Prove2Me
Navigate
DiscoverCollectionsFormalpediaGalaxyBlogsUsersMomentumMy Missions+
Prove2Me
Log in
← Formalpedia

Eqs. (6.9)-(6.10): the monotone policy (y) earns Wϕ(y) + R(y) from every state and g(W) is the maximum of these over the thresholds

Proved
AllocationIndices.spinning_plates_optimal_avg

by naimengye · Sep 24, 2026 · Mathlib 0df444a (Lean v4.33.1)

average-rewardmonotone-policiesrestless-bandits

Eqs. (6.9)–(6.10) (p. 157). As a consequence of the fact that there always exists a member of A\mathcal{A}A which achieves g(W)g(W)g(W), g(W)=max⁡1≤x≤k+1[Wϕ(x)+R(x)]g(W) = \max_{1 \le x \le k+1} [W\phi(x) + R(x)]g(W)=max1≤x≤k+1​[Wϕ(x)+R(x)], where R(x)=r(x)ϕ(x)+r(x−1)[1−ϕ(x)]R(x) = r(x)\phi(x) + r(x-1)[1 - \phi(x)]R(x)=r(x)ϕ(x)+r(x−1)[1−ϕ(x)] is the return rate generated by the asset under monotone policy (x)(x)(x).

Formally: for the spinning plates asset on k≥1k \ge 1k≥1 states with rates in [0,1][0, 1][0,1], λ(k)=μ(1)=0\lambda(k) = \mu(1) = 0λ(k)=μ(1)=0, λ(x)>0\lambda(x) > 0λ(x)>0 below the top state and μ(x)>0\mu(x) > 0μ(x)>0 above the bottom state, and every subsidy WWW: every monotone policy (y)(y)(y), 0≤y≤k0 \le y \le k0≤y≤k, has average reward Wϕ(y)+R(y)W\phi(y) + R(y)Wϕ(y)+R(y) from every initial state, and the optimal average reward g(W)g(W)g(W) over deterministic stationary Markov policies and initial states equals max⁡0≤y≤k[Wϕ(y)+R(y)]\max_{0 \le y \le k}[W\phi(y) + R(y)]max0≤y≤k​[Wϕ(y)+R(y)].

Preamble
import Definitions.Def_AllocationIndices_Restless

open MeasureTheory ProbabilityTheory BanditAlgorithm Finset
Formal statement
namespace AllocationIndices

/-- **Eqs. (6.9)–(6.10)** (p. 157). In the spinning plates model with positive interior rates
(`λ(x) > 0` below the top state, `μ(x) > 0` above the bottom state) and `λ(k) = μ(1) = 0`, the
monotone policy `(y)` earns the average reward `Wϕ(y) + R(y)` from every initial state, and the
optimal average reward under passive subsidy `W` is
`g(W) = max_{1 ≤ y ≤ k+1} [Wϕ(y) + R(y)]` (thresholds `0, …, k` here), because there is always a
monotone policy achieving `g(W)`. -/
theorem spinning_plates_optimal_avg {k : ℕ} (hk : 0 < k) (lam mu r : Fin k → ℝ)
    (hlam : ∀ x, lam x ∈ Set.Icc (0 : ℝ) 1) (hmu : ∀ x, mu x ∈ Set.Icc (0 : ℝ) 1)
    (hlam_top : ∀ x : Fin k, x.val + 1 = k → lam x = 0)
    (hmu_bot : ∀ x : Fin k, x.val = 0 → mu x = 0)
    (hlam_pos : ∀ x : Fin k, x.val + 1 < k → 0 < lam x)
    (hmu_pos : ∀ x : Fin k, 0 < x.val → 0 < mu x) (W : ℝ) :
    (∀ y ≤ k, ∀ x, avgReward (spinningPlates lam mu r hlam hmu) W (plateThreshold y) x =
        W * plateShare lam mu y + plateReturn lam mu r y) ∧
    optimalAvg (spinningPlates lam mu r hlam hmu) W = plateEnvelope lam mu r W := by sorry

end AllocationIndices
Source
Gittins, Glazebrook and Weber, Multi-armed Bandit Allocation Indices, 2nd ed., Wiley 2011, doi:10.1002/9780470980033, §6.5 pp. 156-157, the reduction to the monotone class A and Eqs. (6.9)-(6.10)
Human review
  • Endorsed by Shuze Chen · Sep 25, 2026

    Confirmed by the moderator at approval.

  • Endorsed by naimengye · Sep 25, 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