Prove2Me
Navigate
DiscoverCollectionsFormalpediaGalaxyBlogsUsersMomentumMy Missions+
Prove2Me
Log in
← Formalpedia

Example 7.5: the Bernoulli target process with a beta prior has index ν(α, β) = r(α, β) = α/(α + β)

Proved
AllocationIndices.bernoulli_target_index

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

bernoulli-banditsgittins-indextarget-processes

Example 7.5. Bernoulli target process, T=1T = 1T=1, beta prior with parameters α,β>0\alpha, \beta > 0α,β>0: r(α,β)=α/(α+β)r(\alpha, \beta) = \alpha/(\alpha + \beta)r(α,β)=α/(α+β), the sequence of states starting from (α,β)(\alpha, \beta)(α,β) is (α,β),(α,β+1),…,C(\alpha, \beta), (\alpha, \beta + 1), \dots, C(α,β),(α,β+1),…,C, every state is favourable since α/(α+β)≥α/(α+β+n)\alpha/(\alpha+\beta) \ge \alpha/(\alpha+\beta+n)α/(α+β)≥α/(α+β+n), and hence ν(α,β)=r(α,β)=α/(α+β)\nu(\alpha, \beta) = r(\alpha, \beta) = \alpha/(\alpha + \beta)ν(α,β)=r(α,β)=α/(α+β).

Formally: for α,β>0\alpha, \beta > 0α,β>0 and a∈(0,1)a \in (0, 1)a∈(0,1), the Gittins index of the Bernoulli target process (from (α,β)(\alpha, \beta)(α,β) the target is reached with probability α/(α+β)\alpha/(\alpha+\beta)α/(α+β), otherwise the state becomes (α,β+1)(\alpha, \beta+1)(α,β+1); reward α/(α+β)\alpha/(\alpha+\beta)α/(α+β) in (α,β)(\alpha, \beta)(α,β) and 000 in CCC) in the state (α,β)(\alpha, \beta)(α,β) equals α/(α+β)\alpha/(\alpha + \beta)α/(α+β).

Preamble
import Definitions.Def_AllocationIndices_Sampling

open MeasureTheory ProbabilityTheory BanditAlgorithm
Formal statement
namespace AllocationIndices

/-- **Example 7.5** (p. 182), the Bernoulli target process with `T = 1` and a beta prior with
parameters `α, β > 0`: every state `(α, β)` is favourable, since `α/(α + β) ≥ α/(α + β + n)`,
and hence `ν(α, β) = r(α, β) = α/(α + β)`. -/
theorem bernoulli_target_index {α β : ℝ} (hα : 0 < α) (hβ : 0 < β) {a : ℝ} (ha0 : 0 < a)
    (ha1 : a < 1) :
    gittinsIndex bernoulliTargetChain bernoulliTargetReward a (Sum.inl (α, β)) =
      α / (α + β) := by sorry

end AllocationIndices
Source
Gittins, Glazebrook and Weber, Multi-armed Bandit Allocation Indices, 2nd ed., Wiley 2011, doi:10.1002/9780470980033, §7.3 p. 182, Example 7.5
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