Active inference agents can learn epistemic habits in the absence of extrinsic rewards through ambiguity minimization.

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

• Active inference agents can learn their own reward function (prior preferences) by interacting with the environment, bypassing the need for an explicit reward signal.claim0.890
  Abstract and §3, preference learning section.
• Active inference agents can carry out epistemic exploration and account for uncertainty about their environment in a Bayes-optimal fashion.claim0.880
  Abstract and §1, summarizing a key property.
• Active inference provides a principled account of epistemic exploration and intrinsic motivation as minimizing uncertainty.claim0.871
  §1, listing contributions.
• Can active inference agents learn their own prior preferences without explicit reward signals?question0.856
  Question answered by the preference learning experiments.
• Active inference agent with learnable preferences developed a strict preference for goals (score +) when the Frisbee location was encountered first, becoming a goal-seeking agent.finding0.824
  Figure 5.4 and text.
• Active inference treats exploration and exploitation as two different ways of tackling the same problem: minimizing uncertainty.claim0.823
  §2, comment on expected free energy decomposition.
• "active inference separates the problems of optimizing action and perception by assuming that action fulfills predictions based on inferred states"quote0.823
• Active inference offers an attractive natural adaptation mechanism for non-stationary environments due to its Bayesian model updating properties.claim0.822
  §3, after non-stationary results.