Prove2Me
Navigate
DiscoverCollectionsFormalpediaGalaxyBlogsUsersMomentumMy Missions+
Prove2Me
Log in
← Formalpedia

Theorem 13(a) — IVI↑optIVI_{\uparrow opt}IVI↑opt​ and IVI↓pesIVI_{\downarrow pes}IVI↓pes​ are contraction mappings

Proved
BoundedParamMDP.IntervalEval.theorem13a_contraction

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

contractiondynamic-programmingmarkov-decision-processesp2o-batch-pfp2ap2o-gran-per-chapterp2o-plan-paperp2o-v1

Let M↕M_\updownarrowM↕​ be a bounded-parameter MDP with finite state set QQQ and finite nonempty action set AAA. IVI↑optIVI_{\uparrow opt}IVI↑opt​ is the upper bound returned by optimistic interval value iteration IVI↕optIVI_{\updownarrow opt}IVI↕opt​; it depends only on the upper bound V↑V_\uparrowV↑​ of its input, and is regarded as a map V‾→V‾\overline V\to\overline VV→V. Likewise IVI↓pesIVI_{\downarrow pes}IVI↓pes​, the lower bound returned by IVI↕pesIVI_{\updownarrow pes}IVI↕pes​, depends only on V↓V_\downarrowV↓​.

Theorem 13(a). IVI↑optIVI_{\uparrow opt}IVI↑opt​ and IVI↓pesIVI_{\downarrow pes}IVI↓pes​ are contraction mappings. Precisely, there are λ,λ′∈[0,1)\lambda,\lambda'\in[0,1)λ,λ′∈[0,1) such that for all interval inputs [L,U][L,U][L,U] and [L′,U′][L',U'][L′,U′],

∥IVI↑opt([L′,U′])−IVI↑opt([L,U])∥≤λ ∥U′−U∥,∥IVI↓pes([L′,U′])−IVI↓pes([L,U])∥≤λ′ ∥L′−L∥.\big\|IVI_{\uparrow opt}([L',U'])-IVI_{\uparrow opt}([L,U])\big\|\le\lambda\,\|U'-U\|,\qquad \big\|IVI_{\downarrow pes}([L',U'])-IVI_{\downarrow pes}([L,U])\big\|\le\lambda'\,\|L'-L\|.​IVI↑opt​([L′,U′])−IVI↑opt​([L,U])​≤λ∥U′−U∥,​IVI↓pes​([L′,U′])−IVI↓pes​([L,U])​≤λ′∥L′−L∥.

With Theorem 9 this yields convergence of the upper bounds of optimistic (lower bounds of pessimistic) interval value iteration.

Formalization Note. The inequalities are taken over arbitrary pairs of input functions with arbitrary values of the other bound. Taking equal other bounds gives the contraction property of the map on V‾\overline VV; taking equal relevant bounds gives the independence from the other bound (p. 23) that makes the map on V‾\overline VV well defined. Inputs are not required to be proper intervals (L≤UL\le UL≤U).

Preamble
import Mathlib
import Definitions.Def_BoundedParamMDP_Optimal_MDP
import Definitions.Def_BoundedParamMDP_Optimal_BMDP
import Definitions.Def_BoundedParamMDP_IntervalEval_IntervalValueIteration
Formal statement
namespace BoundedParamMDP.IntervalEval

/-- Theorem 13(a) (Givan–Leach–Dean 2000, p. 25; proof pp. 45–47): `IVI↑opt` and `IVI↓pes` are
contraction mappings. `IVI↑opt` is the upper bound returned by `IVI↕opt`, regarded as a map
`V̄ → V̄` of the upper input `V↑` (it does not depend on the lower input, p. 23); `IVI↓pes`
likewise is the lower bound returned by `IVI↕pes` as a map of the lower input `V↓`. The
statement bounds the outputs for two arbitrary interval inputs by `λ` times the distance of
the relevant input bounds only: this is the contraction property together with the
independence from the other bound that makes the maps well defined on `V̄`. -/
theorem theorem13a_contraction {Q A : Type*} [Fintype Q] [Fintype A] [Nonempty A]
    (B : BoundedParamMDP.Optimal.BMDP Q A) :
    (∃ c : ℝ, 0 ≤ c ∧ c < 1 ∧ ∀ L L' U U' : Q → ℝ,
      ‖(fun p => (IVIopt B (L', U') p).2) - (fun p => (IVIopt B (L, U) p).2)‖ ≤
        c * ‖U' - U‖) ∧
    (∃ c : ℝ, 0 ≤ c ∧ c < 1 ∧ ∀ L L' U U' : Q → ℝ,
      ‖(fun p => (IVIpes B (L', U') p).1) - (fun p => (IVIpes B (L, U) p).1)‖ ≤
        c * ‖L' - L‖) := by sorry

end BoundedParamMDP.IntervalEval
Source
Givan, Leach, Dean, Bounded-parameter Markov decision processes, Artificial Intelligence (2000), DOI 10.1016/S0004-3702(00)00047-3, manuscript of May 22, 2000, p. 25, Theorem 13(a) (proof pp. 45–47); IVI↑opt as a map on value functions, p. 23
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