"Active inference is a self-organising process of action policy selection."

Entities in the same semantic neighborhood but without a typed relation to this one — candidates for new edges or unrecognized duplicates.

• Active inference is a normative principle underwriting perception, action, planning, decision-making and learning in biological or artificial agents.quote0.871
• "In active inference a policy is simply a sequence of choices for actions through time"quote0.864
  Definition of sequential policy in active inference, contrasting with state-action policies in RL.
• Active inference provides a principled account of epistemic exploration and intrinsic motivation as minimizing uncertainty.claim0.859
  §1, listing contributions.
• Active inference provides a framework (derived from first principles) for solving and understanding the behavior of autonomous agents.claim0.847
• Active inference can be framed as the minimisation of surprise by perception and action.claim0.842
  Concise characterisation from Section 2.
• "active inference separates the problems of optimizing action and perception by assuming that action fulfills predictions based on inferred states"quote0.839
• Active inference offers an attractive natural adaptation mechanism for non-stationary environments due to its Bayesian model updating properties.claim0.833
  §3, after non-stationary results.
• Active inference describes the dynamics of systems that persist at non-equilibrium steady-state and that can be statistically segregated from their environment via a Markov blanket.claim0.830
  Sets the theoretical grounding in Section 2.