Lemma 3.3 — Exact attainable mean set
ProvedXuDRMDP.Finite.lemma_3_3Let be a finite nonempty staged state set with finite nonempty action sets , initial stage consisting of alone, finite horizon , zero terminal rewards and discount . Assume the nested local parameter sets () are nonempty, convex and compact sets of valid transition/reward vectors. Local sets may couple all actions. Let . The local class consists of all Borel probability laws supported on with , and consists of their statewise product laws. Policies are all history-dependent randomized policies on state/action histories, including null histories. Returns are the independent finite trajectory expectations, subsequently integrated against the parameter law.
For every state , the set of attainable local means is exactly
This is set equality in both directions for the full Borel-law class. Repeated confidence levels, zero increments, identical nested sets and singleton sets are included.
Differences from the source:
- encoding: finite states and state-dependent actions, one-based staged histories, and expected discounted trajectory returns → nonempty Fin types, zero-based stages, total policy extensions on unused histories, and explicit finite trajectory sums followed by Bochner integration; reason: finite relabeling and unused extensions preserve all source instances; compact outer support ensures integrability and finite bounded returns
- reading: Definition 3.2 displays (r,p) in the weighted sum but (p,r) in its membership condition → consistent (p,r) coordinates in the reduction set; reason: Lemma 3.3 and its proof fix the intended order; see insight I1
import Definitions.Def_XuDRMDP_Finite_Setup import Definitions.Def_XuDRMDP_Finite_Policies import Definitions.Def_XuDRMDP_Finite_Ambiguity import Definitions.Def_XuDRMDP_Finite_Returns import Definitions.Def_XuDRMDP_Finite_Robustness open MeasureTheory
namespace XuDRMDP.Finite
theorem lemma_3_3 {n : ℕ} [NeZero n] {a : Fin n → ℕ} [∀ s, NeZero (a s)]
(G : Setup n a) (U : Uncertainty G) (s : Fin n) :
{x | ∃ μ ∈ localClass U s, localMean μ = x} = reducedSet U s := by sorry
end XuDRMDP.Finite
Read-back
What the Lean code literally says, in plain math · claude-opus-5-5
Data.
- states and actions with every .
- A setup : horizon , discount , stage map , and initial state .
- An uncertainty structure consisting of:
- confidence levels ;
- for each state , sets in , each nonempty, convex and compact, all of whose points are valid local MDP coordinates at for . Valid means the point equals some imported-type MDP's data at , has zero rewards if , and otherwise zero transition entries to states not at stage .
- A fixed state .
Let be the set of measures on (standard Borel σ-algebra) with:
- a probability measure;
- ;
- for every .
Let and for .
Claim. The set of means of measures in equals the weighted Minkowski sum:
Means are vector-valued Bochner integrals, and operations on pairs are componentwise.
Degenerate cases.
- For : , . The claim reads: the means of probability measures giving full mass are exactly the points of .
- When some , the constraint is vacuous and may be . A zero-weight layer contributes to the sum, while must still be chosen from the nonempty .
- The Bochner integral is for a non-integrable measure, and the left-hand set is formed under that convention.
- The setup enters only through the validity requirement built into .
Confirmed by the mission captain (proposal self-audit).
Confirmed by the moderator at approval.