Documentation

Determinize.Proof.FiniteModel.Model

Expected reward returned within steps transitions; unfinished paths contribute zero.

Equations
Instances For
    theorem Determinize.Proof.FiniteModel.outputWithin_mono (model : Spec.FiniteModel.Model) (state : Fin model.size) :
    Monotone fun (steps : ℕ) => model.outputWithin steps state

    Increasing the exploration horizon only adds returned output mass.

    theorem Determinize.Proof.FiniteModel.returned_outputWithin (model : Spec.FiniteModel.Model) (state : Fin model.size) (reward : ℚ) (returned : model.kind state = Spec.FiniteModel.StateKind.returned reward) (steps : ℕ) :
    model.outputWithin steps state = MeasureTheory.Measure.dirac ↑reward
    theorem Determinize.Proof.FiniteModel.rejected_outputWithin (model : Spec.FiniteModel.Model) (state : Fin model.size) (rejected : model.kind state = Spec.FiniteModel.StateKind.rejected) (steps : ℕ) :
    model.outputWithin steps state = 0
    theorem Determinize.Proof.FiniteModel.integrable_outputWithin (model : Spec.FiniteModel.Model) (steps : ℕ) (state : Fin model.size) (f : ℝ → ℝ) :

    Every finite-horizon output law has finite support.

    theorem Determinize.Proof.FiniteModel.rewardWithin_integral (model : Spec.FiniteModel.Model) (steps : ℕ) (state : Fin model.size) :
    ∫ (value : ℝ), value ∂model.outputWithin steps state = ↑(model.rewardWithin steps state)

    Exact rational reward iteration agrees with the real-measure interpretation.