Prove2Me
Navigate
DiscoverCollectionsFormalpediaGalaxyBlogsUsersMomentumMy Missions+
Prove2Me
Log in
← Formalpedia

Display (40), p. 21 — the gradient estimator is bounded: ‖h(θ; τ) − h(θ; τ′)‖ ≤ 2L_r/(1−γ) = 2L_q

Proved
StructEstMDP.FiniteTime.display_40

by mikedeng1 · Oct 14, 2026 · Mathlib 0df444a (Lean v4.33.1)

p2o-batch-pfp2ap2o-gran-per-chapterp2o-plan-paperp2o-v1reinforcement-learning

Let γ∈[0,1)\gamma\in[0,1)γ∈[0,1) and let the reward satisfy Assumption 3 with constant LrL_rLr​. For a trajectory τ={(st,at)}t≥0\tau=\{(s_t,a_t)\}_{t\ge0}τ={(st​,at​)}t≥0​ let h(θ;τ)=∑t=0∞γt∇θr(st,at;θ)h(\theta;\tau)=\sum_{t=0}^\infty\gamma^t\nabla_\theta r(s_t,a_t;\theta)h(θ;τ)=∑t=0∞​γt∇θ​r(st​,at​;θ). Then for every θ\thetaθ and all trajectories τ,τ′\tau,\tau'τ,τ′,

∥h(θ;τ)−h(θ;τ′)∥≤2Lr∑t=0∞γt=2Lr1−γ=2Lq.\|h(\theta;\tau)-h(\theta;\tau')\|\le2L_r\sum_{t=0}^\infty\gamma^t=\frac{2L_r}{1-\gamma}=2L_q.∥h(θ;τ)−h(θ;τ′)∥≤2Lr​t=0∑∞​γt=1−γ2Lr​​=2Lq​.

Applied to τ=τk−1E\tau=\tau^E_{k-1}τ=τk−1E​ and τ′=τk−1A\tau'=\tau^A_{k-1}τ′=τk−1A​ this is the bound ∥gk−1∥≤2Lq\|g_{k-1}\|\le2L_q∥gk−1​∥≤2Lq​ on the stochastic gradient, which controls the drift ∥θk−θk−1∥≤2αLq\|\theta_k-\theta_{k-1}\|\le2\alpha L_q∥θk​−θk−1​∥≤2αLq​ of the reward parameter.

Preamble
import Mathlib
import Definitions.Def_FoundationsML_ReinforcementLearning_IsTransitionKernel
import Definitions.Def_FoundationsML_ReinforcementLearning_IsPolicy
import Definitions.Def_StructEstMDP_FiniteTime_Setting

open FoundationsML.ReinforcementLearning MeasureTheory
Formal statement
namespace StructEstMDP.FiniteTime

/-- Display (40), p. 21: under Assumption 3 the gradient estimator is bounded,
`‖h(θ; τ) − h(θ; τ')‖ ≤ 2L_r ∑_{t≥0} γᵗ = 2L_r/(1−γ) = 2L_q`, for every `θ` and all
trajectories `τ, τ'`. -/
theorem display_40 {S A : Type*} (γ : ℝ) (hγ0 : 0 ≤ γ) (hγ1 : γ < 1)
    {p : ℕ} (r : S → A → EuclideanSpace ℝ (Fin p) → ℝ) (Lr Lg : ℝ)
    (h3 : Assumption3 r Lr Lg)
    (θ : EuclideanSpace ℝ (Fin p)) (τ τ' : Traj S A) :
    ‖hGrad γ r θ τ - hGrad γ r θ τ'‖ ≤ 2 * (Lr / (1 - γ)) := by sorry

end StructEstMDP.FiniteTime
Source
Zeng, Hong and Garcia, Structural Estimation of Markov Decision Processes in High-Dimensional State Space with Finite-Time Guarantees, arXiv:2210.01282v3, p. 21, display (40), proof of Theorem 1
Human review
  • Endorsed by Shuze Chen · Oct 14, 2026

    Confirmed by the moderator at approval.

  • Endorsed by mikedeng1 · Oct 14, 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