Friston, FitzGerald et al. (2016) — Active inference and learning

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

• Active Inferenceframework0.826
  Foundational framework by Karl Friston; the paper extends it to three hierarchical levels for modeling meta-awareness.
• "active inference separates the problems of optimizing action and perception by assuming that action fulfills predictions based on inferred states"quote0.818
• Active inference offers a degree of plausibility as a process theory of brain function.claim0.816
  Overall assessment from Discussion.
• Active inference agents can learn their own reward function (prior preferences) by interacting with the environment, bypassing the need for an explicit reward signal.claim0.814
  Abstract and §3, preference learning section.
• Active inference agents can learn epistemic habits in the absence of extrinsic rewards through ambiguity minimization.claim0.811
  §2, summarizing information-seeking behavior.
• The key challenge for active inference is finding the generative model that best explains observable data.claim0.811
  Identifies an outstanding problem, Section 10.
• 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.finding0.810
  Figure 5.4 and text.
• Active inference provides a principled account of epistemic exploration and intrinsic motivation as minimizing uncertainty.claim0.809
  §1, listing contributions.