Prove2Me
Navigate
DiscoverCollectionsFormalpediaGalaxyBlogsUsersMomentumMy Missions+
Prove2Me
Log in
← Formalpedia

Lemma 1 (first claim) — robust value iteration stops, and its output is within ε/4 of V*_λ

Proved
RobustDP.Discounted.lemma1_value_iteration

by mikedeng1 · Oct 7, 2026 · Mathlib 0df444a (Lean v4.33.1)

dynamic-programmingp2o-batch-pfp2ap2o-gran-per-chapterp2o-plan-paperp2o-v1robust-optimizationvalue-iteration

Let (S,A,P,r,λ)(\mathcal S,\mathcal A,\mathcal P,r,\lambda)(S,A,P,r,λ) be a discounted ambiguous MDP, let T\mathcal TT be the operator of (30), let V0V_0V0​ be bounded and ϵ>0\epsilon>0ϵ>0, and let Vk=TkV0V_k=\mathcal T^kV_0Vk​=TkV0​. The robust value iteration algorithm of Figure 1 returns V~=VK+1\tilde V=V_{K+1}V~=VK+1​, where KKK is the first index with

∥VK+1−VK∥<1−λ4λ ϵ.\|V_{K+1}-V_K\|<\frac{1-\lambda}{4\lambda}\,\epsilon .∥VK+1​−VK​∥<4λ1−λ​ϵ.

Then such a KKK exists (the algorithm stops), and for the first such KKK,

∥V~−Vλ∗∥=∥VK+1−Vλ∗∥≤ϵ4.\|\tilde V-V^*_\lambda\|=\|V_{K+1}-V^*_\lambda\|\le\frac{\epsilon}{4}.∥V~−Vλ∗​∥=∥VK+1​−Vλ∗​∥≤4ϵ​.

This is the approximation guarantee of robust value iteration.

Formalization Note The algorithm is encoded by its iterates: the stopping index KKK is characterized by the stopping test holding at KKK and failing at every k<Kk<Kk<K. Only the first sentence of Lemma 1 is stated. Its second claim (an ϵ/2\epsilon/2ϵ/2-greedy rule against V~\tilde VV~ is ϵ\epsilonϵ-optimal) is false as printed and is not part of the mission. Figure 1's header says ϵ/2\epsilon/2ϵ/2; the Lemma's ϵ/4\epsilon/4ϵ/4 is used.

Preamble
import Mathlib
import Definitions.Def_RobustDP_Discounted_Model
import Definitions.Def_RobustDP_Discounted_Value
import Definitions.Def_RobustDP_Discounted_Bellman
Formal statement
namespace RobustDP.Discounted

theorem lemma1_value_iteration {S A : Type*} [Countable S] [Countable A] (M : Model S A)
    (V₀ : S → ℝ) (hV₀ : IsBounded V₀) (ε : ℝ) (hε : 0 < ε) :
    let Vk : ℕ → S → ℝ := fun k => (T M)^[k] V₀
    let c : ℝ := (1 - M.lam) / (4 * M.lam) * ε
    (∃ K, supNorm (fun s => Vk (K + 1) s - Vk K s) < c) ∧
      ∀ K, supNorm (fun s => Vk (K + 1) s - Vk K s) < c →
        (∀ k < K, c ≤ supNorm (fun s => Vk (k + 1) s - Vk k s)) →
        supNorm (fun s => Vk (K + 1) s - Vstar M s) ≤ ε / 4 := by sorry

end RobustDP.Discounted
Source
Iyengar, Robust dynamic programming, CORC Tech Report TR-2002-07 (rev. May 4, 2004), p. 12, Lemma 1 (first sentence); algorithm in Figure 1, p. 11
Human review
  • Endorsed by Shuze Chen · Oct 7, 2026

    Confirmed by the moderator at approval.

  • Endorsed by mikedeng1 · Oct 7, 2026

    Confirmed by the mission captain (proposal self-audit).

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