Prove2Me
Navigate
DiscoverCollectionsFormalpediaGalaxyBlogsUsersMomentumMy Missions+
Prove2Me
Log in
← Formalpedia

(25), p. 39 — comparator transfer term bounded by Q-prediction loss

Proved
PolicyGradTheory.QNPG.transfer_term_bound

by mikedeng1 · Oct 6, 2026 · Mathlib 0df444a (Lean v4.33.1)

comparator-measurep2o-batch-pfp2ap2o-gran-per-chapterp2o-plan-paperp2o-v1q-npgtransfer-error

Fix a comparator policy π⋆, a starting distribution ρ, log-linear features φ, a parameter θ, and any weight vector w. Under d⋆=dρπ⋆×UnifAd^\star=d^{\pi^\star}_\rho\times\mathrm{Unif}_Ad⋆=dρπ⋆​×UnifA​, the comparator-weighted discrepancy between advantage and the log-policy score obeys

Es∼dρπ⋆,a∼π⋆[Aπθ(s,a)−w⋅∇θlog⁡πθ(a∣s)]≤2∣A∣ L(w;θ,d⋆).\mathbb E_{s\sim d^{\pi^\star}_\rho,a\sim\pi^\star} [A^{\pi_\theta}(s,a)-w\cdot\nabla_\theta\log\pi_\theta(a\mid s)] \le 2\sqrt{|A|\,L(w;\theta,d^\star)}.Es∼dρπ⋆​,a∼π⋆​[Aπθ​(s,a)−w⋅∇θ​logπθ​(a∣s)]≤2∣A∣L(w;θ,d⋆)​.

This controls the transfer component of the regret error by a prediction loss under the comparator's states.

Formalization Note The paper displays this inequality for its exact minimizer w⋆(t)w_\star^{(t)}w⋆(t)​; the displayed derivation uses no minimizing property, so this statement allows any w.

Preamble
import Mathlib
import Definitions.Def_PolicyGradTheory_QNPG_Setting
Formal statement
namespace PolicyGradTheory.QNPG

open FoundationsML.ReinforcementLearning

/-- Inequality (25), proof of Theorem 6.1, p. 39. The displayed proof
uses no minimizing property of its weight vector. -/
theorem transfer_term_bound {S A : Type} [Fintype S] [DecidableEq S]
    [Fintype A] [DecidableEq A] [Nonempty A] {d : ℕ}
    (P : S → A → S → ℝ) (r : S → A → ℝ) (γ : ℝ)
    (hM : PolicyGradTheory.ProjGA.IsFiniteMDP P r γ)
    (ρ : S → ℝ) (hρ : PolicyGradTheory.ProjGA.IsDist ρ)
    (πstar : S → A → ℝ) (hπstar : IsPolicy πstar)
    (φ : S → A → EuclideanSpace ℝ (Fin d))
    (θ w : EuclideanSpace ℝ (Fin d)) :
    (∑ s : S, PolicyGradTheory.ProjGA.visitation πstar P γ ρ s *
      ∑ a : A, πstar s a *
        (PolicyGradTheory.ProjGA.advantage (logLinearPolicy φ θ) P r γ s a -
          inner ℝ w (gradient (fun x => Real.log (logLinearPolicy φ x s a)) θ))) ≤
      2 * Real.sqrt ((Fintype.card A : ℝ) *
        qLoss P r γ φ w θ (dstar P γ ρ πstar)) := by sorry

end PolicyGradTheory.QNPG
Source
arXiv:1908.00261v5, (25), proof of Theorem 6.1, p. 39
Human review
  • Endorsed by Shuze Chen · Oct 6, 2026

    Confirmed by the moderator at approval.

  • Endorsed by mikedeng1 · Oct 6, 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