Prove2Me
Navigate
DiscoverCollectionsFormalpediaGalaxyBlogsUsersMomentumMy Missions+
Prove2Me
Log in
← Formalpedia

Theorems 1 and 2 — exact value decomposition for every reward holds iff the agents are separable, with the marginalized local Q-values as the decomposition

Proved
MarkovEntanglementExact.exact_value_decomposition_iff_separable

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

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

Consider a two-agent MDP with finite state sets SA,SBS_A,S_BSA​,SB​, feasible action sets, transition kernel PPP and policy π\piπ, and let PABπP^\pi_{AB}PABπ​ be the induced transition matrix on joint state-action pairs. Let 0≤γ<10\le\gamma<10≤γ<1. Then:

  1. (Theorem 1) if the two agents are separable, the exact value decomposition holds: there are maps Q^A,Q^B\hat Q_A,\hat Q_BQ^​A​,Q^​B​, each reading only its own agent's reward, with
QABπ=Q^A(rA)⊗e+e⊗Q^B(rB)for all rA,rB;Q^\pi_{AB}=\hat Q_A(r_A)\otimes e+e\otimes\hat Q_B(r_B)\quad\text{for all } r_A,r_B;QABπ​=Q^​A​(rA​)⊗e+e⊗Q^​B​(rB​)for all rA​,rB​;
  1. (Theorem 2) if γ>0\gamma>0γ>0 and such maps exist, the two agents are separable;
  2. for every distribution μ\muμ on joint pairs with positive agent marginals, as in footnote 1, and the local transition matrices PAπ,PBπP^\pi_A,P^\pi_BPAπ​,PBπ​ of Eq. (2):
    • PAπP^\pi_APAπ​ and PBπP^\pi_BPBπ​ are transition matrices;
    • (Theorem 1) for every decomposition PABπ=∑j=1KxjPA(j)⊗PB(j)P^\pi_{AB}=\sum_{j=1}^Kx_jP^{(j)}_A\otimes P^{(j)}_BPABπ​=∑j=1K​xj​PA(j)​⊗PB(j)​ as in Definition 1,
PAπ=∑j=1KxjPA(j),PBπ=∑j=1KxjPB(j);P^\pi_A=\sum_{j=1}^Kx_jP^{(j)}_A,\qquad P^\pi_B=\sum_{j=1}^Kx_jP^{(j)}_B;PAπ​=j=1∑K​xj​PA(j)​,PBπ​=j=1∑K​xj​PB(j)​;
  • (Theorem 1) if the two agents are separable, then for all rA,rBr_A,r_BrA​,rB​,
QABπ=QAπ⊗e+e⊗QBπ,QAπ=(I−γPAπ)−1rA,QBπ=(I−γPBπ)−1rB;Q^\pi_{AB}=Q^\pi_A\otimes e+e\otimes Q^\pi_B,\qquad Q^\pi_A=(I-\gamma P^\pi_A)^{-1}r_A,\quad Q^\pi_B=(I-\gamma P^\pi_B)^{-1}r_B;QABπ​=QAπ​⊗e+e⊗QBπ​,QAπ​=(I−γPAπ​)−1rA​,QBπ​=(I−γPBπ​)−1rB​;
  • (Theorem 2) if γ>0\gamma>0γ>0 and that identity holds for all rA,rBr_A,r_BrA​,rB​, the two agents are separable.

So for γ>0\gamma>0γ>0, separability, the exact decomposition by reward-local maps, and the decomposition by the marginalized local Q-values are equivalent. This is the headline of the paper: "Markov entanglement serves as a sufficient and necessary condition for the exact value decomposition."

Formalization Note The coefficients xjx_jxj​ are signed. The Q-values are the solutions of the Bellman equation, and the local transitions the solutions of Eq. (2): both exist and are unique, by the milestones, so the universal quantifiers are neither vacuous nor free. γ=0\gamma=0γ=0 is allowed in the clauses of Theorem 1, and the clauses of Theorem 2 carry γ>0\gamma>0γ>0 themselves.

Differences from the source:

  • generalization: one action set per agent, and |S_A| = |S_B|, |A_A| = |A_B| "for simplicity" → feasible action sets AA s, AB s and unrelated finite state types; reason: footnote 1 restricts the action sets; the constant action set of equal size is the special case AA := fun _ => A
  • 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
  • encoding: Q-values as the printed expectation, and Q^π_A = (I − γP^π_A)⁻¹ r_A → Q-values as the solutions of IsBellmanQ; reason: M1 proves the solution exists, is unique, and equals the series and the inverse formula
  • 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
  • reading: "Q_i : r_i → R^{|S||A|}" with Q^π_AB = Q_A(r_A) ⊗ e + e ⊗ Q_B(r_B) for any pair of rewards, and the V-value wording of §1.1 → ∃ maps QA, QB, then ∀ rA rB, for Q-values; reason: §2, p.7 fixes the Q statement; the maps read only their own reward, and Appendix E shows the other quantifier order fails
  • reading: "sufficient and necessary", with Theorem 1 at γ ∈ [0, 1) and Theorem 2 at γ > 0 → a conjunction in which only the necessity clauses assume 0 < γ; reason: §4, p.12 names γ = 0 as a trivial counterexample to necessity only
  • encoding: bounded local rewards |r_i| ≤ r^i_max → all rewards rA, rB on the finite pair types; reason: every function on a finite type is bounded
  • generalization: Theorem 1 states its conclusion for the local values of the marginalized chains under μ → clause 1 additionally gives reward-local maps for every separable P, with no occupancy measure (the μ form is kept in clause 3); reason: the maps are the Bellman solutions of the transition matrices Σ_j x_j P^(j)_A and Σ_j x_j P^(j)_B (M3), and this is the hypothesis form of Theorem 2 that the equivalence joins to
Preamble
import Mathlib
import Definitions.Def_markov_entanglement
import Definitions.Def_MarkovEntanglementExact_IsFeasibleKernel
import Definitions.Def_MarkovEntanglementExact_IsFeasiblePolicy
import Definitions.Def_MarkovEntanglementExact_inducedMatrix
import Definitions.Def_MarkovEntanglementExact_IsSeparableWitness
import Definitions.Def_MarkovEntanglementExact_HasExactValueDecomposition
import Definitions.Def_MarkovEntanglementExact_LocalValuesDecompose
import Definitions.Def_MarkovEntanglementExact_IsOccupancy

