Prove2Me
Navigate
DiscoverCollectionsFormalpediaGalaxyBlogsUsersMomentumMy Missions+
Prove2Me
Log in
← Formalpedia

§4, p. 10 — if A is self-weighted for M and all policies of M are proper, M′ has only proper policies

Proved
StableFA.DerivedMDP.derived_all_proper

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

derived-mdpp2o-batch-pfp2ap2o-gran-per-chapterp2o-plan-paperp2o-v1proper-policyself-weightedstochastic-shortest-path

Let MMM be a finite nondiscounted Markov decision process in which every policy is proper, let AAA be an averager that is self-weighted for MMM, and let M′M'M′ be the derived MDP of Theorem 4.1 with γ=1\gamma=1γ=1. Then:

  1. there is an integer m>0m>0m>0 such that, for every admissible (possibly nonstationary) policy π\piπ of M′M'M′ and every starting state iii,
P{xm≠1∣x0=i,π}<1in M′;P\{x_m\ne 1\mid x_0=i,\pi\}<1\quad\text{in } M' ;P{xm​=1∣x0​=i,π}<1in M′;
  1. every stationary policy of M′M'M′ is proper.

The report proves this in the paragraph after the definition of self-weighted averagers. Part 1 is exactly the hypothesis of the stochastic shortest path theorem applied to M′M'M′, which is how the convergence of approximate value iteration follows.

Formalization Note M′M'M′ is derivedModel M A 1. The page states the claim as "M′M'M′ will have only proper policies"; part 2 is that wording, and part 1 is the uniform bound the page's argument establishes ("no matter what state we start from, we have a positive probability of reaching state 1 in m−1m-1m−1 steps"), written as Bertsekas' Assumption 7.2.1, the hypothesis of BertsekasDP.ssp_main_theorem. The hypotheses concern MMM and AAA only.

Preamble
import Mathlib
import Definitions.Def_BertsekasSSPModel
import Definitions.Def_StableFA_DerivedMDP_Setting
Formal statement
namespace StableFA.DerivedMDP

theorem derived_all_proper {n : ℕ} {C : Type} [Fintype C]
    (M : BertsekasSSPModel n C) (A : Averager n)
    (hproper : ∀ μ : Fin n → C, (∀ i, μ i ∈ M.U i) → IsProper M μ)
    (hself : SelfWeighted M A) :
    (∃ m : ℕ, 0 < m ∧ ∀ π : ℕ → Fin n → C, BertsekasSSPAdmissible (derivedModel M A 1) π →
        ∀ i, BertsekasSSPSurvival (derivedModel M A 1) π m i < 1) ∧
      ∀ μ : Fin n → C, (∀ i, μ i ∈ M.U i) → IsProper (derivedModel M A 1) μ := by sorry

end StableFA.DerivedMDP
Source
Gordon, Stable Function Approximation in Dynamic Programming, Tech. Rep. CMU-CS-95-103, Carnegie Mellon University (1995), p. 10, §4, paragraph after the definition of self-weighted
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