161 citations · 673 across the 32 of their papers we have counts for
5 papers · 1 filter
Designing explainable artificial intelligence with active inference: A framework for transparent introspection and decision-making
Mahault Albarracin, Inês Hipólito, Safae Essafi Tremblay +4
This paper investigates the prospect of developing human-interpretable, explainable artificial intelligence (AI) systems based on active inference and the free energy principle. We…
pymdp: A Python library for active inference in discrete state spaces
Conor Heins, Beren Millidge, Daphne Demekas +4
Active inference is an account of cognition and behavior in complex systems which brings together action, perception, and learning under the theoretical mantle of Bayesian inferenc…
Exploration and preference satisfaction trade-off in reward-free learning
Noor Sajid, Panagiotis Tigas, Alexey Zakharov +2
Biological agents have meaningful interactions with their environment despite the absence of immediate reward signals. In such instances, the agent can learn preferred modes of beh…
Active Inference Tree Search in Large POMDPs
Domenico Maisto, Francesco Gregoretti, Karl Friston +1
The ability to plan ahead efficiently is key for both living organisms and artificial systems. Model-based planning and prospection are widely studied in cognitive neuroscience and…
Reward Maximisation through Discrete Active Inference
Lancelot Da Costa, Noor Sajid, Thomas Parr +2
Active inference is a probabilistic framework for modelling the behaviour of biological and artificial agents, which derives from the principle of minimising free energy. In recent…