open scoped BigOperators
open MarkovEntanglement
Formal statement
namespace MarkovEntanglementExact

/-- **Exact value decomposition holds for every reward if and only if the agents are separable,
with the marginalized local Q-values as the decomposition** (Theorems 1 and 2 combined).

Let `P = P^π_AB` be the transition matrix of a two-agent MDP with feasible action sets under a
policy `π`, and `0 ≤ γ < 1`. Then:

1. if the agents are separable, the exact decomposition holds with maps reading only their own
   agent's reward (Theorem 1);
2. if `γ > 0` and that decomposition holds, the agents are separable (Theorem 2);
3. for every occupancy `μ` of footnote 1, and the local transition matrices `P_A`, `P_B` of
   Eq. (2): they are transition matrices; for every decomposition
   `P = Σ_j x_j P^(j)_A ⊗ P^(j)_B` they equal `Σ_j x_j P^(j)_A` and `Σ_j x_j P^(j)_B`; if the
   agents are separable, `Q^π_AB = Q^π_A ⊗ e + e ⊗ Q^π_B` for every reward pair; and if `γ > 0`
   and that identity holds for every reward pair, the agents are separable.

Source: Chen & Peng, Multi-agent Markov Entanglement, arXiv:2506.02385v3, Theorem 1, p.9, and
Theorem 2, p.12, combined in the sentence following Theorem 2, p.12.

**Formalization Note.** Agent `A`'s state-action pairs are `Σ s, AA s`, with `AA s` the feasible
action set of footnote 1, p.8, and the paper's constant action set is a special case. Q-values
are the solutions of `IsBellmanQ`, which exist and are unique, and local transitions the
solutions of `IsLocalTransitionA/B`, which exist and are unique under `IsOccupancy`, so the
universal quantifiers are neither vacuous nor free. `μ` is not assumed stationary and need not be
unique or strictly positive on joint pairs; the paper's occupancy measure is an instance once the
feasible sets are restricted as in footnote 1. The clauses that need `γ > 0` carry it themselves,
because `γ = 0` is a counterexample to them only (§4, p.12). -/
theorem exact_value_decomposition_iff_separable
    {SA SB : Type*} [Fintype SA] [Fintype SB] [DecidableEq SA] [DecidableEq SB]
    {AA : SA → Type*} {AB : SB → Type*} [∀ s, Fintype (AA s)] [∀ s, Fintype (AB s)]
    [∀ s, DecidableEq (AA s)] [∀ s, DecidableEq (AB s)]
    (kernel : (s : SA × SB) → AA s.1 × AB s.2 → SA × SB → ℝ)
    (hkernel : IsFeasibleKernel kernel)
    (π : (s : SA × SB) → AA s.1 × AB s.2 → ℝ)
    (hπ : IsFeasiblePolicy π)
    {P : Matrix ((Σ s, AA s) × (Σ s, AB s)) ((Σ s, AA s) × (Σ s, AB s)) ℝ}
    (hP : P = inducedMatrix kernel π)
    (γ : ℝ) (hγ0 : 0 ≤ γ) (hγ1 : γ < 1) :
    (IsSeparable P → HasExactValueDecomposition P γ) ∧
      (0 < γ → HasExactValueDecomposition P γ → IsSeparable P) ∧
      ∀ μ : (Σ s, AA s) × (Σ s, AB s) → ℝ, IsOccupancy μ →
        ∀ (PA : Matrix (Σ s, AA s) (Σ s, AA s) ℝ) (PB : Matrix (Σ s, AB s) (Σ s, AB s) ℝ),
          IsLocalTransitionA P μ PA → IsLocalTransitionB P μ PB →
            IsTransitionMatrix PA ∧ IsTransitionMatrix PB ∧
            (∀ (K : ℕ) (x : Fin K → ℝ) (PAj : Fin K → Matrix (Σ s, AA s) (Σ s, AA s) ℝ)
                (PBj : Fin K → Matrix (Σ s, AB s) (Σ s, AB s) ℝ),
              IsSeparableWitness P K x PAj PBj →
                PA = ∑ k, x k • PAj k ∧ PB = ∑ k, x k • PBj k) ∧
            (IsSeparable P → LocalValuesDecompose P PA PB γ) ∧
            (0 < γ → LocalValuesDecompose P PA PB γ → IsSeparable P) := by sorry

end MarkovEntanglementExact
Source
Chen & Peng, Multi-agent Markov Entanglement, arXiv:2506.02385v3, Theorem 1, p.9, Theorem 2, p.12, and the following sentence, p.12
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