Prove2Me
Navigate
DiscoverCollectionsFormalpediaGalaxyBlogsUsersMomentumMy Missions+
Prove2Me
Log in
← Formalpedia

A Gittins-index policy dominates every competing policy

Proved
BanditAlgorithm.gittins_index_policy_dominates

by Harry_Xu · 1 vote · Jul 30, 2026 · Mathlib c5ea003 (Lean v4.30.0)

banditsbayesian-banditsgittins-indexoptimal-control

Consider a discounted kkk-armed Markov bandit on a standard Borel state space. All arms evolve according to the same Markov kernel PPP, yield measurable reward rrr, and are discounted by α∈(0,1)\alpha\in(0,1)α∈(0,1). Assume the expected discounted absolute reward of each single-arm chain is finite. If π∗\pi^*π∗ always activates an arm whose current state has maximal Gittins index, then for every competing policy π\piπ and every initial state vector xxx,

Vπ(x)≤Vπ∗(x).V^{\pi}(x)\le V^{\pi^*}(x).Vπ(x)≤Vπ∗(x).

This is the pointwise policy-dominance form of the Gittins index theorem. It isolates the prevailing-charge and interleaving argument from the order-theoretic final step that identifies the optimal value with the supremum over policies.

Formalization Note Policies may be randomized Markov kernels on the complete observed history. The integrability assumption is the formal version of Assumption 35.6.

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

open MeasureTheory ProbabilityTheory ENNReal
Formal statement
theorem BanditAlgorithm.gittins_index_policy_dominates
    {k : ℕ} {S : Type*} [MeasurableSpace S]
    [StandardBorelSpace 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)
    (πstar : MarkovBanditPolicy k S) (hπ : IsGittinsIndexPolicy P r α πstar)
    (x : Fin k → S) :
    ∀ π : MarkovBanditPolicy k S,
      markovBanditDiscountedValue P r α π x ≤
        markovBanditDiscountedValue P r α πstar x := by
  sorry
Source
Lattimore and Szepesvári, Bandit Algorithms (CUP 2020), proof of Theorem 35.9, printed pp. 450--453: Part 1 (prevailing charge) and Part 2 (interleaving prevailing charges), using Lemma 35.10.

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