Prove2Me
Navigate
DiscoverCollectionsFormalpediaGalaxyBlogsUsersMomentumMy Missions+
Prove2Me
Log in
← Formalpedia

Vanishing discounted terminal retirement potential

Proved
BanditAlgorithm.tendsto_gittins_terminal_retirement_potential_zero

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

banditsgittins-indexintegrabilityprobability

Consider a finite-armed rested Markov bandit with measurable rewards and discount factor 0<α<10<\alpha<10<α<1. Under discounted absolute-reward integrability, the expected retirement potential at the prevailing charges grows slowly enough that its discounted terminal contribution vanishes:

αNUNπ⟶0(N→∞)\alpha^N U_N^\pi \longrightarrow 0 \qquad (N\to\infty)αNUNπ​⟶0(N→∞)

for every policy π\piπ and every initial state vector.

This theorem supplies the uniform-integrability tail step needed to pass from the finite prevailing-charge inequality to infinite-horizon Gittins optimality.

Formalization Note The conclusion is convergence in R\mathbb RR along Filter.atTop; no bounded-reward assumption is imposed beyond the platform's formalization of Assumption 35.6.

Preamble
import Definitions.Def_GittinsTerminalPotential

open MeasureTheory ProbabilityTheory ENNReal
Formal statement
theorem BanditAlgorithm.tendsto_gittins_terminal_retirement_potential_zero
    {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)
    (π : MarkovBanditPolicy k S) (x : Fin k → S) :
    Filter.Tendsto (fun N ↦ α ^ N *
      markovBanditExpectedRetirementPotential P r α π x N)
      Filter.atTop (nhds 0) := by
  sorry
Source
Tor Lattimore and Csaba Szepesvári, Bandit Algorithms (free online edition), https://tor-lattimore.com/downloads/book/book.pdf, Assumption 35.6 and §35.4 proof of Theorem 35.9, terminal passage after Parts 1–2, printed pp. 447 and 451–453 / PDF pp. 455 and 459–461.

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