Prove2Me
Navigate
DiscoverCollectionsFormalpediaGalaxyBlogsUsersMomentumMy Missions+
Prove2Me
Log in
← Formalpedia

Lemma 2 — along policy improvement the gaps ε_i^{R_n} tend to 0 at every state

Proved
DermanDenumerable.AvgCost.lemma2

by mikedeng1 · Oct 5, 2026 · Mathlib 0df444a (Lean v4.33.1)

average-costdynamic-programmingp2o-batch-pfp2bp2o-gran-per-chapterp2o-plan-paperp2o-v1policy-improvement

Assume (A), (B), (C), (E) and (F). Let {gR,vjR}\{g^R, v^R_j\}{gR,vjR​} be the uniformly bounded family of (E), and let R1,R2,…R_1, R_2, \dotsR1​,R2​,… be a sequence of policy improvement iterations starting from an arbitrary R1∈C′′R_1 \in C''R1​∈C′′: for every nnn, the decisions ki′k_i'ki′​ of Rn+1R_{n+1}Rn+1​ minimize wik+∑jqij(k)vjRnw_{ik} + \sum_j q_{ij}(k) v_j^{R_n}wik​+∑j​qij​(k)vjRn​​ at every state. With

εiRn=gRn+viRn−(wiki′+∑jqij(ki′)vjRn),\varepsilon_i^{R_n} = g^{R_n} + v_i^{R_n} - \Big(w_{ik_i'} + \sum_j q_{ij}(k_i') v_j^{R_n}\Big),εiRn​​=gRn​+viRn​​−(wiki′​​+j∑​qij​(ki′​)vjRn​​),

we have, for each i∈Ii \in Ii∈I,

lim⁡n→∞εiRn=0.\lim_{n\to\infty} \varepsilon_i^{R_n} = 0 .n→∞lim​εiRn​​=0.

The lemma says that the improvement step eventually stops finding improvements at each fixed state; it is the key step of Theorem 4.

Formalization Note. The improvement step is taken against the family vRv^RvR of (E), as in the paper's definition of εiR\varepsilon_i^RεiR​; ties among minimizing decisions are broken arbitrarily. Condition (D) is implied by (E) and is not a separate hypothesis. The sequence is indexed from 000 in Lean.

Preamble
import Mathlib
import Definitions.Def_DermanDenumerable_AvgCost_Model
open scoped Topology
open Filter SennottDP.AvgFinite
Formal statement
namespace DermanDenumerable.AvgCost

/-- Derman (1966), Lemma 2, pp. 1551–1552: under (A), (B), (C), (E) (hence (D)) and (F), for any
sequence `R_1, R_2, ⋯` of policy improvement iterations (relative to the family `{g^R, v^R}` of (E))
starting from an arbitrary rule of `C''`, `lim_{n→∞} ε_i^{R_n} = 0` for every state `i`. -/
theorem lemma2 {S Act : Type} [Countable S] (M : MDC S Act)
    (w : S → Act → ℝ) (hB : CostBounded M w) (hC : CondC M) (gR : StationaryPolicy M → ℝ)
    (vR : StationaryPolicy M → S → ℝ) (hE : IsUniformEvaluation M w gR vR) (hF : CondF M)
    (R : ℕ → StationaryPolicy M) (hR : IsPISequence M w vR R) :
    ∀ i : S, Tendsto (fun n : ℕ => gap M w gR vR (R n) (R (n + 1)) i) atTop (𝓝 0) := by sorry

end DermanDenumerable.AvgCost
Source
Derman, Denumerable State Markovian Decision Processes—Average Cost Criterion, Ann. Math. Statist. 37(6) (1966), pp. 1551–1552, Lemma 2 (ε_i^R and the procedure on p. 1551)
Human review
  • Endorsed by Shuze Chen · Oct 6, 2026

    Confirmed by the moderator at approval.

  • Endorsed by mikedeng1 · Oct 6, 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