"In active inference a policy is simply a sequence of choices for actions through time"

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 self-organising process of action policy selection."quote0.864
• Active inference is a normative principle underwriting perception, action, planning, decision-making and learning in biological or artificial agents.quote0.823
• Active inference dispenses with the Bellman optimality principle and replaces it with a (variational) principle of least action.claim0.820
  §2, expected free energy section.
• Active inference provides a framework (derived from first principles) for solving and understanding the behavior of autonomous agents.claim0.819
• Active inference provides a principled account of epistemic exploration and intrinsic motivation as minimizing uncertainty.claim0.818
  §1, listing contributions.
• 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.claim0.808
  Sets the theoretical grounding in Section 2.
• Active inference agents can learn their own reward function (prior preferences) by interacting with the environment, bypassing the need for an explicit reward signal.claim0.804
  Abstract and §3, preference learning section.
• Active inference offers an attractive natural adaptation mechanism for non-stationary environments due to its Bayesian model updating properties.claim0.801
  §3, after non-stationary results.