concept
active
concept:expected-free-energy

Expected Free Energy

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

Neighborhood — ranked by edge-count

Thinkers (1)

thinker

Frameworks (1)

framework
  • Active Inference
    associated_withimplements
    Foundational framework by Karl Friston; the paper extends it to three hierarchical levels for modeling meta-awareness.

Claims (1)

claim

Methods (1)

method
  • Selecting policies using a softmax (normalized exponential) function of negative expected free energy.

Concepts (15)

concept
  • Ambiguity (Expected Free Energy)
    associated_withrelated_to
    Expected entropy of outcomes given states; resolved by selecting states that yield unambiguous outcomes.
  • Risk (Expected Free Energy)
    associated_withrelated_to
    KL divergence between predicted and preferred final states or outcomes.
  • free energy
    related_to
    Thermodynamic potential ΔF = ΔE − TΔS; domain walls form if ΔF < 0
  • Action Selection
    associated_withimplements
    Choice of policies minimizing expected free energy to realize preferred future states.
  • Bayes-optimal exploration driven by uncertainty minimization; natural behavior in active inference without handcrafted mechanisms.
  • Extrinsic Value
    associated_with
    Expected evidence for preferred outcomes; utility-weighted term in expected free energy.
  • The component of expected free energy that drives utility-maximizing actions based on prior preferences over outcomes.
  • ambiguity
    associated_with
    Multiple possible meanings for words like Alice, disambiguated by context; harder when grammar and meaning intertwine
  • Epistemic Value
    associated_with
    Expected information gain about hidden states; drives curiosity and novelty-seeking; mutual information term in expected free energy.
  • Expected Ambiguity
    associated_with
    The expected conditional entropy of outcomes given hidden states; lowering ambiguity favors states that solicit unambiguous observations.
  • Risk
    associated_with
    Expected complexity component of expected free energy; minimized by risk-sensitive behavior
  • Novelty
    associated_with
    New term in expected free energy representing information gain about the likelihood mapping; drives ignorance resolution
  • Expected Cost
    associated_with
    The KL divergence between predicted and preferred outcomes, minimized by policies that realize prior preferences.
  • The balance between gathering new information (exploration) and using existing knowledge to obtain rewards (exploitation).
  • Ignorance
    associated_with

Related by similarity (8)

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.