
Habitual and Reflective Control in Hierarchical Predictive Coding
In cognitive science, behaviour is often separated into two types. Refle...
read it

A Mathematical Walkthrough and Discussion of the Free Energy Principle
The FreeEnergyPrinciple (FEP) is an influential and controversial theo...
read it

Predictive Coding: a Theoretical and Experimental Review
Predictive coding offers a potentially unifying account of cortical func...
read it

Applications of the Free Energy Principle to Machine Learning and Neuroscience
In this PhD thesis, we explore and apply methods inspired by the free en...
read it

Online reinforcement learning with sparse rewards through an active inference capsule
Intelligent agents must pursue their goals in complex environments with ...
read it

Towards a Mathematical Theory of Abstraction
While the utility of wellchosen abstractions for understanding and pred...
read it

Understanding the origin of informationseeking exploration in probabilistic objectives for control
The explorationexploitation tradeoff is central to the description of ...
read it

Neural Kalman Filtering
The Kalman filter is a fundamental filtering algorithm that fuses noisy ...
read it

Investigating the Scalability and Biological Plausibility of the Activation Relaxation Algorithm
The recently proposed Activation Relaxation (AR) algorithm provides a si...
read it

Relaxing the Constraints on Predictive Coding Models
Predictive coding is an influential theory of cortical function which po...
read it

Activation Relaxation: A Local Dynamical Approximation to Backpropagation in the Brain
The backpropagation of error algorithm (backprop) has been instrumental ...
read it

Control as Hybrid Inference
The field of reinforcement learning can be split into modelbased and mo...
read it

On the Relationship Between Active Inference and Control as Inference
Active Inference (AIF) is an emerging framework in the brain sciences wh...
read it

Reinforcement Learning as Iterative and Amortised Inference
There are several ways to categorise reinforcement learning (RL) algorit...
read it

Predictive Coding Approximates Backprop along Arbitrary Computation Graphs
Backpropagation of error (backprop) is a powerful algorithm for training...
read it

Whence the Expected Free Energy?
The Expected Free Energy (EFE) is a central quantity in the theory of ac...
read it

Reinforcement Learning through Active Inference
The central tenet of reinforcement learning (RL) is that agents seek to ...
read it

Deep Active Inference as Variational Policy Gradients
Active Inference is a theory of action arising from neuroscience which c...
read it
Beren Millidge
is this you? claim profile