Realising Active Inference in Variational Message Passing: the Outcome-blind Certainty Seeker
This work addresses a bottleneck for researchers in neuroscience and AI by making active inference more accessible, though it is incremental as it builds on existing frameworks.
The paper tackles the complexity of applying active inference in neuroscience and AI by providing a complete mathematical treatment and deriving update equations for new models, leveraging variational message passing to simplify the expected free energy so that agents seek unambiguous states.
Active inference is a state-of-the-art framework in neuroscience that offers a unified theory of brain function. It is also proposed as a framework for planning in AI. Unfortunately, the complex mathematics required to create new models -- can impede application of active inference in neuroscience and AI research. This paper addresses this problem by providing a complete mathematical treatment of the active inference framework -- in discrete time and state spaces -- and the derivation of the update equations for any new model. We leverage the theoretical connection between active inference and variational message passing as describe by John Winn and Christopher M. Bishop in 2005. Since, variational message passing is a well-defined methodology for deriving Bayesian belief update equations, this paper opens the door to advanced generative models for active inference. We show that using a fully factorized variational distribution simplifies the expected free energy -- that furnishes priors over policies -- so that agents seek unambiguous states. Finally, we consider future extensions that support deep tree searches for sequential policy optimisation -- based upon structure learning and belief propagation.