Learning.IsBayesAlgEnvSeq.integrable_regret
No docstring.
Learning.IsBayesAlgEnvSeq.integrable_regret.{u_1, u_2, u_4} {๐ : Type u_1} {๐ : Type u_2} {ฮฉ : Type u_4} [MeasurableSpace ๐] [MeasurableSpace ๐] [MeasurableSpace ฮฉ] [Countable ๐] [Nonempty ๐] {ฮบ : ProbabilityTheory.Kernel (๐ ร ๐) โ} {E : ฮฉ โ ๐} {A : โ โ ฮฉ โ ๐} {n : โ} {P : MeasureTheory.Measure ฮฉ} [MeasureTheory.IsFiniteMeasure P] (hE : Measurable E) (hA : โ (t : โ), Measurable (A t)) {l u : โ} (h : โ (e : ๐) (a : ๐), โซ (x : โ), id x โฮบ (e, a) โ Set.Icc l u) : MeasureTheory.Integrable (regret ฮบ E A n) PLearning.IsBayesAlgEnvSeq.integrable_regret.{u_1, u_2, u_4} {๐ : Type u_1} {๐ : Type u_2} {ฮฉ : Type u_4} [MeasurableSpace ๐] [MeasurableSpace ๐] [MeasurableSpace ฮฉ] [Countable ๐] [Nonempty ๐] {ฮบ : ProbabilityTheory.Kernel (๐ ร ๐) โ} {E : ฮฉ โ ๐} {A : โ โ ฮฉ โ ๐} {n : โ} {P : MeasureTheory.Measure ฮฉ} [MeasureTheory.IsFiniteMeasure P] (hE : Measurable E) (hA : โ (t : โ), Measurable (A t)) {l u : โ} (h : โ (e : ๐) (a : ๐), โซ (x : โ), id x โฮบ (e, a) โ Set.Icc l u) : MeasureTheory.Integrable (regret ฮบ E A n) P
Code
lemma integrable_regret [Countable ๐] [Nonempty ๐] {ฮบ : Kernel (๐ ร ๐) โ} {E : ฮฉ โ ๐}
{A : โ โ ฮฉ โ ๐} {n : โ} {P : Measure ฮฉ} [IsFiniteMeasure P] (hE : Measurable E)
(hA : โ t, Measurable (A t)) {l u : โ} (h : โ e a, (ฮบ (e, a))[id] โ Set.Icc l u) :
Integrable (regret ฮบ E A n) PProof
by rw [regret_eq_sum_gap'] exact integrable_finsetSum _ (fun _ _ โฆ integrable_gap hE hA h)
Actions: Source ยท Open Issue
Meaning last changed in v4.34.0-rc2-1-g439785b (2026-08-23), the 2th recorded change.
Self-contained, with its dependencies inlined and proofs replaced by sorry: download the raw file ยท open it in the Lean web editor.
Dependency graph
Audit surface: 2 project declarations, 52 external constants
โ Proved: no sorry anywhere in its closure
This is the tool's own reading of one build's recorded axioms, and it is not robust against an author who wants it to pass. Checking meant to be relied on should go through Comparator, which replays the proof through the kernel from an export against an explicit list of permitted axioms.