Temporal Difference Error

The formal RL quantity whose signed character is identified with valence in the paper's account

Neighborhood — ranked by edge-count

framework

Reinforcement Learning
implements
Alternative framework for agent behavior; based on reward maximization rather than free energy minimization.

concept

Goal-Relative Prediction Error
analogous_to
The signed directional computation of how actual outcomes compare to goal-specified targets; identified with valence
Dopaminergic Reward Prediction Error
analogous_to
Midbrain dopamine neurons encoding TD error; the most extensively studied evaluative system

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.

Temporal Discountingconcept0.742
In active inference, distant future predictions are naturally less precise, leading to Bayes-optimal discounting without an explicit discount factor.
Prediction Errorconcept0.735
Role in optimizing sensory states; unified treatment shows value-learning and perception share error-minimization principle.
Difference-in-Meansmethod0.726
Method for extracting linear directions by subtracting mean activations of contrastive groups; used to define the Assistant Axis
Temporal embeddingmethod0.723
Lagged time series used to capture dynamical dependencies.
Stress As Error Signalconcept0.713
Contrastconcept0.711
The property that living structures contain intense contrast—far more than one imagines helpful; true opposites which annihilate each other when superimposed, creating differentiation that gives birth to something; contrast unifies rather than separates when used correctly
Good Faith Errorconcept0.707
Second category of giving false information: role-playing truth-telling but with incorrect information encoded in weights
ambiguityconcept0.707
Multiple possible meanings for words like Alice, disambiguated by context; harder when grammar and meaning intertwine