LeanMachineLearning exposition

Learning.measurable_feedbackFunZeroπŸ”—

This page has the declaration's own card below, then its dependency graph, then a card for each dependency (type dependencies first, then the rest of the transitive closure). For a theorem, the graph and the dependency cards only follow its statement's dependencies (its proof is replaced by sorry, so what it proves doesn't depend on how); for everything else, both the type and the body/value are followed, since their content is part of what later declarations build on.

Minimal Lean file

measurable_feedbackFunZeroπŸ”—

LemmaLearning.measurable_feedbackFunZero
Details

No docstring.

πŸ”—theorem
Learning.measurable_feedbackFunZero.{u_1, u_2} {𝓐 : Type u_1}
  {𝓨 : Type u_2} {m𝓐 : MeasurableSpace 𝓐} {m𝓨 : MeasurableSpace 𝓨}
  (env : Environment 𝓐 𝓨) [IsDeterministicEnv env] :
  Measurable (feedbackFunZero env)
Learning.measurable_feedbackFunZero.{u_1,
    u_2}
  {𝓐 : Type u_1} {𝓨 : Type u_2}
  {m𝓐 : MeasurableSpace 𝓐}
  {m𝓨 : MeasurableSpace 𝓨}
  (env : Environment 𝓐 𝓨)
  [IsDeterministicEnv env] :
  Measurable (feedbackFunZero env)

Code

lemma measurable_feedbackFunZero (env : Environment 𝓐 𝓨) [IsDeterministicEnv env] :
    Measurable (feedbackFunZero env)
Type uses (3)
Used by (4)

Actions: Source Β· Open Issue

Proof
(IsDeterministicEnv.exists_f0).choose_spec.choose

Dependency graph

Type dependencies (3)

EnvironmentπŸ”—

StructureLearning.Environment
Details

A stochastic environment.

πŸ”—structure
Learning.Environment.{u_4, u_5} (𝓐 : Type u_4) (𝓨 : Type u_5)
  [MeasurableSpace 𝓐] [MeasurableSpace 𝓨] : Type (max u_4 u_5)
Learning.Environment.{u_4, u_5}
  (𝓐 : Type u_4) (𝓨 : Type u_5)
  [MeasurableSpace 𝓐]
  [MeasurableSpace 𝓨] : Type (max u_4 u_5)

Code

structure Environment (𝓐 𝓨 : Type*) [MeasurableSpace 𝓐] [MeasurableSpace 𝓨] where
  /-- Distribution of the next observation as function of the past history. -/
  feedback : (n : β„•) β†’ Kernel ((Iic n β†’ 𝓐 Γ— 𝓨) Γ— 𝓐) 𝓨
  /-- The feedback kernels are Markov kernels. -/
  [h_feedback : βˆ€ n, IsMarkovKernel (feedback n)]
  /-- Distribution of the first observation given the first action. -/
  Ξ½0 : Kernel 𝓐 𝓨
  /-- The initial observation kernel is a Markov kernel. -/
  [hp0 : IsMarkovKernel Ξ½0]
Used by (128)

Actions: Source Β· Open Issue

IsDeterministicEnvπŸ”—

Type ClassLearning.IsDeterministicEnv
Details

An environment is deterministic if its initial feedbacks are determined by measurable functions (and not possibly random kernels).

πŸ”—type class
Learning.IsDeterministicEnv.{u_1, u_2} {𝓐 : Type u_1} {𝓨 : Type u_2}
  {m𝓐 : MeasurableSpace 𝓐} {m𝓨 : MeasurableSpace 𝓨}
  (env : Environment 𝓐 𝓨) : Prop
Learning.IsDeterministicEnv.{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 IsDeterministicEnv (env : Environment 𝓐 𝓨) : Prop where
  exists_f0 : βˆƒ (f0 : 𝓐 β†’ 𝓨) (hf0 : Measurable f0), env.Ξ½0 = Kernel.deterministic f0 hf0
  exists_f : βˆ€ n, βˆƒ (f : ((Iic n β†’ 𝓐 Γ— 𝓨) Γ— 𝓐) β†’ 𝓨) (hf : Measurable f),
    env.feedback n = Kernel.deterministic f hf
Type uses (1)
Used by (11)

Actions: Source Β· Open Issue

feedbackFunZeroπŸ”—

DefinitionLearning.feedbackFunZero
Details

The initial feedback function of a deterministic environment.

πŸ”—def
Learning.feedbackFunZero.{u_1, u_2} {𝓐 : Type u_1} {𝓨 : Type u_2}
  {m𝓐 : MeasurableSpace 𝓐} {m𝓨 : MeasurableSpace 𝓨}
  (env : Environment 𝓐 𝓨) [h_det : IsDeterministicEnv env] : 𝓐 β†’ 𝓨
Learning.feedbackFunZero.{u_1, u_2}
  {𝓐 : Type u_1} {𝓨 : Type u_2}
  {m𝓐 : MeasurableSpace 𝓐}
  {m𝓨 : MeasurableSpace 𝓨}
  (env : Environment 𝓐 𝓨)
  [h_det : IsDeterministicEnv env] : 𝓐 β†’ 𝓨

Code

noncomputable
def feedbackFunZero (env : Environment 𝓐 𝓨) [h_det : IsDeterministicEnv env] : 𝓐 β†’ 𝓨 :=
  h_det.exists_f0.choose
Type uses (2)
Used by (6)

Actions: Source Β· Open Issue