Rewards reinforce behaviors that secure rewards.

Highlights circularity in RL reward hypothesis; grounds motivation for preference-based active inference.

Neighborhood — ranked by edge-count

paper

cosine ≥ 0.65 · no typed edge

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

REINFORCEframework0.787
Classical RL algorithm adapted by the paper with modifications including clipped-surrogate losses and length-normalized advantages for agentic training.
reward as predictable stimuliconcept0.785
Reinterpretation of rewards as simply predictable (unsurprising) stimuli under the free-energy principle.
Rewards are simply predictable stimuli (and aversive stimuli are, by definition, surprising)claim0.783
Redefines reward and punishment in terms of predictability.
The elimination of reward as a motivator of behavior with prior beliefs dissolves the tautology of reinforcement learning (rewards reinforce behaviors that secure rewards).claim0.779
§4 Discussion.
Empowerment as intrinsic reward bridges causal learning and reinforcement learning in agent development.claim0.762
Whether a state is rewarding (or not) is a function of the agent themselves, and not the environment.claim0.758
§1, contrasting RL reward conceptualization.
How do the parts discern which of their actions should be reinforced?question0.757
Core credit assignment question for distributed systems.
Reward improvementconcept0.754
The increase in reward during training, whose dynamics align with those of causal emergence in successful agents.