Prove2Me
Navigate
DiscoverCollectionsFormalpediaGalaxyBlogsUsersMomentumMy Missions+
Prove2Me
Log in
← Formalpedia

Proof of Lemma 5.6, p. 13 — first-step analysis: E = 1 + P†_π E for expected travel times

Proved
OptimisticPSRL.Diameter.first_step_travelTime

by mikedeng1 · Oct 15, 2026 · Mathlib 0df444a (Lean v4.33.1)

first-step-analysishitting-timemarkov-chainmdpp2o-batch-pfp2ap2o-gran-per-chapterp2o-plan-paperp2o-v1

Let M\mathcal MM be a finite MDP with transition probability vectors Ps,aP_{s,a}Ps,a​, let π:S→A\pi:\mathcal S\to\mathcal Aπ:S→A be a deterministic stationary policy, and let Ts→s2πT^{\pi}_{s\to s_2}Ts→s2​π​ denote the expected number of steps to reach the target s2s_2s2​ from sss under π\piπ. For every state s≠s2s\neq s_2s=s2​,

Ts→s2π  =  1+∑s′≠s2Ps,π(s)(s′) Ts′→s2π.T^{\pi}_{s\to s_2} \;=\; 1+\sum_{s'\neq s_2} P_{s,\pi(s)}(s')\,T^{\pi}_{s'\to s_2}.Ts→s2​π​=1+s′=s2​∑​Ps,π(s)​(s′)Ts′→s2​π​.

In matrix form, the vector E=(Ts→s2π)s≠s2E=(T^{\pi}_{s\to s_2})_{s\neq s_2}E=(Ts→s2​π​)s=s2​​ solves E=1+Pπ†EE=\mathbf 1+P^{\dagger}_{\pi}EE=1+Pπ†​E, where Pπ†P^{\dagger}_{\pi}Pπ†​ is the (S−1)×(S−1)(S-1)\times(S-1)(S−1)×(S−1) matrix with entries Ps,π(s)(s′)P_{s,\pi(s)}(s')Ps,π(s)​(s′), s,s′≠s2s,s'\neq s_2s,s′=s2​. This is the first-step equation the proof of Lemma 5.6 starts from.

Formalization Note. States and actions are 0-based (Fin S, Fin A); Ts→s2πT^{\pi}_{s\to s_2}Ts→s2​π​ is the platform's mdpTravelTime M f s s₂ in [0,∞][0,\infty][0,∞]. The identity is stated for every deterministic stationary policy (the proof uses it for one) and with no finiteness assumption: both sides may equal ∞\infty∞. Products and sums are taken in [0,∞][0,\infty][0,∞], where 0⋅∞=00\cdot\infty=00⋅∞=0.

Preamble
import Mathlib
import Definitions.Def_FiniteMDPLearning
open BanditAlgorithm NNReal ENNReal
Formal statement
namespace OptimisticPSRL.Diameter
theorem first_step_travelTime {S A : ℕ} (M : FiniteMDP S A) (f : Fin S → Fin A)
    (src tgt : Fin S) (hne : src ≠ tgt) :
    mdpTravelTime M f src tgt =
      1 + ∑ s' ∈ Finset.univ.erase tgt, (M.P src (f src) s' : ℝ≥0∞) * mdpTravelTime M f s' tgt := by sorry
end OptimisticPSRL.Diameter
Source
Agrawal & Jia, Posterior sampling for reinforcement learning: worst-case regret bounds, arXiv:1705.07041v3, p. 13, proof of Lemma 5.6, first display (E = 1 + P†_π E)
Human review
  • Endorsed by Shuze Chen · Oct 15, 2026

    Confirmed by the moderator at approval.

  • Endorsed by mikedeng1 · Oct 15, 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