LeanMachineLearning

Learning.Environment.ext๐Ÿ”—

Theorem

No docstring.

Types
  • ๐“ž : Type u_5MeasurableSpace ๐“žA measurable space is a space equipped with a ฯƒ-algebra.
  • ๐“ : Type u_6MeasurableSpace ๐“
  • ๐“จ : Type u_7MeasurableSpace ๐“จ
Given
Assuming
  • obs : x.obs = y.obs
  • feedback : x.feedback = y.feedback
Then
x = y
Code
theorem ext : โˆ€ {๐“ž : Type u_5} {๐“ : Type u_6} {๐“จ : Type u_7} {inst : MeasurableSpace ๐“ž} {inst_1 : MeasurableSpace ๐“}
  {inst_2 : MeasurableSpace ๐“จ} {x y : Learning.Environment ๐“ž ๐“ ๐“จ}, x.obs = y.obs โ†’ x.feedback = y.feedback โ†’ x = y
Proof

Meaning last changed in v4.34.0-rc2-76-g565f652 (2026-09-10).

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: 3 project declarations, 9 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.