LeanMachineLearning

Learning.sumRewards_eq_comp_history๐Ÿ”—

Lemma

From the authors

sumRewards A R a n is a function of the history before time n.

Types
  • ๐“ž : Type u_1
  • ๐“ : Type u_2DecidableEq ๐“
  • ๐“จ : Type u_3AddCommGroup ๐“จAn additive commutative group is an additive group with commutative (+).
  • ฮฉ : Type u_4
Given
  • O : โ„• โ†’ ฮฉ โ†’ ๐“ž
  • A : โ„• โ†’ ฮฉ โ†’ ๐“
  • R : โ„• โ†’ ฮฉ โ†’ ๐“จ
  • a : ๐“
  • n : โ„•
Then
sumRewards A R a n = (fun h => sumRewards' n h a) โˆ˜ history O A R n
Code
lemma sumRewards_eq_comp_history {R : โ„• โ†’ ฮฉ โ†’ ๐“จ} (a : ๐“) (n : โ„•) :
    sumRewards A R a n = (fun h : Hist ๐“ž ๐“ ๐“จ n โ†ฆ sumRewards' n h a) โˆ˜ history O A R n
Proof
by
  ext ฯ‰
  exact sumRewards_eq_sumRewards'

Meaning last changed in v4.34.0-rc2-76-g565f652 (2026-09-10), the 2th recorded change.

Self-contained, with its dependencies inlined and proofs replaced by sorry: download the raw file ยท open it in the Lean web editor.

Dependency graph

Audit surface: 7 project declarations, 24 external constants

โœ“ Proved: no sorry anywhere in its closure

This is the tool's own reading of one build's recorded axioms, and it is not robust against an author who wants it to pass. Checking meant to be relied on should go through Comparator, which replays the proof through the kernel from an export against an explicit list of permitted axioms.