Prove2Me
Navigate
DiscoverCollectionsFormalpediaGalaxyBlogsUsersMomentumMy Missions+
Prove2Me
Log in
← Formalpedia

Stopping-time reward ratios are bounded by the Gittins index

Proved
BanditAlgorithm.gittins_stopping_ratio_le_index

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

banditsoptimal-stoppingprobability

Let (St)t≥0(S_t)_{t\ge 0}(St​)t≥0​ be a Markov chain with transition kernel PPP, started from state xxx, measurable reward function r:S→Rr:S\to\mathbb Rr:S→R, and discount factor α∈(0,1)\alpha\in(0,1)α∈(0,1). Assume the expected infinite discounted sum of absolute rewards is finite. For any stopping time τ≥1\tau\ge 1τ≥1, the expected discounted reward per expected discounted unit of time is at most the Gittins index:

Ex ⁣[∑t<ταtr(St)]Ex ⁣[∑t<ταt]≤g(x).\frac{\mathbb E_x\!\left[\sum_{t<\tau}\alpha^t r(S_t)\right]}{\mathbb E_x\!\left[\sum_{t<\tau}\alpha^t\right]} \le g(x).Ex​[∑t<τ​αt]Ex​[∑t<τ​αtr(St​)]​≤g(x).

This is the fundamental upper-bound direction of the stopping-time characterization of the Gittins index and is reusable in prevailing-charge arguments for discounted Markov bandits.

Formalization Note Stopping times take values in N∪{∞}\mathbb N\cup\{\infty\}N∪{∞} and are adapted to the natural coordinate filtration. The integrability assumption ensures the numerator is a genuine finite Bochner integral and the denominator is at least one.

Preamble
import Mathlib.MeasureTheory.Constructions.Polish.Basic
import Mathlib.Analysis.Normed.Group.InfiniteSum
import Mathlib.Analysis.SpecificLimits.Normed
import Definitions.Def_GittinsIndex

open MeasureTheory ProbabilityTheory ENNReal
Formal statement
theorem BanditAlgorithm.gittins_stopping_ratio_le_index
    {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)
    (τ : (ℕ → S) → ℕ∞) (hτ : IsTrajStoppingTime τ)
    (hτ1 : ∀ ω, 1 ≤ τ ω) :
    (∫ ω, discountedStoppedSum α r τ ω ∂markovChainMeasure P x) /
        (∫ ω, discountedStoppedSum α (fun _ ↦ 1) τ ω
          ∂markovChainMeasure P x) ≤
      gittinsIndex P r α x := by
  sorry
Source
Lattimore and Szepesvári, Bandit Algorithms (CUP 2020), §35.4.1, printed p.448, Eq. (35.9), under Assumption 35.6 on printed p.448.

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