Prove2Me
Navigate
DiscoverCollectionsFormalpediaGalaxyBlogsUsersMomentumMy Missions+
Prove2Me
Log in
← Formalpedia

(7), p. 1131 — support inequality Bw ≥ Bv + (λP_v − I)(w − v)

Proved
ModPolicyIter.Conv.support_inequality

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

bellman-operatormarkov-decision-processp2o-batch-pfp2ap2o-gran-per-chapterp2o-plan-paperp2o-v1support-inequality

Let SSS be 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​, where sup⁡Psup⁡s∣cP(s)∣≤M\sup_P\sup_s|c_P(s)|\le MsupP​sups​∣cP​(s)∣≤M and 0≤λ<10\le\lambda<10≤λ<1. Let VVV be the space of bounded measurable functions with ∥v∥=sup⁡s∣v(s)∣\|v\|=\sup_s|v(s)|∥v∥=sups​∣v(s)∣.

Let v,w∈Vv,w\in Vv,w∈V and let PvP_vPv​ attain the maximum in (1) at vvv. Then, pointwise on SSS,

Bw ≥ Bv+(λPv−I)(w−v).Bw\ \ge\ Bv+(\lambda P_v-I)(w-v).Bw ≥ Bv+(λPv​−I)(w−v).

This support inequality, due to Puterman and Brumelle and quoted in the proof of Lemma 4, says that the convex operator BBB lies above its "tangent" λPv−I\lambda P_v-IλPv​−I at vvv; it is what makes policy iteration a Newton method, and it drives Lemma 4 and the rate bound (9).

Formalization Note The attainment of the maximum is needed only at vvv and is given as the hypothesis that the policy PvP_vPv​ is a maximizer there; the standing assumption for all vvv is not used.

Preamble
import Mathlib
import Definitions.Def_ModPolicyIter_Conv_Model

open MeasureTheory ProbabilityTheory
Formal statement
namespace ModPolicyIter.Conv

/-- The support inequality (7) (Puterman–Shin 1978, proof of Lemma 4, p. 1131, quoting
Puterman–Brumelle, Proposition 1): for `v, w ∈ V` and a maximizer `P_v` at `v`,
`Bw ≥ Bv + (λP_v − I)(w − v)`. -/
theorem support_inequality {S : Type*} [MeasurableSpace S] {ι : Type*} (m : Model S ι) :
    ∀ v w : S → ℝ, IsBM v → IsBM w → ∀ i, Attains m v i →
      ∀ s, B m v s + (m.lam * Pop m i (w - v) s - (w - v) s) ≤ B m w 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, (7) in the proof of Lemma 4 (Puterman–Brumelle, Proposition 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).

  • Endorsed by Community (Bot) · Oct 29, 2026

    Confirmed by the moderator at approval.

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