Prove2Me
Navigate
DiscoverCollectionsFormalpediaGalaxyBlogsUsersMomentumMy Missions+
Prove2Me
Log in
← Formalpedia

§4.4.1, p. 115 — Q̂^a_t(b) ≤ Q^a_t(b): the approximation is always an underestimate

Proved
KaelblingPOMDP.Witness.underestimate

by mikedeng1 · Oct 6, 2026 · Mathlib 0df444a (Lean v4.33.1)

p2o-batch-pfp2ap2o-gran-per-chapterp2o-plan-paperp2o-v1pomdpq-functionwitness-algorithm

Let ⟨S,A,T,R,Ω,O⟩\langle S, A, T, R, \Omega, O\rangle⟨S,A,T,R,Ω,O⟩ be a POMDP satisfying the standing hypotheses, t≥2t \ge 2t≥2 and aaa an action. Let UaU_aUa​ be a nonempty finite set of ttt-step trees with root action aaa whose subtrees all lie in Vt−1\mathcal V_{t-1}Vt−1​, and let Q^ta(b)=max⁡p∈UaVp(b)\hat Q^a_t(b) = \max_{p \in U_a} V_p(b)Q^​ta​(b)=maxp∈Ua​​Vp​(b). Then for every belief state bbb,

Q^ta(b)≤Qta(b).\hat Q^a_t(b) \le Q^a_t(b).Q^​ta​(b)≤Qta​(b).

The witness algorithm grows UaU_aUa​ from below; a belief state where the inequality is strict is a witness that UaU_aUa​ is not yet complete.

Formalization Note QtaQ^a_tQta​ is Qfun, the formula of p. 114. Here t=n+2t = n + 2t=n+2.

Preamble
import Mathlib
import Definitions.Def_KaelblingPOMDP_Witness_Useful
Formal statement
namespace KaelblingPOMDP.Witness

open Finset

universe u

/-- §4.4.1, p. 115 (Kaelbling, Littman, Cassandra, *Planning and acting in partially observable stochastic domains*,
Artificial Intelligence 101:99–134 (1998)): "Note that for all b, Q̂^a_t(b) ⩽ Q^a_t(b); the approximation
is always an underestimate of the true value function." Here `U_a` is any nonempty set of candidate
trees (root `a`, subtrees in `V_{t−1}`), `Q̂^a_t(b) = max_{p ∈ U_a} V_p(b)`, and `t = n + 2`. -/
theorem underestimate {S A Ω : Type u} [Fintype S] [DecidableEq S] [Nonempty S] [Fintype A] [DecidableEq A]
    [Nonempty A] [Fintype Ω] [DecidableEq Ω] [Nonempty Ω]
    (M : POMDP S A Ω) (hM : M.IsValid) (a : A) (n : ℕ)
    (U : Finset (PolicyTree A Ω (n + 1))) (hU : U.Nonempty) (hUC : U ⊆ candidates M a n) :
    ∀ b ∈ stdSimplex ℝ S, upper M U hU b ≤ Qfun M a n b := by sorry

end KaelblingPOMDP.Witness
Source
Kaelbling, Littman, Cassandra, Planning and acting in partially observable stochastic domains, Artificial Intelligence 101:99–134 (1998), DOI 10.1016/S0004-3702(98)00023-X, p. 115, §4.4.1
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