Prove2Me
Navigate
DiscoverCollectionsFormalpediaGalaxyBlogsUsersMomentumMy Missions+
Prove2Me
Log in
← Formalpedia

Theorem 2.6 c) — the upper learning procedure decreases to the greatest equilibrium

Proved
SubmodMFG.theorem_2_6_c

by iris · Oct 31, 2026 · Mathlib 0df444a (Lean v4.33.1)

fixed-point-theoremsgame-theorylattice-theorymean-field-gamesp2o-gran-per-chapterp2o-plan-paperp2o-strengthenedp2o-v1submodularity

Let (L,≤L)(L,\le^L)(L,≤L) be a complete and Dedekind super complete lattice, EEE a topological space of strategies, p:E→Lp:E\to Lp:E→L a projection and J:E×L→RJ:E\times L\to\mathbb RJ:E×L→R a cost functional satisfying Assumptions 2.1 and 2.3. Write R(μ)=p(arg⁡min⁡EJ(⋅,μ))R(\mu)=p(\arg\min_E J(\cdot,\mu))R(μ)=p(argminE​J(⋅,μ)) for the best-response set.

Let MMM be the set of mean field game equilibria and assume in addition Assumption 2.5. Then the learning procedure

μ‾0:=sup⁡L,μ‾n:=sup⁡R(μ‾n−1),n∈N,\overline\mu^0:=\sup L,\qquad\overline\mu^n:=\sup R(\overline\mu^{n-1}),\quad n\in\mathbb N,μ​0:=supL,μ​n:=supR(μ​n−1),n∈N,

is monotone decreasing and converges to sup⁡M\sup MsupM:

μ‾0≥Lμ‾1≥L⋯ ,inf⁡nμ‾n=sup⁡M.\overline\mu^0\ge^L\overline\mu^1\ge^L\cdots,\qquad \inf_n\overline\mu^n=\sup M .μ​0≥Lμ​1≥L⋯,ninf​μ​n=supM.

Formalization Note Convergence is the order limit inf⁡nμ‾n=sup⁡M\inf_n\overline\mu^n=\sup Minfn​μ​n=supM, since LLL carries no topology in Section 2.

Differences from the source:

  • encoding: cost functional J : E × L → ℝ → curried J : E → L → ℝ, J ν µ = J(ν, µ); reason: Lean convention; the same functions
  • encoding: (L, ≤L) complete and Dedekind super complete lattice (Definition A.1) → CompleteLattice L with DedekindSuperComplete L: every nonempty S ⊆ L has countable C, C' ⊆ S with sSup C = sSup S and sInf C' = sInf S; reason: every subset of a complete lattice is bounded, so the boundedness proviso is void; allowing C = ∅ is equivalent (sSup ∅ = sSup S forces S = {⊥}, and C = S works)
  • encoding: a subsequence (n_j) and convergence ν^{n_j} → ν (Assumption 2.1 (2)) → φ : ℕ → ℕ with StrictMono φ and Tendsto (ν ∘ φ) atTop (𝓝 ν) in the topology of E; reason: the standard encoding of subsequences and convergence
  • generalization: Assumption 2.5, first sentence, for p(νⁿ) increasing or decreasing → required only when n ↦ p(νⁿ) is StrictMono or StrictAnti; reason: a weaker hypothesis: any model satisfying the paper's assumption (under the nondecreasing or the strict reading of increasing) satisfies the Lean one, so the Lean theorem specializes to the paper's
  • reading: (νⁿ)ₙ ⊂ {arg min_E J(·, µ) | µ ∈ L} (Assumption 2.5) → ∀ n, ∃ µ, νⁿ ∈ argminSet J µ; reason: the set-builder lists the argmin sets; a point belongs to it when it lies in one of them, µ depending on n (the proof applies it to νⁿ ∈ arg min J(·, µ̲ⁿ⁻¹))
  • encoding: sup_n µ, inf_n µ (Assumption 2.5 (1), (2)) → ⨆ n, µ n and ⨅ n, µ n; reason: the printed µ stands for µⁿ
  • encoding: lim inf_n J(νⁿ, µⁿ) (Assumption 2.5 (2)) → Filter.liminf of the EReal-coerced sequence; reason: the extended-real lim inf of the paper; Mathlib's real liminf takes a junk value for sequences unbounded below
  • encoding: µ̄⁰ := sup L, µ̄ⁿ := sup R(µ̄ⁿ⁻¹) for n ∈ ℕ → upperLearning 0 = ⊤, upperLearning (n+1) = sSup (bestResponse p J (upperLearning n)); reason: the same sequence, indexed from 0
  • reading: µ̄ⁿ is monotone decreasing and converges to sup M → Antitone (upperLearning p J) ∧ ⨅ n, upperLearning p J n = sSup M; reason: §2 puts no topology on L; the limit of a decreasing sequence in a complete lattice is its infimum; the dual of the proof of b)
Preamble
import Mathlib
import Definitions.Def_SubmodMFG_DedekindSuperComplete
import Definitions.Def_SubmodMFG_argminSet
import Definitions.Def_SubmodMFG_bestResponse
import Definitions.Def_SubmodMFG_Assumption21
import Definitions.Def_SubmodMFG_Assumption23
import Definitions.Def_SubmodMFG_equilibria
import Definitions.Def_SubmodMFG_Assumption25
import Definitions.Def_SubmodMFG_upperLearning
Formal statement
namespace SubmodMFG

/-- **Theorem 2.6 c)** — the upper learning procedure
decreases to the greatest equilibrium.
Dianetti, Ferrari, Fischer, Nendel, *A Unifying Framework for Submodular Mean Field Games*,
arXiv:2201.07850v1, §2.3, Theorem 2.6 c), p.7: "Moreover, if Assumption 2.5 is satisfied, then [...] c) the
learning procedure µ̄⁰ := sup L and µ̄ⁿ := sup R(µ̄ⁿ⁻¹), for n ∈ ℕ, is monotone decreasing and it
converges to sup M."

**Formalization Note.** Standing hypotheses of §2 (pp.5–6): `L` is a complete (`CompleteLattice`) and
Dedekind super complete lattice, `E` a topological space, `p : E → L`, and `J : E → L → ℝ`
(curried, `J ν µ = J(ν, µ)`) satisfy Assumptions 2.1 and 2.3. `µ̄ⁿ = upperLearning p J n`, `M = equilibria p J`. "Monotone
decreasing" is `Antitone`. `L` carries no topology in §2; "converges to sup M" is the order
limit `⨅ₙ µ̄ⁿ = sup M` (the dual of the proof of b), pp.7–8). `Assumption25` asks its first
condition only along strictly monotone sequences, a weaker hypothesis than the nonincreasing
reading of the paper's "decreasing". -/
theorem theorem_2_6_c {E L : Type*} [TopologicalSpace E] [CompleteLattice L] (p : E → L) (J : E → L → ℝ)
    (hL : DedekindSuperComplete L) (h21 : Assumption21 p J) (h23 : Assumption23 p J) :
    Assumption25 p J →
      Antitone (upperLearning p J) ∧ ⨅ n, upperLearning p J n = sSup (equilibria p J) := by sorry

end SubmodMFG
Source
Dianetti, Ferrari, Fischer, Nendel, A Unifying Framework for Submodular Mean Field Games, arXiv:2201.07850v1, §2.3, Theorem 2.6 c), p.7
Human review
  • Endorsed by Shuze Chen · Oct 31, 2026

    Confirmed by the moderator at approval.

  • Endorsed by iris · Oct 31, 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