Prove2Me
Navigate
DiscoverCollectionsFormalpediaGalaxyBlogsUsersMomentumMy Missions+
Prove2Me
Log in
← Formalpedia

(5.3), p. 8 — every eigenvalue ω of B_π solves ω² − (μ+1)(1 − √(1/κ))ω + ½(μ+1)(1 − √(1/κ))² = 0 for some μ ∈ Sp(L_π)

Proved
AccelVI.AVC.eq_5_3

by mikedeng1 · Oct 15, 2026 · Mathlib 0df444a (Lean v4.33.1)

accelerationblock-matrixp2o-batch-pfp2ap2o-gran-per-chapterp2o-plan-paperp2o-v1spectrum

Let (S,A,P,r,λ)(\mathbb S,\mathbb A,P,r,\lambda)(S,A,P,r,λ) be a finite MDP with λ∈(0,1)\lambda\in(0,1)λ∈(0,1), π\piπ a policy with transition matrix LπL_\piLπ​, κ=(1+λ)/(1−λ)\kappa=(1+\lambda)/(1-\lambda)κ=(1+λ)/(1−λ), and BπB_\piBπ​ the matrix (5.1). For every complex eigenvalue ω\omegaω of BπB_\piBπ​ there is a complex eigenvalue μ\muμ of LπL_\piLπ​ such that

ω2−(μ+1)(1−1/κ) ω+12(μ+1)(1−1/κ)2=0.\omega^2-(\mu+1)\big(1-\sqrt{1/\kappa}\big)\,\omega+\tfrac12(\mu+1)\big(1-\sqrt{1/\kappa}\big)^2=0.ω2−(μ+1)(1−1/κ​)ω+21​(μ+1)(1−1/κ​)2=0.

The equation ties the spectrum of BπB_\piBπ​ to that of LπL_\piLπ​; its two roots ω±(μ)\omega^\pm(\mu)ω±(μ) are the candidates for the leading eigenvalue of BπB_\piBπ​. No reversibility is needed.

Formalization Note. Both spectra are taken over C\mathbb CC (the matrices are real, their eigenvalues need not be).

Preamble
import Mathlib
import Definitions.Def_mm_basic
import Definitions.Def_AccelVI_AVC_Setting
Formal statement
namespace AccelVI.AVC

variable {S A : Type*} [Fintype S] [DecidableEq S] [Fintype A]

/-- (5.3), p. 8 (proof of Lemma 5.3): every complex eigenvalue `ω` of `B_π` satisfies
`ω² − (μ + 1)(1 − √(1/κ))ω + ½(μ + 1)(1 − √(1/κ))² = 0` for some eigenvalue `μ` of `L_π`. -/
theorem eq_5_3 (M : MDP S A) (hM : M.Valid) (pol : S → A → ℝ) (hpol : FoundationsML.ReinforcementLearning.IsPolicy pol) :
    ∀ ω ∈ spectrum ℂ ((Bpol M pol).map (algebraMap ℝ ℂ)),
      ∃ μ ∈ spectrum ℂ ((LPol M pol).map (algebraMap ℝ ℂ)),
        ω ^ 2 - (μ + 1) * (theta M.lam : ℂ) * ω + 1 / 2 * (μ + 1) * (theta M.lam : ℂ) ^ 2 = 0 := by sorry

end AccelVI.AVC
Source
Goyal & Grand-Clément, A First-Order Approach to Accelerated Value Iteration, arXiv:1905.09963v7, p. 8, proof of Lemma 5.3, display (5.3)
Human review
  • Endorsed by Shuze Chen · Oct 15, 2026

    Confirmed by the moderator at approval.

  • Endorsed by mikedeng1 · Oct 15, 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