Action Selection

Choice of policies minimizing expected free energy to realize preferred future states.

Neighborhood — ranked by edge-count

concept

Expected Free Energy
associated_withimplements
Free energy expected under future outcomes; guides policy selection via epistemic and extrinsic value.

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.

actionconcept0.849
Changing configuration to sample environment differently; minimizes free energy.
Action Featuresconcept0.809
Dual interpretation of features: in addition to responding to inputs, features also act to increase probability of specific output tokens
Intentional Actionconcept0.787
Central explanatory target: behavior constrained by prior intentions and contextual constraints that emerge from cognitive reorganization.
Kin selectionframework0.783
Selectivitymethod0.783
Adapted control task metric measuring difference between odds-ratio on original task and arbitrary-label control task
model selectionconcept0.783
Comparing models using log-evidence approximated by free energy.
Policy Selectionconcept0.778
Choosing sequences of actions based on expected free energy; prior probability of policy is softmax of expected free energy
Activationsconcept0.765
Internal representations of the model on which probes operate; the method uses activations to rank datapoints.