Prove2Me
Navigate
DiscoverCollectionsFormalpediaGalaxyBlogsUsersMomentumMy Missions+
Prove2Me
Log in
← Formalpedia

Proposition A.1(iii), p. 31 — Q_α(y) → 0 whenever y_α − y_β → −∞ for some β ≠ α

Proved
ReinfRegGames.StrictStable.proposition_A_1_iii

by mikedeng1 · Oct 9, 2026 · Mathlib 0df444a (Lean v4.33.1)

choice-maplearning-in-gamesp2o-batch-pfp2ap2o-gran-per-chapterp2o-plan-paperp2o-v1penalty-function

Let hhh be a penalty function on the simplex Δ=Δ(B)\Delta=\Delta(B)Δ=Δ(B) of a finite set BBB (Definition 2.1, strong convexity constant KKK), and let QQQ be its choice map, Q(y)=arg⁡max⁡x∈Δ{⟨y∣x⟩−h(x)}Q(y)=\arg\max_{x\in\Delta}\{\langle y|x\rangle-h(x)\}Q(y)=argmaxx∈Δ​{⟨y∣x⟩−h(x)}. Let α≠β\alpha\neq\betaα=β in BBB. Then Qα(y)→0Q_\alpha(y)\to0Qα​(y)→0 whenever yα−yβ→−∞y_\alpha-y_\beta\to-\inftyyα​−yβ​→−∞; uniformly:

∀ε>0 ∃M ∀y∈RB:yα−yβ<−M ⟹ Qα(y)<ε.\forall\varepsilon>0\ \exists M\ \forall y\in\mathbb R^B:\quad y_\alpha-y_\beta<-M\ \Longrightarrow\ Q_\alpha(y)<\varepsilon.∀ε>0 ∃M ∀y∈RB:yα​−yβ​<−M ⟹ Qα​(y)<ε.

A strategy whose score falls arbitrarily far behind that of another strategy is played with vanishing probability. In the proof of Theorem 5.2 this turns the divergence zkμ→−∞z_{k\mu}\to-\inftyzkμ​→−∞ of the relative scores into convergence x(t)→x∗x(t)\to x^*x(t)→x∗.

Formalization Note The page's "Qα(y)→0Q_\alpha(y)\to0Qα​(y)→0 whenever yα−yβ→−∞y_\alpha-y_\beta\to-\inftyyα​−yβ​→−∞" is stated in the uniform form that the proof (A.3)–(A.4) gives; it is equivalent to the sequential form. x=Q(y)x=Q(y)x=Q(y) is the predicate "xxx maximizes ⟨y∣⋅⟩−h\langle y|\cdot\rangle-h⟨y∣⋅⟩−h over Δ\DeltaΔ".

Preamble
import Mathlib
import Definitions.Def_agt_games
import Definitions.Def_ReinfRegGames_Extinction_Model
Formal statement
namespace ReinfRegGames.StrictStable

theorem proposition_A_1_iii {B : Type*} [Fintype B] (h : (B → ℝ) → ℝ) (K : ℝ) (hpen : ReinfRegGames.Extinction.IsPenalty h K)
    (α β : B) (hβα : β ≠ α) :
    ∀ ε > 0, ∃ M : ℝ, ∀ y x : B → ℝ, ReinfRegGames.Extinction.IsChoice h y x → y α - y β < -M → x α < ε := by sorry

end ReinfRegGames.StrictStable
Source
Mertikopoulos & Sandholm, Learning in games via reinforcement and regularization, arXiv:1407.6267v2, p. 31, Proposition A.1(iii) (proof (A.3)–(A.4))
Human review
  • Endorsed by Shuze Chen · Oct 9, 2026

    Confirmed by the moderator at approval.

  • Endorsed by mikedeng1 · Oct 9, 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