Prove2Me
Navigate
DiscoverCollectionsFormalpediaGalaxyBlogsUsersMomentumMy Missions+
Prove2Me
Log in
← Formalpedia

Theorem 4.1, p. 16 (base case, p. 18) — along every orbit of (RL), every strictly dominated strategy becomes extinct

Proved
ReinfRegGames.Extinction.theorem_4_1_dominated

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

dominated-strategiesextinctionlearning-in-gamesp2o-batch-pfp2ap2o-gran-per-chapterp2o-plan-paperp2o-v1

Consider a finite game in normal form, a penalty function hℓh_\ellhℓ​ (Definition 2.1) for every player ℓ\ellℓ, and an orbit x(t)=Q(y(t))x(t)=Q(y(t))x(t)=Q(y(t)), t≥0t\ge0t≥0, of the reinforcement learning dynamics (RL). Let kkk be a player and pk,pk′∈Xkp_k,p'_k\in\mathcal X_kpk​,pk′​∈Xk​ mixed strategies such that pkp_kpk​ is dominated by pk′p'_kpk′​:

uk(pk;z−k)<uk(pk′;z−k)for every mixed profile z∈X.(4.1)u_k(p_k;z_{-k})<u_k(p'_k;z_{-k})\qquad\text{for every mixed profile } z\in\mathcal X. \qquad (4.1)uk​(pk​;z−k​)<uk​(pk′​;z−k​)for every mixed profile z∈X.(4.1)

Then pkp_kpk​ becomes extinct along x(t)x(t)x(t):

min⁡{xkα(t): α∈supp⁡(pk)} ⟶ 0(t→∞).\min\{x_{k\alpha}(t):\ \alpha\in\operatorname{supp}(p_k)\}\ \longrightarrow\ 0\qquad (t\to\infty).min{xkα​(t): α∈supp(pk​)} ⟶ 0(t→∞).

This is the case of Theorem 4.1 for strategies that are dominated in the original game, the base case r=1r=1r=1 of the paper's induction. No steepness of the penalty functions is assumed.

Formalization Note Extinction is written without a minimum: for every ε>0\varepsilon>0ε>0 there is TTT such that for every t≥Tt\ge Tt≥T some α\alphaα with pkα>0p_{k\alpha}>0pkα​>0 has xkα(t)<εx_{k\alpha}(t)<\varepsilonxkα​(t)<ε; this is the limit, not a lim inf⁡\liminfliminf. Every player has a penalty function because the orbit uses every player's choice map.

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

theorem theorem_4_1_dominated {ι : Type*} [Fintype ι] [DecidableEq ι] {A : ι → Type*}
    [∀ k, Fintype (A k)] [∀ k, DecidableEq (A k)]
    (u : ι → (∀ k, A k) → ℝ) (h : ∀ k, (A k → ℝ) → ℝ) (K : ι → ℝ)
    (hpen : ∀ k, IsPenalty (h k) (K k))
    (y x : ℝ → ∀ k, A k → ℝ) (horb : IsRLOrbit u h y x)
    (k : ι) (p p' : A k → ℝ) (hp : AGT.IsLottery p) (hp' : AGT.IsLottery p')
    (hdom : ∀ z : ∀ ℓ, A ℓ → ℝ, AGT.IsMixedProfile z →
      AGT.expectedPayoff u (Function.update z k p) k <
        AGT.expectedPayoff u (Function.update z k p') k) :
    ∀ ε > 0, ∃ T : ℝ, ∀ t ≥ T, ∃ α, 0 < p α ∧ x t k α < ε := by sorry

end ReinfRegGames.Extinction
Source
Mertikopoulos & Sandholm, Learning in games via reinforcement and regularization, arXiv:1407.6267v2, p. 16, Theorem 4.1 (dominated case); proof p. 18
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