The natural curiosity emerging in active inference contrasts with handcrafted exploration in reinforcement learning such as epsilon-greedy or ad hoc novelty bonuses.

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

• Active inference treats exploration and exploitation as two different ways of tackling the same problem: minimizing uncertainty.claim0.842
  §2, comment on expected free energy decomposition.
• In active inference, reward can simply be treated as another observation we have a preference over, rather than a special signal.claim0.838
  Abstract; central distinction.
• Curiosity manifests as active sampling of the world to minimize uncertainty about hypotheses for states of the world, driven by novelty-seeking policies that resolve ignorance about contingencies.claim0.829
  Formal definition of curiosity within active inference framework
• Active inference agents can learn their own reward function (prior preferences) by interacting with the environment, bypassing the need for an explicit reward signal.claim0.828
  Abstract and §3, preference learning section.
• How does active inference compare to reinforcement learning in environments with no rewards or uninformative prior preferences?question0.819
  Core question addressed by the simulations when rewards are removed.
• Active inference agents engage in information-seeking behavior in reward-free FrozenLake environments, contrasting with Q-learning but similar to Bayesian RL.finding0.811
  Empirical demonstration on FrozenLake; shows epistemic value drives exploration absent reward signal.
• Active inference offers an attractive natural adaptation mechanism for non-stationary environments due to its Bayesian model updating properties.claim0.809
  §3, after non-stationary results.
• Active inference agents can learn epistemic habits in the absence of extrinsic rewards through ambiguity minimization.claim0.802
  §2, summarizing information-seeking behavior.