Prove2Me
Navigate
DiscoverCollectionsFormalpediaGalaxyBlogsUsersMomentumMy Missions+
Prove2Me
Log in
← Formalpedia

Corollary 1, p. 1131 — value iteration below, U^k-iteration above modified policy iteration: u⁰ₙ ≤ vₙᵏ ≤ uₙᵏ

Proved
ModPolicyIter.Conv.corollary_1

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

markov-decision-processmodified-policy-iterationp2o-batch-pfp2ap2o-gran-per-chapterp2o-plan-paperp2o-v1value-iteration

Throughout, SSS is a set of states with a σ\sigmaσ-algebra; each policy P∈PP\in\mathcal PP∈P is a Markov transition kernel on SSS with a measurable one-period reward cPc_PcP​, sup⁡Psup⁡s∣cP(s)∣≤M\sup_P\sup_s|c_P(s)|\le MsupP​sups​∣cP​(s)∣≤M; 0≤λ<10\le\lambda<10≤λ<1; VVV is the space of bounded measurable functions with ∥v∥=sup⁡s∣v(s)∣\|v\|=\sup_s|v(s)|∥v∥=sups​∣v(s)∣; and the maximum in Bv=max⁡P{cP+(λP−I)v}Bv=\max_P\{c_P+(\lambda P-I)v\}Bv=maxP​{cP​+(λP−I)v} is attained for every v∈Vv\in Vv∈V, a maximizer being written PvP_vPv​.

Let k≥0k\ge 0k≥0 and let {vn}\{v_n\}{vn​} be generated by modified policy iteration of order kkk, recursion (4): vn+1=vn+APnkBvnv_{n+1}=v_n+A^k_{P_n}Bv_nvn+1​=vn​+APn​k​Bvn​ with APk=∑i=0k(λP)iA^k_P=\sum_{i=0}^k(\lambda P)^iAPk​=∑i=0k​(λP)i, where PnP_nPn​ attains the maximum in (1) at vnv_nvn​. Assume v0∈Vv_0\in Vv0​∈V and Bv0≥0Bv_0\ge 0Bv0​≥0. Assume also that UkU^kUk maps VVV into VVV. Then for every n≥0n\ge 0n≥0, pointwise on SSS,

(U0)nv0 ≤ vn ≤ (Uk)nv0.(U^0)^nv_0\ \le\ v_n\ \le\ (U^k)^nv_0 .(U0)nv0​ ≤ vn​ ≤ (Uk)nv0​.

The iterates of value iteration and of UkU^kUk-iteration from the same start bracket those of modified policy iteration of order kkk.

Formalization Note The hypothesis that UkU^kUk maps VVV into VVV is the paper's implicit premise (see Lemma 2); for k=0k=0k=0 it follows from the attainment assumption. The paragraph before the corollary speaks of "Uk+1U^{k+1}Uk+1"; the corollary and its proof use UkU^kUk, which is what is stated.

Preamble
import Mathlib
import Definitions.Def_ModPolicyIter_Conv_Setting

open MeasureTheory ProbabilityTheory
Formal statement
namespace ModPolicyIter.Conv

/-- Corollary 1 (Puterman–Shin 1978, p. 1131): if `Bv₀ ≥ 0` and `u^0_0 = u^k_0 = v_0`, then
`u^0_n ≤ v_n ≤ u^k_n` for every `n`, where `u^j_n = (U^j)^n v_0` and `v_n` is the run (4) of
order `k`. `hUV` (`U^k` maps `V` into `V`) is the paper's implicit premise. -/
theorem corollary_1 {S : Type*} [MeasurableSpace S] {ι : Type*} (m : Model S ι)
    (hmax : MaxAttained m) (k : ℕ) (hUV : ∀ w : S → ℝ, IsBM w → IsBM (U m k w))
    (v : ℕ → S → ℝ) (pol : ℕ → ι)
    (hrun : IsRun m k v pol) (hv0 : IsBM (v 0)) (hB0 : ∀ s, 0 ≤ B m (v 0) s) :
    ∀ n s, (U m 0)^[n] (v 0) s ≤ v n s ∧ v n s ≤ (U m k)^[n] (v 0) s := by sorry

end ModPolicyIter.Conv
Source
Puterman and Shin, Modified policy iteration algorithms for discounted Markov decision problems, Management Science 24 (1978), DOI 10.1287/mnsc.24.11.1127, p. 1131, Corollary 1
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