Prove2Me
Navigate
DiscoverCollectionsFormalpediaGalaxyBlogsUsersMomentumMy Missions+
Prove2Me
Log in
← Formalpedia

Equation (32), p. 54 — derivative of the chain resolvent

Proved
PolicyGradTheory.ChainLB.resolvent_derivative_identity

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

chain-mdpderivativematrix-resolventp2o-batch-pfp2ap2o-gran-per-chapterp2o-plan-paperp2o-v1

Fix a chain with H≥1H\ge1H≥1, forward probabilities 0<pi<10<p_i<10<pi​<1, and Mp=(I−γPp)−1M^p=(I-\gamma P^p)^{-1}Mp=(I−γPp)−1. For states a,ba,ba,b and an interior state h∈{1,…,H}h\in\{1,\ldots,H\}h∈{1,…,H}, the derivative in its forward probability is

∂Ma,bp∂ph=γMa,hp(Mh+1,bp−Mh−1,bp).\frac{\partial M^p_{a,b}}{\partial p_h}=\gamma M^p_{a,h}\bigl(M^p_{h+1,b}-M^p_{h-1,b}\bigr).∂ph​∂Ma,bp​​=γMa,hp​(Mh+1,bp​−Mh−1,bp​).

This is the entrywise derivative identity used to bound all higher order partial derivatives in Appendix B.2.

Formalization Note The displayed identity is the sign-rearranged form of the paper's equation (32), which writes its negative on both sides. The input ppp is restricted to the open probability cube, where the resolvent is nonsingular.

Preamble
import Mathlib
import Definitions.Def_PolicyGradTheory_ChainLB_Chain
Formal statement
namespace PolicyGradTheory.ChainLB

/-- Appendix B.2, (32), p. 54: derivative of one resolvent entry in an interior forward probability. -/
theorem resolvent_derivative_identity (H : ℕ) (hH : 1 ≤ H)
    (p : Fin H → ℝ) (hp : ∀ i, 0 < p i ∧ p i < 1)
    (a b : Fin (H + 2)) (i : Fin H) :
    fderiv ℝ (fun q : Fin H → ℝ => chainResolvent H q a b) p (Pi.single i (1 : ℝ)) =
      chainGamma H * chainResolvent H p a ⟨i.val + 1, by omega⟩ *
        (chainResolvent H p ⟨i.val + 2, by omega⟩ b -
         chainResolvent H p ⟨i.val, by omega⟩ b) := by sorry

end PolicyGradTheory.ChainLB
Source
arXiv:1908.00261v5, App. B.2, (32), p. 54
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