Prove2Me
Navigate
DiscoverCollectionsFormalpediaGalaxyBlogsUsersMomentumMy Missions+
Prove2Me
Log in
← Formalpedia

Corollary 2(b) — V*_λ is the unique bounded solution of the robust optimality equation (30), and ε-optimal stationary policies exist

Proved
RobustDP.Discounted.corollary2b_value_unique_fixed_point

by mikedeng1 · Oct 7, 2026 · Mathlib 0df444a (Lean v4.33.1)

bellman-equationdynamic-programmingp2o-batch-pfp2ap2o-gran-per-chapterp2o-plan-paperp2o-v1robust-optimization

Let (S,A,P,r,λ)(\mathcal S,\mathcal A,\mathcal P,r,\lambda)(S,A,P,r,λ) be a discounted ambiguous MDP with robust value function Vλ∗(s)=sup⁡π∈ΠVλπ(s)V^*_\lambda(s)=\sup_{\pi\in\Pi}V^\pi_\lambda(s)Vλ∗​(s)=supπ∈Π​Vλπ​(s), the supremum over all history dependent randomized policies. Then

  1. Vλ∗V^*_\lambdaVλ∗​ is bounded and solves
V(s)=sup⁡a∈A(s) inf⁡p∈P(s,a)Ep[r(s,a,s′)+λV(s′)],s∈S;(30)V(s)=\sup_{a\in\mathcal A(s)}\ \inf_{p\in\mathcal P(s,a)}\mathbf E^p\big[r(s,a,s')+\lambda V(s')\big],\qquad s\in\mathcal S;\tag{30}V(s)=a∈A(s)sup​ p∈P(s,a)inf​Ep[r(s,a,s′)+λV(s′)],s∈S;(30)
  1. every bounded solution of (30) equals Vλ∗V^*_\lambdaVλ∗​;
  2. for every ϵ>0\epsilon>0ϵ>0 there is a deterministic Markov decision rule dϵd^\epsilondϵ whose stationary policy πϵ=(dϵ,dϵ,… )\pi^\epsilon=(d^\epsilon,d^\epsilon,\dots)πϵ=(dϵ,dϵ,…) satisfies Vλπϵ(s)≥Vλ∗(s)−ϵV^{\pi^\epsilon}_\lambda(s)\ge V^*_\lambda(s)-\epsilonVλπϵ​(s)≥Vλ∗​(s)−ϵ for every sss.

This is the robust Bellman equation of discounted dynamic programming: the robust value function is computed by a fixed point of a state-wise max–min operator, and nearly optimal policies can be taken stationary.

Formalization Note "Unique solution" is uniqueness among bounded functions (the space V\mathbf VV of the page). The ϵ\epsilonϵ-optimal stationary policy is deterministic, as the page's construction (28) gives. VλπV^\pi_\lambdaVλπ​ is the value against the dynamic (rectangular) adversary.

Preamble
import Mathlib
import Definitions.Def_RobustDP_Discounted_Model
import Definitions.Def_RobustDP_Discounted_Value
import Definitions.Def_RobustDP_Discounted_Bellman
Formal statement
namespace RobustDP.Discounted

theorem corollary2b_value_unique_fixed_point {S A : Type*} [Countable S] [Countable A]
    (M : Model S A) :
    IsBounded (Vstar M) ∧ (∀ s, Vstar M s = T M (Vstar M) s) ∧
      (∀ U : S → ℝ, IsBounded U → (∀ s, U s = T M U s) → U = Vstar M) ∧
      ∀ ε : ℝ, 0 < ε → ∃ d : DecisionRule M, ∀ s, Vstar M s - ε ≤ V M (stationary M d) s := by sorry

end RobustDP.Discounted
Source
Iyengar, Robust dynamic programming, CORC Tech Report TR-2002-07 (rev. May 4, 2004), p. 11, Corollary 2(b), eq. (30)
Human review
  • Endorsed by Shuze Chen · Oct 7, 2026

    Confirmed by the moderator at approval.

  • Endorsed by mikedeng1 · Oct 7, 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