Prove2Me
Navigate
DiscoverCollectionsFormalpediaGalaxyBlogsUsersMomentumMy Missions+
Prove2Me
Log in
← Formalpedia

Theorem 1, first display, p.9 — PAπ=∑jxjPA(j)P^\pi_A=\sum_jx_jP^{(j)}_APAπ​=∑j​xj​PA(j)​ and PBπ=∑jxjPB(j)P^\pi_B=\sum_jx_jP^{(j)}_BPBπ​=∑j​xj​PB(j)​

Proved
MarkovEntanglementExact.local_transition_eq_sum

by iris · Oct 30, 2026 · Mathlib 0df444a (Lean v4.33.1)

markov-chainp2o-gran-per-chapterp2o-plan-paperp2o-strengthenedp2o-v1reinforcement-learningvalue-decomposition

Let P=∑j=1KxjPA(j)⊗PB(j)P=\sum_{j=1}^Kx_jP^{(j)}_A\otimes P^{(j)}_BP=∑j=1K​xj​PA(j)​⊗PB(j)​ be as in Definition 1, μ\muμ a distribution with positive agent marginals, and PA,PBP_A,P_BPA​,PB​ the local transition matrices of Eq. (2). Then

PA=∑j=1KxjPA(j),PB=∑j=1KxjPB(j).P_A=\sum_{j=1}^Kx_jP^{(j)}_A,\qquad P_B=\sum_{j=1}^Kx_jP^{(j)}_B.PA​=j=1∑K​xj​PA(j)​,PB​=j=1∑K​xj​PB(j)​.

Thus for a separable system the local chain does not depend on the occupancy measure, and it is the chain that local TD learning sees.

Differences from the source:

  • generalization: P^π_AB of a two-agent MDP and policy → an arbitrary transition matrix P on a product of two finite sets; reason: the argument uses only the stochasticity of P; P^π_AB is an instance by M12
  • generalization: μ is the stationary occupancy measure of a unichain, unique and strictly positive on states → μ is any distribution on joint pairs with μ ≥ 0, Σμ = 1 and positive agent marginals; reason: the derivation uses only the positivity of the conditioning marginals (footnote 1); the paper's occupancy measure is an instance, proved in the verification file OccupancyInstance
  • encoding: Eq. (2) with the conditional μ(s_B, a_B | s_A, a_A) → IsLocalTransitionA/B, Eq. (2) multiplied through by the marginal; reason: equivalent under positive marginals; the quotient form is proved in M2
  • reading: first sum printed Σ_{i=1}^K x_j P^(j)_A → the sum over j of x_j P^(j)_A; reason: the index i is a typo for j, as Definition 1 and the second sum show
Preamble
import Mathlib
import Definitions.Def_markov_entanglement
import Definitions.Def_MarkovEntanglementExact_IsSeparableWitness
import Definitions.Def_MarkovEntanglementExact_IsOccupancy

open scoped BigOperators
open MarkovEntanglement
Formal statement
namespace MarkovEntanglementExact

/-- Theorem 1, first display: if `P = Σ_j x_j P^(j)_A ⊗ P^(j)_B`, then the marginalized local
transition matrices of Eq. (2) are `P_A = Σ_j x_j P^(j)_A` and `P_B = Σ_j x_j P^(j)_B`.

Source: Chen & Peng, Multi-agent Markov Entanglement, arXiv:2506.02385v3, Theorem 1, p.9 (the
printed index `i` of the first sum is a typo for `j`). -/
theorem local_transition_eq_sum
    {SA SB : Type*} [Fintype SA] [Fintype SB] [DecidableEq SA] [DecidableEq SB]
    (P : Matrix (SA × SB) (SA × SB) ℝ)
    {K : ℕ} {x : Fin K → ℝ} {PAj : Fin K → Matrix SA SA ℝ} {PBj : Fin K → Matrix SB SB ℝ}
    (hw : IsSeparableWitness P K x PAj PBj)
    (μ : SA × SB → ℝ) (hμ : IsOccupancy μ)
    (PA : Matrix SA SA ℝ) (PB : Matrix SB SB ℝ)
    (hA : IsLocalTransitionA P μ PA) (hB : IsLocalTransitionB P μ PB) :
    PA = ∑ k, x k • PAj k ∧ PB = ∑ k, x k • PBj k := by sorry

end MarkovEntanglementExact
Source
Chen & Peng, Multi-agent Markov Entanglement, arXiv:2506.02385v3, Theorem 1, p.9
Human review
  • Endorsed by Shuze Chen · Oct 31, 2026

    Confirmed by the moderator at approval.

  • Endorsed by iris · Oct 31, 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