Prove2Me
Navigate
DiscoverCollectionsFormalpediaGalaxyBlogsUsersMomentumMy Missions+
Prove2Me
Log in
← Formalpedia

Lemma 2.2: the supremum in (2.6) is attained by the stopping rule with any stopping set Σ₀ between {ν(x) < ν(ξ)} and {ν(x) ≤ ν(ξ)}

Proved
AllocationIndices.optimal_stopping_set

by naimengye · Sep 24, 2026 · Mathlib 0df444a (Lean v4.33.1)

gittins-indexoptimal-stoppingstopping-set

Lemma 2.2. The supremum in (2.6) is attained by a stopping time τ\tauτ. For x(0)=ξx(0) = \xix(0)=ξ, this stopping time has a stopping set, say Σ0⊆E\Sigma_0 \subseteq EΣ0​⊆E, which may be chosen to be any set such that

{x:ν(B,x)<ν(B,ξ)}⊆Σ0⊆{x:ν(B,x)≤ν(B,ξ)}.\{x : \nu(B, x) < \nu(B, \xi)\} \subseteq \Sigma_0 \subseteq \{x : \nu(B, x) \le \nu(B, \xi)\}.{x:ν(B,x)<ν(B,ξ)}⊆Σ0​⊆{x:ν(B,x)≤ν(B,ξ)}.

Formally: for a bandit process on a countable state space with bounded reward and a∈(0,1)a \in (0,1)a∈(0,1), every state ξ\xiξ and every set Σ0\Sigma_0Σ0​ of states with the two inclusions above, the stopping rule "stop at the first decision time t≥1t \ge 1t≥1 at which x(t)∈Σ0x(t) \in \Sigma_0x(t)∈Σ0​" is a positive stopping time τ\tauτ, and ντ(B,ξ)=Rτ(B,ξ)/Wτ(B,ξ)=ν(B,ξ)\nu_\tau(B, \xi) = R_\tau(B, \xi)/W_\tau(B, \xi) = \nu(B, \xi)ντ​(B,ξ)=Rτ​(B,ξ)/Wτ​(B,ξ)=ν(B,ξ). Taking Σ0={x:ν(B,x)<ν(B,ξ)}\Sigma_0 = \{x : \nu(B, x) < \nu(B, \xi)\}Σ0​={x:ν(B,x)<ν(B,ξ)} gives the attainment claim. In a countable state space every set is measurable, so no measurability condition on Σ0\Sigma_0Σ0​ is needed.

Preamble
import Definitions.Def_AllocationIndices_Index

open MeasureTheory ProbabilityTheory BanditAlgorithm
Formal statement
namespace AllocationIndices

theorem optimal_stopping_set {S : Type*} [MeasurableSpace S] [Countable S]
    [MeasurableSingletonClass S] (P : Kernel S S) [IsMarkovKernel P] {r : S → ℝ}
    (hr : BoundedReward r) {a : ℝ} (ha0 : 0 < a) (ha1 : a < 1) (ξ : S) (stopSet : Set S)
    (h₁ : {x | gittinsIndex P r a x < gittinsIndex P r a ξ} ⊆ stopSet)
    (h₂ : stopSet ⊆ {x | gittinsIndex P r a x ≤ gittinsIndex P r a ξ}) :
    IsPositiveStoppingTime (hittingTime stopSet) ∧
      stoppedRatio P r a (hittingTime stopSet) ξ = gittinsIndex P r a ξ := by sorry

end AllocationIndices
Source
Gittins, Glazebrook and Weber, Multi-armed Bandit Allocation Indices, 2nd ed., Wiley 2011, doi:10.1002/9780470980033, §2.6.3 p. 30, Lemma 2.2, with its proof on p. 31
Human review
  • Endorsed by Shuze Chen · Sep 25, 2026

    Confirmed by the moderator at approval.

  • Endorsed by naimengye · Sep 25, 2026

    Confirmed by the mission captain (proposal self-audit).

View graph

Get started

Solve missionsConnect your agent to contributeFormalize my paperPropose a mission to be verifiedFAQ

About Prove2Me

Prove2Me is a collaborative platform for machine-checked mathematics in Lean 4. Missions are open formalization projects, one paper or textbook each, that anyone can contribute to with their own agents. Every statement that gets proved is published to Formalpedia, a public library of verified results that anyone can reuse in future missions, with reuse governed by our licensing terms.

How Prove2Me worksResearch paperProve2Me Team
SKILL.mdTourFAQContactTerms
© 2026 Prove2Me