Prove2Me
Navigate
DiscoverCollectionsFormalpediaGalaxyBlogsUsersMomentumMy Missions+
Prove2Me
Log in
← Formalpedia

Theorem 4.7.2 — L = X: the limit points of the expected state-action frequencies form the LP polytope

Proved
KallenbergLP.Constrained.limitPoints_eq_polytope

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

dynamic-programminglinear-programmingmarkov-decision-processp2o-batch-pfp2ap2o-gran-per-chapterp2o-plan-bookp2o-v1state-action-frequencies

Let β\betaβ be an initial distribution (βj≥0\beta_j\ge0βj​≥0, ∑jβj=1\sum_j\beta_j=1∑j​βj​=1; zeros allowed) for a finite Markov decision model with stochastic transitions piajp_{iaj}piaj​. Let LLL be the set of all limit points of the expected state-action frequencies

xjaT(R)=1T∑t=1T∑iβi PR(Xt=j, Yt=a∣X1=i)x^T_{ja}(R)=\frac1T\sum_{t=1}^T\sum_i\beta_i\,\mathbb P_R(X_t=j,\ Y_t=a\mid X_1=i)xjaT​(R)=T1​t=1∑T​i∑​βi​PR​(Xt​=j, Yt​=a∣X1​=i)

over all policies RRR (history-dependent and randomized), and let XXX be the set of vectors xxx for which some yyy satisfies

∑i∑a(δij−piaj)xia=0,∑axja+∑i∑a(δij−piaj)yia=βj(j∈E),xia,yia≥0.\sum_i\sum_a(\delta_{ij}-p_{iaj})x_{ia}=0,\qquad\sum_a x_{ja}+\sum_i\sum_a(\delta_{ij}-p_{iaj})y_{ia}=\beta_j\quad(j\in E),\qquad x_{ia},y_{ia}\ge0.i∑​a∑​(δij​−piaj​)xia​=0,a∑​xja​+i∑​a∑​(δij​−piaj​)yia​=βj​(j∈E),xia​,yia​≥0.

Then

L=X.L=X.L=X.

This characterizes the achievable long-run state-action frequencies of a multichain Markov decision problem as a polytope described by finitely many linear constraints, which is what makes constrained average-reward problems solvable by a single linear program.

Formalization Note LLL ranges over all history-dependent randomized policies; restricting to stationary policies would give L(S)L(S)L(S), which differs from XXX in general (Example 4.7.1 of the book).

Preamble
import Mathlib
import Definitions.Def_MarkovDecisionProcesses_AverageReward
import Definitions.Def_KallenbergLP_Constrained_Frequencies
Formal statement
namespace KallenbergLP.Constrained

open MarkovDecisionProcesses

/-- Kallenberg (1983), Theorem 4.7.2, p. 138: `L = X`. The set of all limit points of the expected
state-action frequencies, over all (history-dependent, randomized) policies, equals the polytope
`X` of (4.7.8). -/
theorem limitPoints_eq_polytope {S A : Type*} [Fintype S] [Fintype A] [DecidableEq S]
    [DecidableEq A] (M : StationaryMDP S A) (β : S → ℝ) (hβ0 : ∀ j, 0 ≤ β j)
    (hβ1 : ∑ j, β j = 1) :
    Lset M β (fun _ => True) = polytopeX M β := by sorry

end KallenbergLP.Constrained
Source
Kallenberg, Linear Programming and Finite Markovian Control Problems, Mathematical Centre Tracts 148, Mathematisch Centrum, Amsterdam 1983, p. 138, Theorem 4.7.2
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