4 papers
AXIOM: Learning to Play Games in Minutes with Expanding Object-Centric Models
Conor Heins, Toon Van de Maele, Alexander Tschantz +11
Current deep reinforcement learning (DRL) approaches achieve state-of-the-art performance in various domains, but struggle with data efficiency compared to human learning, which le…
Distributed Intelligence in the Computing Continuum with Active Inference
Victor Casamayor Pujol, Boris Sedlak, Tommaso Salvatori +2
The Computing Continuum (CC) is an emerging Internet-based computing paradigm that spans from local Internet of Things sensors and constrained edge devices to large-scale cloud dat…
Divide-and-Conquer Predictive Coding: a structured Bayesian inference algorithm
Eli Sennesh, Hao Wu, Tommaso Salvatori
Unexpected stimuli induce "error" or "surprise" signals in the brain. The theory of predictive coding promises to explain these observations in terms of Bayesian inference by sugge…
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…