Action and Perception as Divergence Minimization – original publication September 3, 2020
The paper introduces Action Perception Divergence (APD), a framework for categorizing objective functions in intelligent agents. It distinguishes betw…
Chats
Why Bayesian brains perform poorly on explicit probabilistic reasoning problems
The paper explores why Bayesian inference in the brain contributes to poor performance on explicit probabilistic reasoning tasks. It distinguishes bet…
Canonical neural networks perform active inference
This research explores canonical neural networks, demonstrating that they perform active inference and learning via rate coding models. It reveals tha…
pymdp: A Python library for active inference in discrete state spaces
The post introduces pymdp, a Python library designed for simulating active inference in complex systems using partially-observable Markov Decision Pro…
Unsupervised model-based pre-training for data-efficient reinforcement learning from pixels
The paper discusses advancements in unsupervised reinforcement learning (RL), focusing on enhancing data efficiency in high-dimensional environments. …
The Role of Idiothetic Signals, Landmarks, and Conjunctive Representations in the Development of Place and Head-Direction Cells: A Self-Organizing Neural Network Model
The paper discusses the construction of spatial maps for navigation, proposing that a unified mechanism underlies the chunking of sensory data in both…
Chunking space and time with information geometry
The paper "Chunking space and time with information geometry" presents a unified approach to how humans and robots process sensory data by forming dis…
A free energy principle for generic quantum systems
The Free Energy Principle (FEP) proposes that random dynamical systems minimize an upper bound on surprisal through weak coupling. This paper reformul…
Active inference, Bayesian optimal design, and expected utility
The abstract discusses active inference, linked to the free energy principle, as a method for understanding certain random dynamical systems resemblin…
Trust as Extended Control: Active Inference and User Feedback During Human-Robot Collaboration
The paper explores the concept of trust in human-robot collaboration (HRC), emphasizing its necessity for seamless interaction. It reviews existing li…