LeanMachineLearning

Learning.Environment.comapActionπŸ”—

Definition

From the authors

The environment that reads f a when the algorithm plays a, both in the current round and in the past rounds.

Types
  • π“ž : Type u_1mπ“ž : MeasurableSpace π“žA measurable space is a space equipped with a Οƒ-algebra.
  • 𝓐 : Type u_4m𝓐 : MeasurableSpace 𝓐
  • 𝓐' : Type u_5m𝓐' : MeasurableSpace 𝓐'
  • 𝓨 : Type u_7m𝓨 : MeasurableSpace 𝓨
Given
Assuming
  • hf : Measurable fA function f between measurable spaces is measurable if the preimage of every measurable set is measurable.
Result
Environment π“ž 𝓐' 𝓨
Body
env.comap (fun x => Hist.mapAction f) β‹― f hf
Code
def Environment.comapAction (env : Environment π“ž 𝓐 𝓨) (f : 𝓐' β†’ 𝓐)
    (hf : Measurable f := by fun_prop) : Environment π“ž 𝓐' 𝓨 :=
  env.comap (fun _ ↦ Hist.mapAction f) (fun _ ↦ by fun_prop) f hf

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 Β· open it in the Lean web editor.

Dependency graph

Audit surface: 10 project declarations, 23 external constants

βœ“ 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.