Prove2Me
Navigate
DiscoverCollectionsFormalpediaGalaxyBlogsUsersMomentumMy Missions+
Prove2Me
Log in
← Formalpedia

Conditioning the trajectory law on one action: Eq[F∣Zu=z]=Equ→z[F]\mathbb E_q[F\mid Z_u=z]=\mathbb E_{q^{u\to z}}[F]Eq​[F∣Zu​=z]=Equ→z​[F]

Proved
TPG.integral_cond_Z

by Wenqian Xing · Oct 12, 2026 · Mathlib 0df444a (Lean v4.33.1)

causal-inferencemarkov-chainnonstationaritypolicy-gradienttreatment-effect

Setting. SSS is a finite state space, actions are Zt∈{0,1}Z_t\in\{0,1\}Zt​∈{0,1}, time is t=0,1,…,T−1t=0,1,\dots,T-1t=0,1,…,T−1 (the source's time t+1t+1t+1). The environment has transition matrices PztP_z^tPzt​, initial distribution ρ\rhoρ and reward laws R(⋅∣x,z)R(\cdot\mid x,z)R(⋅∣x,z) on R\mathbb RR. For a sequence q=(qt)t≥0q=(q_t)_{t\ge0}q=(qt​)t≥0​ of treatment probabilities, Pq\mathbb P_qPq​ and Eq\mathbb E_qEq​ denote the law of the trajectory (Xt,Zt,Yt)t<T(X_t,Z_t,Y_t)_{t<T}(Xt​,Zt​,Yt​)t<T​ when X0∼ρX_0\sim\rhoX0​∼ρ, the actions are independent with P(Zt=1)=qt\mathbb P(Z_t=1)=q_tP(Zt​=1)=qt​, Xt+1∼PZtt(Xt,⋅)X_{t+1}\sim P^t_{Z_t}(X_t,\cdot)Xt+1​∼PZt​t​(Xt​,⋅), and the rewards are conditionally independent with Yt∼R(⋅∣Xt,Zt)Y_t\sim R(\cdot\mid X_t,Z_t)Yt​∼R(⋅∣Xt​,Zt​) (Env.trajLaw T q); the Bernoulli policy πθ\pi_\thetaπθ​ is qt≡θq_t\equiv\thetaqt​≡θ.

Lemma. Let 0≤qt≤10\le q_t\le10≤qt​≤1 for all ttt, let u<Tu<Tu<T with 0<qu<10<q_u<10<qu​<1, let z∈{0,1}z\in\{0,1\}z∈{0,1}, and let FFF be a measurable function of the trajectory that is integrable along every state–action path. Then the expectation of FFF under the conditional law given {Zu=z}\{Z_u=z\}{Zu​=z} is the expectation under the law in which the action at time uuu is zzz with probability one:

Eq[F∣Zu=z]=Equ→z[F],\mathbb E_q[F\mid Z_u=z]=\mathbb E_{q^{u\to z}}[F],Eq​[F∣Zu​=z]=Equ→z​[F],

where qu→zq^{u\to z}qu→z is qqq with quq_uqu​ replaced by z∈{0,1}z\in\{0,1\}z∈{0,1}.

With F=YtF=Y_tF=Yt​ this turns the QQQ-values of the source into expected rewards under modified randomization sequences.

Preamble
import Mathlib
import Definitions.Def_TPG_Model
import Definitions.Def_TPG_Estimators
import Definitions.Def_TPG_Markov
import Definitions.Def_TPG_Bridge

open MeasureTheory ProbabilityTheory
open scoped BigOperators ENNReal
Formal statement
namespace TPG
theorem integral_cond_Z {S : Type} [Fintype S] [MeasurableSpace S] [MeasurableSingletonClass S]
    (E : Env S) (T : ℕ) (q : ℕ → ℝ) (hq : ∀ t : ℕ, 0 ≤ q t ∧ q t ≤ 1)
    (u : Fin T) (z : Bool) (hu : 0 < q (u : ℕ) ∧ q (u : ℕ) < 1)
    (F : Traj S T → ℝ) (hF : Measurable F)
    (hint : ∀ p : (Fin T → S) × (Fin T → Bool),
      Integrable (fun y : Fin T → ℝ => F (embedPath p.1 p.2 y)) (E.rewardLaw p.1 p.2)) :
    ∫ ω, F ω ∂(ProbabilityTheory.cond (E.trajLaw T q) {ω | Z u ω = z})
      = ∫ ω, F ω ∂(E.trajLaw T (Function.update q (u : ℕ) (if z then 1 else 0))) := by sorry
end TPG
Source
Johari, Peng, Xing, Estimation of Treatment Effects Under Nonstationarity via the Truncated Policy Gradient Estimator, revised manuscript of October 2026 (revision of arXiv:2506.05308v3, https://arxiv.org/abs/2506.05308); numbering follows the revised manuscript. Auxiliary statement, not a numbered result of the paper: it identifies the conditional expectations E_θ[Y_t | Z_u = z] of eqs. (7) and (10), pp. 13 and 15.

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