Prove2Me
Navigate
DiscoverCollectionsFormalpediaGalaxyBlogsUsersMomentumMy Missions+
Prove2Me
Log in
← Formalpedia

Expected Gittins terminal-potential envelope

Proved
BanditAlgorithm.gittins_expected_terminal_potential_le_stack_envelope

by Harry_Xu · Aug 1, 2026 · Mathlib c5ea003 (Lean v4.30.0)

banditsgittins-indexprobability

For any finite horizon NNN and any Markov bandit policy π\piπ, the expected terminal Gittins retirement potential is bounded by the expectation of the explicit retirement envelope on the common product space of independent arm trajectories:

UNπ≤∫EN(ω) dMx(ω).U_N^\pi\le \int E_N(\omega)\,dM_x(\omega).UNπ​≤∫EN​(ω)dMx​(ω).

Here MxM_xMx​ is the product of the arms' Markov-chain laws started from the initial state vector xxx. The envelope is displayed explicitly in the formal statement and is independent of the policy.

This theorem transfers the pathwise retirement-envelope estimate to arbitrary adaptive policies.

Preamble
import Definitions.Def_GittinsTerminalPotential
Formal statement
open MeasureTheory ProbabilityTheory ENNReal

theorem BanditAlgorithm.gittins_expected_terminal_potential_le_stack_envelope
    {k N : 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)
    (π : MarkovBanditPolicy k S) (x : Fin k → S) :
    let absoluteValue := fun y : S ↦
      ∫ path, ∑' t : ℕ, α ^ t * |r (path t)|
        ∂markovChainMeasure P y
    let envelope := fun (ω : Fin k → ℕ → S) ↦ ∑ i : Fin k,
      ((∑ u ∈ Finset.range (N + 1), absoluteValue (ω i u)) +
        (∑' t : ℕ, α ^ t) *
          (absoluteValue (ω i 0) +
            ∑ v ∈ Finset.range N, |r (ω i (v + 1))|))
    let stackMeasure : Measure (Fin k → ℕ → S) :=
      Measure.pi (fun i ↦ markovChainMeasure P (x i))
    markovBanditExpectedRetirementPotential P r α π x N ≤
      ∫ ω, envelope ω ∂stackMeasure := by
  sorry
Source
Tor Lattimore and Csaba Szepesvári, Bandit Algorithms, §35.4, proof of Lemma 35.10, printed pp. 452–453 (free PDF pp. 460–461), https://tor-lattimore.com/downloads/book/book.pdf

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