Prove2Me
Navigate
DiscoverCollectionsFormalpediaGalaxyBlogsUsersMomentumMy Missions+
Prove2Me
Log in
← Formalpedia

Theorem 6.1, p. 25 — in 2-player games, bounded score differences make the time average of an (RL) orbit converge to the Nash set

Proved
ReinfRegGames.TimeAvg.theorem_6_1

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

learning-in-gamesnash-equilibriump2o-batch-pfp2ap2o-gran-per-chapterp2o-plan-paperp2o-v1reinforcement-learningtime-average

Let G\mathcal GG be a 2-player game with finite strategy sets A1,A2\mathcal A_1, \mathcal A_2A1​,A2​ and payoffs u1,u2u_1, u_2u1​,u2​, let each player use a penalty function hkh_khk​ (Definition 2.1), and let (y(t),x(t))(y(t), x(t))(y(t),x(t)) be an orbit of (RL), x(t)=Q(y(t))x(t) = Q(y(t))x(t)=Q(y(t)). Suppose the score differences remain bounded: there is MMM with

∣ykα(t)−ykβ(t)∣≤Mfor all t≥0, k=1,2, α,β∈Ak.|y_{k\alpha}(t) - y_{k\beta}(t)| \le M \qquad\text{for all } t \ge 0,\ k = 1, 2,\ \alpha, \beta \in \mathcal A_k .∣ykα​(t)−ykβ​(t)∣≤Mfor all t≥0, k=1,2, α,β∈Ak​.

Then G\mathcal GG has a Nash equilibrium, and the time average xˉ(t)=t−1∫0tx(s) ds\bar x(t) = t^{-1}\int_0^t x(s)\,dsxˉ(t)=t−1∫0t​x(s)ds converges to the set NE(G)\mathrm{NE}(\mathcal G)NE(G) of mixed Nash equilibria:

dist⁡(xˉ(t),NE(G))→0(t→∞).\operatorname{dist}\big(\bar x(t), \mathrm{NE}(\mathcal G)\big) \to 0 \qquad (t \to \infty).dist(xˉ(t),NE(G))→0(t→∞).

This is the reinforcement-learning analogue of the classical result that interior replicator trajectories of 2-player games have time averages converging to the Nash set; bounded score differences replace "staying away from the boundary".

Formalization Note Players are indexed by Fin 2; the page states and proves the result only for 2-player games (the proof uses that vkv_kvk​ is linear in the single opponent's strategy). Distances are those of Lean's sup metric on profiles. Because the distance to the empty set is 000 in Lean, the conclusion includes explicitly that the Nash set is nonempty, which is what the page's proof shows (the ω-limit set of xˉ(t)\bar x(t)xˉ(t) is nonempty and consists of Nash equilibria); without it the convergence statement would hold vacuously for a game without equilibria.

Preamble
import Mathlib
import Definitions.Def_agt_games
import Definitions.Def_ReinfRegGames_Extinction_Model
import Definitions.Def_ReinfRegGames_TimeAvg_TimeAverage
Formal statement
namespace ReinfRegGames.TimeAvg

theorem theorem_6_1 {A : Fin 2 → Type*} [∀ k, Fintype (A k)] [∀ k, DecidableEq (A k)]
    (u : Fin 2 → (∀ k, A k) → ℝ)
    (h : ∀ k, (A k → ℝ) → ℝ) (K : Fin 2 → ℝ) (hpen : ∀ k, ReinfRegGames.Extinction.IsPenalty (h k) (K k))
    (y x : ℝ → ∀ k, A k → ℝ) (horb : ReinfRegGames.Extinction.IsRLOrbit u h y x)
    (hbdd : ∃ M : ℝ, ∀ t, 0 ≤ t → ∀ k (α β : A k), |y t k α - y t k β| ≤ M) :
    {z : ∀ k, A k → ℝ | AGT.IsMixedNash u z}.Nonempty ∧
    Filter.Tendsto (fun t => Metric.infDist (timeAvg x t) {z | AGT.IsMixedNash u z})
      Filter.atTop (nhds 0) := by sorry

end ReinfRegGames.TimeAvg
Source
Mertikopoulos & Sandholm, Learning in games via reinforcement and regularization, arXiv:1407.6267v2, p. 25, Theorem 6.1
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