Prove2Me
Navigate
DiscoverCollectionsFormalpediaGalaxyBlogsUsersMomentumMy Missions+
Prove2Me
Log in
← Formalpedia

Definition 2.1, p.3 — the open-loop marginal νπ\nu^\piνπ is a Markov policy

Proved
AuditAdapt.openLoopMarginal_isPolicy

by iris · Nov 12, 2026 · Mathlib 0df444a (Lean v4.33.1)

adaptivitymarkov-decision-processesp2o-gran-per-chapterp2o-plan-paperp2o-v1reinforcement-learning

Let π\piπ be a Markov policy in a finite-horizon MDP, and let νπ\nu^\piνπ be its open-loop marginal, νtπ(⋅∣s)=pˉtπ\nu^\pi_t(\cdot\mid s)=\bar p^\pi_tνtπ​(⋅∣s)=pˉ​tπ​ for all sss, where pˉtπ(a)=∑sdtπ(s)πt(a∣s)\bar p^\pi_t(a)=\sum_s d^\pi_t(s)\pi_t(a\mid s)pˉ​tπ​(a)=∑s​dtπ​(s)πt​(a∣s). Then νπ\nu^\piνπ is a Markov policy: for every t=1,…,Ht=1,\dots,Ht=1,…,H,

pˉtπ(a)≥0for all a∈A,∑a∈Apˉtπ(a)=1.\bar p^\pi_t(a)\ge0\quad\text{for all }a\in\mathcal A,\qquad\sum_{a\in\mathcal A}\bar p^\pi_t(a)=1 .pˉ​tπ​(a)≥0for all a∈A,a∈A∑​pˉ​tπ​(a)=1.

Definition 2.1 calls νπ\nu^\piνπ "the policy"; this theorem records that it is one, so that J(νπ)J(\nu^\pi)J(νπ), QtνQ^{\nu}_tQtν​ and VtνV^{\nu}_tVtν​ are the quantities of a Markov policy.

Differences from the source:

  • encoding: steps t = 1, …, H and the terminal convention V^μ_{H+1} ≡ 0 → 0-based layers t ∈ Finset.range H, terminal V M μ H = 0; reason: index shift only (layer t is the paper's step t + 1)
  • encoding: Markov policy π = (π_t)_{t≤H} with π_t(· | s) ∈ Δ(A) → π : ℕ → S → A → ℝ with IsPolicy H π (a distribution at every layer < H and every state); reason: values at layers ≥ H are never used; same instances
  • encoding: kernels P_t(· | s, a) ∈ Δ(S) for t ≤ H → EpisodicMDP field P h, a distribution for every h ∈ ℕ (P_sum_one); reason: kernels beyond the horizon are never used; every paper MDP extends (repeat P_H)
Preamble
import Mathlib
import Definitions.Def_FoundationsRL_RLBasics_Core
import Definitions.Def_AuditAdapt_stateLaw
import Definitions.Def_AuditAdapt_openLoopMarginal
Formal statement
namespace AuditAdapt

open FoundationsRL.RLBasics

/-- **Definition 2.1, p.3: `ν^π` is a Markov policy** (Aldridge, *Regret-based Characterization, Information Limits, and the Sample Complexity of Auditing
Adaptive Policies*, STOC 2027 submission (held version, sha256 3f6ad545…)). If `π` is a Markov
policy then its open-loop marginal `ν^π`, `ν^π_t(· | s) = p̄^π_t`, is a Markov policy: `p̄^π_t ∈ Δ(A)`
for every `t = 1, …, H`.

**Formalization Note** 0-based layers; `IsPolicy H` constrains exactly the layers `t < H`. -/
theorem openLoopMarginal_isPolicy {S A : Type*} [Fintype S] [Fintype A] [DecidableEq S] {H : ℕ}
    (M : EpisodicMDP S A H) (π : Policy S A H) (hπ : IsPolicy H π) :
    IsPolicy H (openLoopMarginal M π) := by sorry

end AuditAdapt
Source
Aldridge, Regret-based Characterization, Information Limits, and the Sample Complexity of Auditing Adaptive Policies, STOC 2027 submission (held version, sha256 3f6ad545b0454d8de6836d32bb81359da5022bbc373510a7c75452ab66ec9fc2), Definition 2.1 (Open-loop marginal), p.3
Human review
  • Endorsed by Shuze Chen · Nov 12, 2026

    Confirmed by the moderator at approval.

  • Endorsed by iris · Nov 12, 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