Home
Research
Projects
Publications
Software
Teaching
Talks
Contact
Light
Dark
Automatic
Active-Inference
Expected free energy as an information constraint on the Bethe Lagrangian
Active inference plans with expected free energy, but message passing minimises a Bethe free energy. This talk connects the two: it adds an information constraint to the Bethe free energy, which brings back the drive to explore. The constrained policy equals the expected free energy policy at a particular multiplier value. That multiplier is solved rather than tuned, so exploration switches off once the agent has enough information.
Oct 15, 2026 10:50 — 11:20
Spanish National Research Council, Madrid, Spain
Slides
Expected free energy as an information constraint
We propose a formulation of expected free energy minimization based on a Bethe free energy functional, fully supporting inference by message passing. The epistemic drive is maintained by imposing an information constraint, in addition to normalisation, marginalisation and form constraints, insisting that the mutual information between future observations, states and parameters given actions must be at least as large as the entropy of the goal prior.
Sep 15, 2026 14:00 — 15:00
TU Eindhoven, Netherlands
Slides
Video
On deriving efficient information-seeking behaviour for intelligent autonomous systems
This talk presents a principled mathematical framework for deriving information-seeking behavior in intelligent agents, grounded in Bayesian inference and the free energy principle.
Oct 20, 2025 16:00 — 17:00
McGill University, Montreal, Canada
Slides
Message passing-based inference in autoregressive active inference agent
We present the design of an autoregressive active inference agent in the form of message passing on a factor graph.
Oct 17, 2025 10:45 — 11:00
McGill University, Montreal, Canada
Slides
Planning to avoid ambiguous states through Gaussian approximations to non-linear sensors
Gaussian approximations to nonlinear observation functions hat are sensitive to curvature, such as a second-order Taylor approximation, produce a state-dependent ambiguity term in expected free energy minimization.
Sep 11, 2024 10:40 — 14:50
Corpus Christi College, Oxford, United Kingdom
Slides
Information-seeking polynomial NARX model-predictive control through free energy minimization
We propose an adaptive model-predictive controller that balances driving the system to a goal state and seeking system observations that are informative with respect to the parameters of a nonlinear autoregressive exogenous model.
Jul 12, 2024 14:00 — 14:30
Toronto, Canada
Slides
Cite
×