Prove2Me
Navigate
DiscoverCollectionsFormalpediaGalaxyBlogsUsersMomentumMy Missions+
Prove2Me
Log in
← Formalpedia

Lemma 1.2, part 3 — sufficient conditions for T(π, a, k) to be MLR-nondecreasing in the action

Proved
LovejoyPOMDP.Monotone.lemma_1_2_3

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

bayesian-updatelikelihood-ratio-orderp2o-batch-pfp2ap2o-gran-per-chapterp2o-plan-paperp2o-v1pomdp

Consider a finite POMDP as in §2 of the paper, with a completely ordered action set AAA. Fix a belief π∈Π(S)\pi\in\Pi(S)π∈Π(S) and an observation k∈Ok\in Ok∈O. Suppose that for all a≥a′a\ge a'a≥a′ in AAA:

  1. πPa≥rπPa′\pi P^a\ge_r\pi P^{a'}πPa≥r​πPa′, and
  2. rjka rj′ka′ ≥ rjka′ rj′kar^a_{jk}\,r^{a'}_{j'k}\ \ge\ r^{a'}_{jk}\,r^a_{j'k}rjka​rj′ka′​ ≥ rjka′​rj′ka​ for all j≥j′j\ge j'j≥j′ in SSS.

Then

T(π,a,k) ≥r T(π,a′,k)for all a≥a′ in A.T(\pi,a,k)\ \ge_r\ T(\pi,a',k)\qquad\text{for all } a\ge a' \text{ in } A.T(π,a,k) ≥r​ T(π,a′,k)for all a≥a′ in A.

After observing kkk, the posterior obtained under a larger action is larger in the likelihood ratio order. This is the step of Proposition 2's proof that compares continuation values across actions.

Preamble
import Mathlib
import Definitions.Def_LovejoyPOMDP_Monotone_Model
Formal statement
namespace LovejoyPOMDP.Monotone

/-- Lovejoy, *Some Monotonicity Results for Partially Observed Markov Decision Processes*, Oper. Res. 35(5):736–743 (1987), DOI 10.1287/opre.35.5.736, p. 739, Lemma 1.2, part 3.

For any `π ∈ Π(S)` and `k ∈ O`: `T(π, a, k) ≥r T(π, a', k)` for all `a ≥ a'` in `A` if for all such
`a` and `a'`: (a) `πP^a ≥r πP^{a'}`; (b) `r^a_{jk} r^{a'}_{j'k} ≥ r^{a'}_{jk} r^a_{j'k}` for all
`j ≥ j'` in `S`. -/
theorem lemma_1_2_3 {S O A : Type*} [Fintype S] [Fintype O] [Fintype A]
    [LinearOrder S] [LinearOrder O] [LinearOrder A] [Nonempty S] [Nonempty O] [Nonempty A]
    (M : POMDP S O A)
    {π : S → ℝ} (hπ : π ∈ stdSimplex ℝ S) (k : O)
    (ha : ∀ a a' : A, a' ≤ a → MLRGE (M.predict π a) (M.predict π a'))
    (hb : ∀ a a' : A, a' ≤ a → ∀ j j' : S, j' ≤ j →
      M.R a' j k * M.R a j' k ≤ M.R a j k * M.R a' j' k) :
    ∀ a a' : A, a' ≤ a → MLRGE (M.bayes π a k) (M.bayes π a' k) := by sorry

end LovejoyPOMDP.Monotone
Source
Lovejoy, Some Monotonicity Results for Partially Observed Markov Decision Processes, Oper. Res. 35(5):736–743 (1987), DOI 10.1287/opre.35.5.736, p. 739, Lemma 1.2, part 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