231 citations · 828 across the 31 of their papers we have counts for
34 papers
Renormalising Generative Models for Active Inference: Foundations, Derivations, and Verification
Karim Zaghw, Andrew Pashea, Marc Pritsch +3
Active inference offers a unified framework for perception, learning, and action, but scaling discrete active-inference models to rich spatial and temporal domains remains difficul…
Learning POMDP World Models from Observations with Language-Model Priors
Valentin Six, Frederik Panse, Mathis Fajeau +7
Whether navigating a building, operating a robot, or playing a game, an agent that acts effectively in an environment must first learn an internal model of how that environment wor…
Active inference and artificial reasoning
Karl Friston, Lancelot Da Costa, Alexander Tschantz +4
This technical note considers the sampling of outcomes that provide the greatest amount of information about the structure of underlying world models. This generalisation furnishes…
Natural Building Blocks for Structured World Models: Theory, Evidence, and Scaling
Lancelot Da Costa, Sanjeev Namjoshi, Mohammed Abbas Ansari +1
The field of world modeling is fragmented, with researchers developing bespoke architectures that rarely build upon each other. We propose a framework that specifies the natural bu…
Bayesian Predictive Coding
Alexander Tschantz, Magnus Koudahl, Hampus Linander +4
Predictive coding (PC) is an influential theory of information processing in the brain, providing a biologically plausible alternative to backpropagation. It is motivated in terms…
Probabilistic Principles for Biophysics and Neuroscience: Entropy Production, Bayesian Mechanics & the Free-Energy Principle
Lancelot Da Costa
This thesis focuses on three fundamental aspects of biological systems; namely, entropy production, Bayesian mechanics, and the free-energy principle. The contributions are threefo…
Toward Universal and Interpretable World Models for Open-ended Learning Agents
Lancelot Da Costa
We introduce a generic, compositional and interpretable class of generative world models that supports open-ended learning agents. This is a sparse class of Bayesian networks capab…
Possible Principles for Aligned Structure Learning Agents
Lancelot Da Costa, Tomáš Gavenčiak, David Hyland +5
This paper offers a roadmap for the development of scalable aligned artificial intelligence (AI) from first principle descriptions of natural intelligence. In brief, a possible pat…
A Rosetta Stone Hypothesis for Neurophenomenology: Mathematical Predictions from Predictive Processing
Lancelot Da Costa, Anil K. Seth, Karl Friston +2
Consciousness science faces the challenge of bridging first-person experience with third-person empirical measurements. Neurophenomenology aims to build such `generative passages'…
A theory of generalised coordinates for stochastic differential equations
Lancelot Da Costa, Nathaël Da Costa, Conor Heins +5
Stochastic differential equations are ubiquitous modelling tools in physics and the sciences. In most modelling scenarios, random fluctuations driving dynamics or motion have some…
From pixels to planning: scale-free active inference
Karl Friston, Conor Heins, Tim Verbelen +7
This paper describes a discrete state-space model -- and accompanying methods -- for generative modelling. This model generalises partially observed Markov decision processes to in…
Metacognitive particles, mental action and the sense of agency
Lars Sandved-Smith, Lancelot Da Costa
This paper articulates metacognition using the language of statistical physics and Bayesian mechanics. Metacognitive beliefs, defined as beliefs about beliefs, find a natural descr…
Towards a Bayesian mechanics of metacognitive particles: A commentary on "Path integrals, particular kinds, and strange things" by Friston, Da Costa, Sakthivadivel, Heins, Pavliotis, Ramstead, and Parr
Lancelot Da Costa, Lars Sandved-Smith
What could metacognition look like in simple physical terms? We define metacognition as having beliefs about beliefs, which can be articulated very simply using the language of sta…
Active Inference as a Model of Agency
Lancelot Da Costa, Samuel Tenka, Dominic Zhao +1
Is there a canonical way to think of agency beyond reward maximisation? In this paper, we show that any type of behaviour complying with physically sound assumptions about how macr…
Sample Path Regularity of Gaussian Processes from the Covariance Kernel
Nathaël Da Costa, Marvin Pförtner, Lancelot Da Costa +1
Gaussian processes (GPs) are the most common formalism for defining probability distributions over spaces of functions. While applications of GPs are myriad, a comprehensive unders…
Supervised structure learning
Karl J. Friston, Lancelot Da Costa, Alexander Tschantz +10
This paper concerns structure learning or discovery of discrete generative models. It focuses on Bayesian model selection and the assimilation of training data or content, with a s…
On efficient computation in active inference
Aswin Paul, Noor Sajid, Lancelot Da Costa +1
Despite being recognized as neurobiologically plausible, active inference faces difficulties when employed to simulate intelligent behaviour in complex environments due to its comp…
Collective behavior from surprise minimization
Conor Heins, Beren Millidge, Lancelot da Costa +3
Collective motion is ubiquitous in nature; groups of animals, such as fish, birds, and ungulates appear to move as a whole, exhibiting a rich behavioral repertoire that ranges from…
The entropy production of stationary diffusions
Lancelot Da Costa, Grigorios A. Pavliotis
The entropy production rate is a central quantity in non-equilibrium statistical physics, scoring how far a stochastic process is from being time-reversible. In this paper, we comp…
Path integrals, particular kinds, and strange things
Karl Friston, Lancelot Da Costa, Dalton A. R. Sakthivadivel +4
This paper describes a path integral formulation of the free energy principle. The ensuing account expresses the paths or trajectories that a particle takes as it evolves over time…
Modelling non-reinforced preferences using selective attention
Noor Sajid, Panagiotis Tigas, Zafeirios Fountas +3
How can artificial agents learn non-reinforced preferences to continuously adapt their behaviour to a changing environment? We decompose this question into two challenges: () en…
Sparse coupling and Markov blankets: A comment on "How particular is the physics of the Free Energy Principle?" by Aguilera, Millidge, Tschantz and Buckley
Conor Heins, Lancelot Da Costa
In this commentary, we respond to a technical analysis of the Free Energy Principle (hereafter: FEP) presented in "How particular is the physics of the Free Energy Principle" by Ag…
On Bayesian Mechanics: A Physics of and by Beliefs
Maxwell J. D. Ramstead, Dalton A. R. Sakthivadivel, Conor Heins +5
The aim of this paper is to introduce a field of study that has emerged over the last decade called Bayesian mechanics. Bayesian mechanics is a probabilistic mechanics, comprising…
Geometric Methods for Sampling, Optimisation, Inference and Adaptive Agents
Alessandro Barp, Lancelot Da Costa, Guilherme França +4
In this chapter, we identify fundamental geometric structures that underlie the problems of sampling, optimisation, inference and adaptive decision-making. Based on this identifica…