In active inference, reward can simply be treated as another observation we have a preference over, rather than a special signal.

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.claim0.876
  Abstract and §3, preference learning section.
• How does active inference compare to reinforcement learning in environments with no rewards or uninformative prior preferences?question0.853
  Core question addressed by the simulations when rewards are removed.
• Can active inference agents learn their own prior preferences without explicit reward signals?question0.842
  Question answered by the preference learning experiments.
• The natural curiosity emerging in active inference contrasts with handcrafted exploration in reinforcement learning such as epsilon-greedy or ad hoc novelty bonuses.claim0.838
  §2, comparing exploration mechanisms.
• Under active inference, the ultimate ‘goal’ is to maintain a coherent phenotype and persist over time, not to maximize reward.claim0.833
  §3, preference learning discussion.
• Active inference provides a principled account of epistemic exploration and intrinsic motivation as minimizing uncertainty.claim0.827
  §1, listing contributions.
• 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"quote0.822