Active Inference, Curiosity and Insight (Friston et al., 2017)

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.claim0.837
  §1, listing contributions.
• "active inference separates the problems of optimizing action and perception by assuming that action fulfills predictions based on inferred states"quote0.834
• Friston et al. 2016: Active inference and learning (Neuroscience & Biobehavioral Reviews)concept0.829
  Foundational active inference reference
• Active inference treats exploration and exploitation as two different ways of tackling the same problem: minimizing uncertainty.claim0.828
  §2, comment on expected free energy decomposition.
• Active inference provides a framework (derived from first principles) for solving and understanding the behavior of autonomous agents.claim0.814
• Active inference offers a degree of plausibility as a process theory of brain function.claim0.814
  Overall assessment from Discussion.
• The key challenge for active inference is finding the generative model that best explains observable data.claim0.812
  Identifies an outstanding problem, Section 10.
• Active inference agents can carry out epistemic exploration and account for uncertainty about their environment in a Bayes-optimal fashion.claim0.809
  Abstract and §1, summarizing a key property.