Active Inference in Discrete State Spaces from First Principles
By: Patrick Kenny
Potential Business Impact:
Helps brains learn by guessing and checking.
We seek to clarify the concept of active inference by disentangling it from the Free Energy Principle. We show how the optimizations that need to be carried out in order to implement active inference in discrete state spaces can be formulated as constrained divergence minimization problems which can be solved by standard mean field methods that do not appeal to the idea of expected free energy. When it is used to model perception, the perception/action divergence criterion that we propose coincides with variational free energy. When it is used to model action, it differs from an expected free energy functional by an entropy regularizer.
Similar Papers
Active Inference is a Subtype of Variational Inference
Artificial Intelligence
Helps smart machines learn and explore better.
Active inference for action-unaware agents
Artificial Intelligence
Helps robots learn to move without knowing their own actions.
Prior preferences in active inference agents: soft, hard, and goal shaping
Artificial Intelligence
Helps robots learn goals, but they explore less.