There is an implicit behavioral equivalence between Bayesian model-based reinforcement learning and active inference when prior preferences are treated as a reward function.

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.claim0.839
  Abstract and §3, preference learning section.
• How does active inference compare to reinforcement learning in environments with no rewards or uninformative prior preferences?question0.825
  Core question addressed by the simulations when rewards are removed.
• Can active inference agents learn their own prior preferences without explicit reward signals?question0.824
  Question answered by the preference learning experiments.
• In active inference, reward can simply be treated as another observation we have a preference over, rather than a special signal.claim0.816
  Abstract; central distinction.
• Reinforcement learning can be regarded as a limiting or special case of model-based approaches in general — or active inference in particular — when epistemic value is removed.claim0.812
  §3 Discussion.
• In the absence of prior preferences, Active Inference null model and Bayesian RL maintain exploration with average scores of 44.00 and 39.94 respectively, whereas Q-learning does not explore.finding0.810
  Table 2 first row; reward shaping section.
• Behavior prescribed by active inference dynamics is approximately Bayes-optimal.claim0.804
  Process theory outcomes produce normatively sound decision-making.
• Active inference and Bayesian model-based RL learn reward-maximizing behavior in <10 episodes in deterministic FrozenLake.finding0.800
  Discussion of Figure 3.