Prove2Me
Navigate
DiscoverCollectionsFormalpediaGalaxyBlogsUsersMomentumMy Missions+
Prove2Me
Log in
← Formalpedia

Remark 6.7, p. 33 — bounded log-linear features give B²-smooth log policies

Proved
PolicyGradTheory.QNPG.log_linear_smooth

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

log-linear-policyp2o-batch-pfp2ap2o-gran-per-chapterp2o-plan-paperp2o-v1smoothness

For a log-linear policy with feature vectors of Euclidean norm at most B, the log probability of any fixed state-action pair has a B²-Lipschitz parameter gradient:

∥∇θlog⁡πθ(a∣s)−∇θlog⁡πθ′(a∣s)∥≤B2∥θ−θ′∥.\|\nabla_\theta\log\pi_\theta(a\mid s)- \nabla_\theta\log\pi_{\theta'}(a\mid s)\| \le B^2\|\theta-\theta'\|.∥∇θ​logπθ​(a∣s)−∇θ​logπθ′​(a∣s)∥≤B2∥θ−θ′∥.

This is the paper's smoothness condition for applying its deterministic NPG regret lemma to log-linear policies.

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

/-- Remark 6.7, p. 33, with smoothness understood as the gradient-Lipschitz
condition preceding (24), p. 37. -/
theorem log_linear_smooth {S A : Type} [Fintype A] [Nonempty A] {d : ℕ}
    (φ : S → A → EuclideanSpace ℝ (Fin d)) (B : ℝ)
    (hφ : ∀ s a, ‖φ s a‖ ≤ B) (s : S) (a : A) :
    ∀ θ θ' : EuclideanSpace ℝ (Fin d),
      ‖gradient (fun x => Real.log (logLinearPolicy φ x s a)) θ -
        gradient (fun x => Real.log (logLinearPolicy φ x s a)) θ'‖ ≤
        B ^ 2 * ‖θ - θ'‖ := by sorry

end PolicyGradTheory.QNPG
Source
arXiv:1908.00261v5, Remark 6.7, p. 33; smoothness definition (24), p. 37
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