Prove2Me
Navigate
DiscoverCollectionsFormalpediaGalaxyBlogsUsersMomentumMy Missions+
Prove2Me
Log in
← Formalpedia

§5.1, proof of Theorem 5.2, p. 17 — lim sup E^σ_x[C^n/n] ≤ J_σ(x) for γ ≥ 1 (Jensen)

Proved
RiskSensMDP.AverageCost.jensen_step

by mikedeng1 · Oct 8, 2026 · Mathlib 0df444a (Lean v4.33.1)

average-costjensen-inequalityp2o-batch-pfp2ap2o-gran-per-chapterp2o-plan-paperp2o-v1power-utilityrisk-sensitive

Let γ≥1\gamma\ge1γ≥1 and U(y)=yγU(y)=y^\gammaU(y)=yγ. For every policy σ∈Π\sigma\in\Piσ∈Π and every initial state x∈Ex\in Ex∈E, the risk-neutral average cost is at most the risk-sensitive one:

ρσ(x)=lim sup⁡n→∞Exσ[Cnn]≤lim sup⁡n→∞U−1(Exσ[U(Cnn)])=Jσ(x).\rho_\sigma(x)=\limsup_{n\to\infty}\mathbb E^\sigma_x\Big[\frac{C^n}{n}\Big]\le\limsup_{n\to\infty}U^{-1}\Big(\mathbb E^\sigma_x\Big[U\Big(\frac{C^n}{n}\Big)\Big]\Big)=J_\sigma(x).ρσ​(x)=n→∞limsup​Exσ​[nCn​]≤n→∞limsup​U−1(Exσ​[U(nCn​)])=Jσ​(x).

This is the comparison step of the paper's proof of Theorem 5.2. For a convex utility the certainty-equivalent cost is never below the expected cost, for every policy, including history-dependent ones.

Formalization Note Both sides are the limits superior defined in Criterion: ρσ(x)=lim sup⁡1nExσ[Cn]\rho_\sigma(x)=\limsup\frac1n\mathbb E^\sigma_x[C^n]ρσ​(x)=limsupn1​Exσ​[Cn] and Jσ(x)=lim sup⁡1n(Exσ[(Cn)γ])1/γJ_\sigma(x)=\limsup\frac1n(\mathbb E^\sigma_x[(C^n)^\gamma])^{1/\gamma}Jσ​(x)=limsupn1​(Exσ​[(Cn)γ])1/γ. Their equality with the displayed forms is linearity of expectation and the preceding milestone.

Preamble
import Mathlib
import Definitions.Def_RiskSensMDP_AverageCost_Model
import Definitions.Def_RiskSensMDP_AverageCost_HarrisRecurrence
import Definitions.Def_RiskSensMDP_AverageCost_Criterion

open MeasureTheory ProbabilityTheory Filter Finset
Formal statement
namespace RiskSensMDP.AverageCost

/-- §5.1, proof of Theorem 5.2, p. 17: for `γ ≥ 1` (convex `U(y) = y^γ`), Jensen's inequality gives
`limsup_{n → ∞} E^σ_x[C^n/n] ≤ limsup_{n → ∞} U⁻¹(E^σ_x[U(C^n/n)]) = J_σ(x)` for every policy
`σ ∈ Π` and every `x ∈ E`. -/
theorem jensen_step {E A : Type*} [MeasurableSpace E] [StandardBorelSpace E]
    [MeasurableSpace A] [StandardBorelSpace A]
    (M : Model E A) (γ : ℝ) (hγ : 1 ≤ γ) (σ : Policy M) (x : E) :
    riskNeutralAvgCost M σ x ≤ powerAvgCost M γ σ x := by sorry

end RiskSensMDP.AverageCost
Source
Bäuerle & Rieder, More Risk-Sensitive Markov Decision Processes, authors' manuscript (KIT repository 1000039663; published Math. Oper. Res. 39(1):105–120, 2014), p. 17, §5.1, proof of Theorem 5.2, last display
Human review
  • Endorsed by Shuze Chen · Oct 8, 2026

    Confirmed by the moderator at approval.

  • Endorsed by mikedeng1 · Oct 8, 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