Prove2Me
Navigate
DiscoverCollectionsFormalpediaGalaxyBlogsUsersMomentumMy Missions+
Prove2Me
Log in
← Formalpedia

§6.3.4, before (49) — policy value is stable under reward perturbation

Proved
BreakingSample.Perturbed.reward_stability

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

p2o-batch-pfp2ap2o-gran-per-chapterp2o-plan-paperp2o-v1reward-perturbationstabilityvalue-function

Keep a transition kernel and deterministic policy fixed, with 0≤γ<10\le\gamma<10≤γ<1. If the immediate rewards rrr and r′r'r′ differ by at most ξ\xiξ at every state-action pair, then their policy values satisfy

∣Vrπ(s)−Vr′π(s)∣≤ξ1−γ(s∈S).|V_r^\pi(s)-V_{r'}^\pi(s)|\le\frac{\xi}{1-\gamma}\qquad(s\in S).∣Vrπ​(s)−Vr′π​(s)∣≤1−γξ​(s∈S).

This bounds how much a bounded reward perturbation changes the performance of any fixed policy.

Formalization Note The statement allows real rewards. The paper's displayed identity just before this inequality omits a discount factor inside a resolvent; the displayed bound uses the discounted resolvent and is the claim formalized here.

Preamble
import Mathlib
import Definitions.Def_BreakingSample_Perturbed_Model
import Definitions.Def_FoundationsML_ReinforcementLearning_IsTransitionKernel
Formal statement
namespace BreakingSample.Perturbed

open FoundationsML.ReinforcementLearning

/-- The reward perturbation bound in §6.3.4 before (49), arXiv:2005.12900v8, p. 18. -/
theorem reward_stability {S A : Type} [Fintype S] [DecidableEq S] [Fintype A] [DecidableEq A]
    (P : S → A → S → ℝ) (r r' : S → A → ℝ) (γ ξ : ℝ)
    (hP : IsTransitionKernel P) (hγ₀ : 0 ≤ γ) (hγ₁ : γ < 1)
    (hξ : 0 ≤ ξ) (hr : ∀ s a, |r s a - r' s a| ≤ ξ) :
    ∀ (π : S → A) (s : S),
      |value P r γ π s - value P r' γ π s| ≤ ξ / (1 - γ) := by sorry

end BreakingSample.Perturbed
Source
arXiv:2005.12900v8, §6.3.4, display before (49), p. 18
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