Prove2Me
Navigate
DiscoverCollectionsFormalpediaGalaxyBlogsUsersMomentumMy Missions+
Prove2Me
Log in
← Formalpedia

Theorem 2.2, first clause, p. 4 — the discounted parallel value backup is a γ-contraction in max norm

Proved
StableFA.Discounted.theorem_2_2_contraction

by mikedeng1 · Oct 6, 2026 · Mathlib 0df444a (Lean v4.33.1)

bellman-operatorcontractionmarkov-decision-processp2o-batch-pfp2ap2o-gran-per-chapterp2o-plan-paperp2o-v1value-iteration

Let MMM be a finite Markov decision process with states 1,…,n1,\dots,n1,…,n, admissible action sets U(i)U(i)U(i) (finite and nonempty), expected one-step costs ciac_{ia}cia​ and transition probabilities paij≥0p_{aij}\ge 0paij​≥0 with ∑jpaij=1\sum_j p_{aij}=1∑j​paij​=1 for every admissible action a∈U(i)a\in U(i)a∈U(i). Let 0≤γ<10\le\gamma<10≤γ<1 be the discount factor. The parallel value iteration operator TMT_MTM​ maps a value function V∈RnV\in\mathbb R^nV∈Rn to

(TMV)(i)=min⁡a∈U(i)(cia+γ∑j=1npaijV(j)).(T_M V)(i)=\min_{a\in U(i)}\Big(c_{ia}+\gamma\sum_{j=1}^n p_{aij}V(j)\Big).(TM​V)(i)=a∈U(i)min​(cia​+γj=1∑n​paij​V(j)).

Then TMT_MTM​ is a contraction in the max norm ∥V∥=max⁡i∣V(i)∣\|V\|=\max_i|V(i)|∥V∥=maxi​∣V(i)∣ with contraction factor γ\gammaγ: for all V,W∈RnV,W\in\mathbb R^nV,W∈Rn,

∥TMV−TMW∥≤γ ∥V−W∥.\|T_M V-T_M W\|\le\gamma\,\|V-W\| .∥TM​V−TM​W∥≤γ∥V−W∥.

This is the basic fact behind the convergence of value iteration in discounted problems, and the starting point of every stability and error bound for approximate value iteration in this mission.

Formalization Note The MDP is the published BertsekasSSPModel, whose rows are only substochastic; the hypothesis ∑jpaij=1\sum_j p_{aij}=1∑j​paij​=1 makes it Gordon's (stochastic) MDP. ∥⋅∥\|\cdot\|∥⋅∥ on Fin n → ℝ is the max norm. Action sets may differ between states, which harmlessly generalizes the paper's single action set AAA. This item is the first sentence of Theorem 2.2 only; the nondiscounted clause and the identification of the fixed point with the optimal value function are not part of it.

Preamble
import Mathlib
import Definitions.Def_BertsekasSSPModel
import Definitions.Def_StableFA_Discounted_Setting

open Filter Topology
Formal statement
namespace StableFA.Discounted

theorem theorem_2_2_contraction {n : ℕ} {C : Type} [Fintype C] (M : BertsekasSSPModel n C)
    (γ : ℝ) (hγ0 : 0 ≤ γ) (hγ1 : γ < 1)
    (hp1 : ∀ i, ∀ u ∈ M.U i, ∑ j, M.p i u j = 1) :
    ∀ V W : Fin n → ℝ,
      ‖BertsekasDiscountedBellmanOp M γ V - BertsekasDiscountedBellmanOp M γ W‖ ≤
        γ * ‖V - W‖ := by sorry

end StableFA.Discounted
Source
Gordon, Stable Function Approximation in Dynamic Programming, Tech. Rep. CMU-CS-95-103, Carnegie Mellon University (1995), p. 4, Theorem 2.2 (value contraction), first sentence
Human review
  • Endorsed by Shuze Chen · Oct 6, 2026

    Confirmed by the moderator at approval.

  • Endorsed by mikedeng1 · Oct 6, 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