Active inference achieves Bayes-optimal behavior in non-stationary environments through online belief updating.

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

• Active inference offers an attractive natural adaptation mechanism for non-stationary environments due to its Bayesian model updating properties.claim0.902
  §3, after non-stationary results.
• Behavior prescribed by active inference dynamics is approximately Bayes-optimal.claim0.876
  Process theory outcomes produce normatively sound decision-making.
• Active inference agents can carry out epistemic exploration and account for uncertainty about their environment in a Bayes-optimal fashion.claim0.856
  Abstract and §1, summarizing a key property.
• Active inference describes the dynamics of systems that persist at non-equilibrium steady-state and that can be statistically segregated from their environment via a Markov blanket.claim0.848
  Sets the theoretical grounding in Section 2.
• Active inference provides a principled account of epistemic exploration and intrinsic motivation as minimizing uncertainty.claim0.842
  §1, listing contributions.
• Active inference agents engage in information-seeking behavior in reward-free FrozenLake environments, contrasting with Q-learning but similar to Bayesian RL.finding0.837
  Empirical demonstration on FrozenLake; shows epistemic value drives exploration absent reward signal.
• Active inference agents can learn their own reward function (prior preferences) by interacting with the environment, bypassing the need for an explicit reward signal.claim0.834
  Abstract and §3, preference learning section.
• These dynamics are consistent with predictive processing since active inference prescribes dynamics that minimise prediction error.concept0.829
  Connection between active inference neuronal dynamics and predictive processing theory.