LeanMachineLearning

Learning.IsObliviousEnvπŸ”—

Type Class

An environment is oblivious if the distribution of the next feedback depends only on the last action and not on the past history.

πŸ”—type class
Learning.IsObliviousEnv.{u_1, u_2} {𝓐 : Type u_1} {𝓨 : Type u_2}
  {m𝓐 : MeasurableSpace 𝓐} {m𝓨 : MeasurableSpace 𝓨}
  (env : Environment 𝓐 𝓨) : Prop
Learning.IsObliviousEnv.{u_1, u_2}
  {𝓐 : Type u_1} {𝓨 : Type u_2}
  {m𝓐 : MeasurableSpace 𝓐}
  {m𝓨 : MeasurableSpace 𝓨}
  (env : Environment 𝓐 𝓨) : Prop

Code

class IsObliviousEnv (env : Environment 𝓐 𝓨) : Prop where exists_eq_prodMkLeft : βˆƒ Ξ½ : β„• β†’ Kernel 𝓐 𝓨, (βˆ€ n, IsMarkovKernel (Ξ½ n)) ∧ (env.Ξ½0 = Ξ½ 0) ∧ (βˆ€ n, env.feedback n = (Ξ½ (n + 1)).prodMkLeft _)

Actions: Source Β· Open Issue

Meaning last changed in v4.34.0-rc2-1-g439785b (2026-08-23), the 2th recorded change.

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: 1 project declarations, 26 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.