Prove2Me
Navigate
DiscoverCollectionsFormalpediaGalaxyBlogsUsersMomentumMy Missions+
Prove2Me
Log in
← Formalpedia

The Gittins retirement value is Lipschitz in the charge

Proved
BanditAlgorithm.gittinsRetirementValue_lipschitz_charge

by Harry_Xu · Jul 31, 2026 · Mathlib 0df444a (Lean v4.33.1)

banditsgittins-indexlipschitzoptimal-stopping

Fix a state xxx in a discounted one-armed retirement game satisfying the discounted absolute-reward integrability assumption. Let vγ(x)v_{\gamma}(x)vγ​(x) denote the optimal value when each played round incurs charge γ\gammaγ.

For any two charges γ\gammaγ and δ\deltaδ,

∣vγ(x)−vδ(x)∣≤∣γ−δ∣∑t=0∞αt.\left|v_{\gamma}(x)-v_{\delta}(x)\right| \le |\gamma-\delta|\sum_{t=0}^{\infty}\alpha^t.∣vγ​(x)−vδ​(x)∣≤∣γ−δ∣t=0∑∞​αt.

Thus the retirement value is uniformly Lipschitz in the charge, with constant equal to the full discounted duration. This controls the boundary case where the charge approaches the fair Gittins index.

Preamble
import Mathlib.MeasureTheory.Constructions.Polish.Basic
import Definitions.Def_GittinsRetirementValue

open MeasureTheory ProbabilityTheory ENNReal
Formal statement
theorem BanditAlgorithm.gittinsRetirementValue_lipschitz_charge
    {S : Type*} [MeasurableSpace S]
    (P : Kernel S S) [IsMarkovKernel P]
    {r : S → ℝ} (hr : Measurable r) {α : ℝ}
    (hα0 : 0 < α) (hα1 : α < 1)
    (hint : DiscountedRewardIntegrable P r α)
    (x : S) (γ δ : ℝ) :
    |gittinsRetirementValue P r α γ x -
        gittinsRetirementValue P r α δ x| ≤
      |γ - δ| * ∑' t : ℕ, α ^ t := by
  sorry
Source
Lattimore and Szepesvari, Bandit Algorithms (Cambridge University Press, 2020), printed p. 448, Eq. (35.7) and the observation immediately following Assumption 35.6 that the retirement value is decreasing in the charge; the quantitative bound follows directly from the discounted-duration bound used in printed p. 449, Lemma 35.7.

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