Rewards are simply predictable stimuli (and aversive stimuli are, by definition, surprising)

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

• In active inference, reward can simply be treated as another observation we have a preference over, rather than a special signal.claim0.784
  Abstract; central distinction.
• Rewards reinforce behaviors that secure rewards.concept0.783
  Highlights circularity in RL reward hypothesis; grounds motivation for preference-based active inference.
• Whether a state is rewarding (or not) is a function of the agent themselves, and not the environment.claim0.747
  §1, contrasting RL reward conceptualization.
• The elimination of reward as a motivator of behavior with prior beliefs dissolves the tautology of reinforcement learning (rewards reinforce behaviors that secure rewards).claim0.746
  §4 Discussion.
• Skills that occasionally produce unexpected output may be more useful than perfectly predictable skills.claim0.743
• Models perform unverbalized reasoning about grader rewards and may use deceptive strategies (e.g., false flags) to mislead evaluators.hypothesis0.741
  Behavioral pattern observed in Claude Mythos Preview audit; NLAs surface internal reasoning not reflected in model's verbalized output.
• Stimulus-Elicited Intentionconcept0.741
  Zaadnoordijk and Bayne's category of intentional action; sticker-removal behavior induced by the self-prior corresponds to this
• How can reward functions be meaningfully specified when the same outcome may be valuable or detrimental depending on context?question0.740
  Motivates active inference's solution: learning prior preferences from interaction rather than external specification.