Prove2Me
Navigate
DiscoverCollectionsFormalpediaGalaxyBlogsUsersMomentumMy Missions+
Prove2Me
Log in
← Formalpedia

Index monotonicity — along a run of the index algorithm, γ(s*) ≥ γ(q*) for consecutive picks s*, q*

Proved
TsitsiklisGittins.IndexTheorem.index_antitone

by mikedeng1 · Oct 6, 2026 · Mathlib 0df444a (Lean v4.33.1)

bandit-algorithmsgittins-indexp2o-batch-pfp2ap2o-gran-per-chapterp2o-plan-paperp2o-v1

Consider the semi-Markov multi-armed bandit problem with finite nonempty state spaces and a run s0,s1,…s_0,s_1,\dotss0​,s1​,… of the index algorithm with indices γ\gammaγ. Then for every kkk with sk+1s_{k+1}sk+1​ defined,

γ(sk+1)≤γ(sk).\gamma(s_{k+1})\le\gamma(s_k).γ(sk+1​)≤γ(sk​).

For k=0k=0k=0 this is the claim that if s∗s^*s∗ is the first state picked and q∗q^*q∗ the next one, then γ(s∗)≥γ(q∗)\gamma(s^*)\ge\gamma(q^*)γ(s∗)≥γ(q∗): if q∗q^*q∗ is in the bandit of s∗s^*s∗, γ(q∗)=r^(q∗)≤max⁡xr(x)=γ(s∗)\gamma(q^*)=\hat r(q^*)\le\max_x r(x)=\gamma(s^*)γ(q∗)=r^(q∗)≤maxx​r(x)=γ(s∗) by (2.3), and otherwise γ(q∗)=r(q∗)≤r(s∗)=γ(s∗)\gamma(q^*)=r(q^*)\le r(s^*)=\gamma(s^*)γ(q∗)=r(q∗)≤r(s∗)=γ(s∗).

The indices are thus non-increasing in the picking order, which is the first half of the characterization "x can be picked before y if and only if γ(x)≥γ(y)\gamma(x)\ge\gamma(y)γ(x)≥γ(y)".

Formalization Note The page proves the case of the first two picks and invokes "the recursive nature of the algorithm" for the rest; the Lean statement is the resulting claim for every pair of consecutive picks.

Preamble
import Mathlib
import Definitions.Def_TsitsiklisGittins_IndexTheorem_IndexRun
Formal statement
namespace TsitsiklisGittins.IndexTheorem

/-- Proof of Theorem 2.2 of Tsitsiklis (1994), p. 198: along a run of the index algorithm the
indices do not increase; a state picked next never has a larger index than the state picked
before it, `γ(s*) ≥ γ(q*)`. -/
theorem index_antitone {n : ℕ} [NeZero n] {X : Fin n → Type} [∀ i, Fintype (X i)] [∀ i, DecidableEq (X i)]
    [∀ i, Nonempty (X i)] [∀ i, MeasurableSpace (X i)] [∀ i, MeasurableSingletonClass (X i)]
    (B : SemiMarkovBandit n X)
    (seq : List (Σ i, X i)) (γ : (Σ i, X i) → ℝ) (hrun : B.IsIndexRun seq γ)
    (k : ℕ) (hk : k + 1 < seq.length) :
    γ seq[k + 1] ≤ γ seq[k] := by sorry

end TsitsiklisGittins.IndexTheorem
Source
Tsitsiklis, A Short Proof of the Gittins Index Theorem, Ann. Appl. Probab. 4 (1994), p. 198 (PDF p. 5), Section 2, proof of Theorem 2.2
Human review
  • Endorsed by Shuze Chen · Oct 6, 2026

    Confirmed by the moderator at approval.

  • Endorsed by mikedeng1 · Oct 6, 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