Active inference treats exploration and exploitation as two different ways of tackling the same problem: minimizing uncertainty.

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.claim0.884
  §1, listing contributions.
• "active inference separates the problems of optimizing action and perception by assuming that action fulfills predictions based on inferred states"quote0.858
• Active inference agents can carry out epistemic exploration and account for uncertainty about their environment in a Bayes-optimal fashion.claim0.851
  Abstract and §1, summarizing a key property.
• Active inference can be framed as the minimisation of surprise by perception and action.claim0.845
  Concise characterisation from Section 2.
• In brief, active inference proposes that agents achieve this by optimising two complementary objective functions, a variational free energy and an expected free energy.quote0.842
  Concise statement of the core hypothesis from Section 2.
• The natural curiosity emerging in active inference contrasts with handcrafted exploration in reinforcement learning such as epsilon-greedy or ad hoc novelty bonuses.claim0.842
  §2, comparing exploration mechanisms.
• Active Inference, Curiosity and Insight (Friston et al., 2017)concept0.828
  The primary source paper being extracted
• "Active inference is a self-organising process of action policy selection."quote0.828