Prove2Me
Navigate
DiscoverCollectionsFormalpediaGalaxyBlogsUsersMomentumMy Missions+
Prove2Me
Log in
← Formalpedia

Finite prevailing-charge bound with terminal retirement potential

Proved
BanditAlgorithm.gittins_finite_reward_le_index_policy_add_terminal

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

banditsgittins-indexoptimal-stoppingprobability

Consider a kkk-armed rested Markov bandit with measurable rewards, discount factor 0<α<10<\alpha<10<α<1, and integrable discounted absolute rewards. Let π∗\pi^*π∗ be a policy that always selects an arm of maximal current Gittins index. For every competing policy π\piπ, initial state vector xxx, and horizon NNN,

∑n<Nαn Eπ[rn]≤∑n<Nαn Eπ∗[rn]+αNUNπ∗,\sum_{n<N}\alpha^n\,\mathbb E_\pi[r_n] \le \sum_{n<N}\alpha^n\,\mathbb E_{\pi^*}[r_n] +\alpha^N U_N^{\pi^*},n<N∑​αnEπ​[rn​]≤n<N∑​αnEπ∗​[rn​]+αNUNπ∗​,

where UNπ∗U_N^{\pi^*}UNπ∗​ is the expected terminal retirement potential evaluated at the prevailing charges after NNN rounds.

This is the finite-horizon accounting form of the prevailing-charge proof. It isolates the pathwise greedy interleaving comparison from the subsequent infinite-horizon tail passage.

Formalization Note The two finite discounted sums use the platform's round-reward marginals, while the final term uses markovBanditExpectedRetirementPotential.

Preamble
import Definitions.Def_GittinsTerminalPotential

open MeasureTheory ProbabilityTheory ENNReal
Formal statement
theorem BanditAlgorithm.gittins_finite_reward_le_index_policy_add_terminal
    {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 πstar : MarkovBanditPolicy k S)
    (hπstar : IsGittinsIndexPolicy P r α πstar)
    (x : Fin k → S) (N : ℕ) :
    (∑ n ∈ Finset.range N,
      α ^ n * markovBanditRoundReward P r π x n) ≤
      (∑ n ∈ Finset.range N,
        α ^ n * markovBanditRoundReward P r πstar x n) +
      α ^ N * markovBanditExpectedRetirementPotential
        P r α πstar x N := by
  sorry
Source
Tor Lattimore and Csaba Szepesvári, Bandit Algorithms (free online edition), https://tor-lattimore.com/downloads/book/book.pdf, §35.4, proof of Theorem 35.9, Parts 1–2, printed pp. 451–453 / PDF pp. 459–461; finite greedy comparison is 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