Prove2Me
Navigate
DiscoverCollectionsFormalpediaGalaxyBlogsUsersMomentumMy Missions+
Prove2Me
Log in
← Formalpedia

BanditAlgorithm.bandit_asymptotically_optimal_ucb_regret_bound

Proved

by Shuze Chen · Jul 19, 2026 · Mathlib 0df444a (Lean v4.33.1)

banditsregretucb

(Asymptotically optimal UCB, finite-time, GOAL) For any 1-subgaussian kkk-armed bandit ν\nuν and any policy π\piπ that is an instance of Algorithm 6 (index μ^i(t−1)+2log⁡f(t)Ti(t−1)\hat\mu_i(t-1) + \sqrt{\frac{2\log f(t)}{T_i(t-1)}}μ^​i​(t−1)+Ti​(t−1)2logf(t)​​ with f(t)=1+tlog⁡2tf(t) = 1 + t\log^2 tf(t)=1+tlog2t), the regret satisfies

Rn≤∑i:Δi>0inf⁡ε∈(0,Δi)Δi(1+5ε2+2(log⁡f(n)+πlog⁡f(n)+1)(Δi−ε)2).R_n \le \sum_{i:\Delta_i>0} \inf_{\varepsilon\in(0,\Delta_i)} \Delta_i\left(1 + \frac{5}{\varepsilon^2} + \frac{2\big(\log f(n) + \sqrt{\pi\log f(n)} + 1\big)}{(\Delta_i-\varepsilon)^2}\right).Rn​≤i:Δi​>0∑​ε∈(0,Δi​)inf​Δi​(1+ε25​+(Δi​−ε)22(logf(n)+πlogf(n)​+1)​).

The per-arm infimum inside the sum is encoded in the equivalent ∀\forall∀-family form: the bound holds at every family ε:Fin k→R\varepsilon : \mathrm{Fin}\ k \to \mathbb{R}ε:Fin k→R with εi∈(0,Δi)\varepsilon_i \in (0, \Delta_i)εi​∈(0,Δi​) for each suboptimal arm iii.

Preamble
import Definitions.Def_banditRegret
import Definitions.Def_asymptoticUcbPolicy
import Mathlib.Analysis.SpecialFunctions.Trigonometric.Basic


open MeasureTheory ProbabilityTheory
Formal statement
theorem BanditAlgorithm.bandit_asymptotically_optimal_ucb_regret_bound {k : ℕ}
    {ν : StochasticBandit k} (hν : IsSubgaussianBandit 1 ν)
    {π : BanditPolicy k} (hπ : IsAsymptoticUCBPolicy π) (n : ℕ)
    (ε : Fin k → ℝ)
    (hε : ∀ i, 0 < banditGap ν i → ε i ∈ Set.Ioo 0 (banditGap ν i)) :
    banditRegret ν π n ≤
      ∑ i ∈ Finset.univ.filter (fun i ↦ 0 < banditGap ν i),
        banditGap ν i *
          (1 + 5 / ε i ^ 2 +
            2 * (Real.log (asymptoticUcbSchedule n) +
                Real.sqrt (Real.pi * Real.log (asymptoticUcbSchedule n)) + 1) /
              (banditGap ν i - ε i) ^ 2) := by
  sorry
Source
L&S Theorem 8.1, Eq. (8.1), p.117

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