The key challenge for active inference is finding the generative model that best explains observable data.

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

• Active inference provides a principled account of epistemic exploration and intrinsic motivation as minimizing uncertainty.claim0.838
  §1, listing contributions.
• Active inference provides a framework (derived from first principles) for solving and understanding the behavior of autonomous agents.claim0.826
• Active inference treats exploration and exploitation as two different ways of tackling the same problem: minimizing uncertainty.claim0.825
  §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"quote0.820
• Active inference offers an attractive natural adaptation mechanism for non-stationary environments due to its Bayesian model updating properties.claim0.820
  §3, after non-stationary results.
• Active inference agents can learn their own reward function (prior preferences) by interacting with the environment, bypassing the need for an explicit reward signal.claim0.813
  Abstract and §3, preference learning section.
• Bayesian model expansion allows for generalisation and concept learning in active inference.claim0.813
  Definition of Bayesian model expansion, Section 9.2.
• Active Inference, Curiosity and Insight (Friston et al., 2017)concept0.812
  The primary source paper being extracted