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.

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

• How does active inference compare to reinforcement learning in environments with no rewards or uninformative prior preferences?question0.823
  Core question addressed by the simulations when rewards are removed.
• Reinforcement learning acting on individual characteristics affecting their connections to others can result in dynamics that are equivalent to unsupervised learning at the system scale.claim0.823
  Key insight linking individual rewards to system-level learning.
• Certain forms of reinforcement learning from human feedback can actually exacerbate, rather than mitigate, the tendency for LLM-based dialogue agents to express a desire for self-preservationclaim0.813
  Empirically grounded claim citing Perez et al. 2022, showing RLHF can backfire on the self-preservation dimension
• There is an implicit behavioral equivalence between Bayesian model-based reinforcement learning and active inference when prior preferences are treated as a reward function.claim0.812
  §3, reward shaping conclusion.
• The elimination of reward as a motivator of behavior with prior beliefs dissolves the tautology of reinforcement learning (rewards reinforce behaviors that secure rewards).claim0.808
  §4 Discussion.
• In active inference, reward can simply be treated as another observation we have a preference over, rather than a special signal.claim0.803
  Abstract; central distinction.
• "reinforcement learning is learning what to do – how to map situations to actions – so as to maximize a numerical reward signal"quote0.801
  Operational definition of RL used throughout the paper, quoted from Sutton.
• Reinforcement learning is sufficient for agency.claim0.798
  Argument that RL meets the agency indicator.