Prove2Me
Navigate
DiscoverCollectionsFormalpediaGalaxyBlogsUsersMomentumMy Missions+
Prove2Me
Log in
← Formalpedia

Proof of Theorem 9.3 — I0(π,w1)=w1=max⁡(I(σ),I(τ))I_0(\pi, w_1) = w_1 = \max(I(\sigma), I(\tau))I0​(π,w1​)=w1​=max(I(σ),I(τ))

Proved
NegativeDP.Switching.InH_zero

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

dynamic-programmingnegative-dynamic-programmingp2o-batch-pfp2bp2o-gran-per-chapterp2o-plan-paperp2o-v1

Consider a negative dynamic programming problem (non-positive returns, β=1\beta=1β=1) on non-empty Borel state and action spaces. Let σ\sigmaσ and τ\tauτ be policies with continuation returns unu_nun​ and vnv_nvn​, and let wn=max⁡(un,vn)w_n=\max(u_n,v_n)wn​=max(un​,vn​). Then for every policy π\piπ and every initial state sss,

I0(π,w1)(s)=w1(s)=max⁡(I(σ)(s),I(τ)(s)).I_0(\pi,w_1)(s)=w_1(s)=\max\big(I(\sigma)(s),I(\tau)(s)\big).I0​(π,w1​)(s)=w1​(s)=max(I(σ)(s),I(τ)(s)).

Here I0(π,w1)I_0(\pi,w_1)I0​(π,w1​) is the expected return when the process is stopped before the first stage and the terminal reward w1w_1w1​ is received at the initial history (s)(s)(s).

This is the starting point of the induction in the proof of Theorem 9.3: the continuation return of a policy from the empty history is its expected return.

Formalization Note The paper's w1w_1w1​ is wmax P σ τ 0 evaluated at the initial history Hist.start s (Lean's index 000 is the paper's stage 111). The return III is defined through the law of the history from the initial state, the continuation return through the continuation law, so the second equality is a statement about those two constructions.

Preamble
import Mathlib
import Definitions.Def_NegativeDP_Switching_Model
open MeasureTheory ProbabilityTheory
open DiscountedDP.Stationary (Hist Plan MarkovPlan)
Formal statement
namespace NegativeDP.Switching

/-- Proof of Theorem 9.3 (p. 888): `I_0(π, w_1) = w_1 = max(I(σ), I(τ))`, for every plan `π`. -/
theorem InH_zero {S A : Type*} [MeasurableSpace S] [StandardBorelSpace S] [Nonempty S]
    [MeasurableSpace A] [StandardBorelSpace A] [Nonempty A]
    (P : Problem S A) (σ τ π : Plan (S := S) (A := A)) (s : S) :
    InH P π 0 (wmax P σ τ 0) s = wmax P σ τ 0 (Hist.start s) ∧
    wmax P σ τ 0 (Hist.start s) = max (I P σ s) (I P τ s) := by sorry
end NegativeDP.Switching
Source
Strauch, Negative Dynamic Programming, Ann. Math. Statist. 37 (1966), p. 888, proof of Theorem 9.3
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