`Learning.IsAlgEnvSeq.isBayesAlgEnvSeq`🔗

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

`isBayesAlgEnvSeq`🔗

LemmaLearning.IsAlgEnvSeq.isBayesAlgEnvSeq

Details

No docstring.

theorem

Learning.IsAlgEnvSeq.isBayesAlgEnvSeq.{u_1, u_2, u_3, u_4}
  {𝓔 : Type u_1} {𝓐 : Type u_2} {𝓨 : Type u_3} {Ω : Type u_4}
  [MeasurableSpace 𝓔] [MeasurableSpace 𝓐] [MeasurableSpace 𝓨]
  [MeasurableSpace Ω] {Q : MeasureTheory.Measure 𝓔}
  [MeasureTheory.IsProbabilityMeasure Q]
  {κ : ProbabilityTheory.Kernel (𝓔 × 𝓐) 𝓨}
  [ProbabilityTheory.IsMarkovKernel κ] {alg : Algorithm 𝓐 𝓨}
  {A : ℕ → Ω → 𝓐} {Y : ℕ → Ω → 𝓔 × 𝓨} {P : MeasureTheory.Measure Ω}
  [MeasureTheory.IsProbabilityMeasure P]
  (h :
    IsAlgEnvSeq A Y (Algorithm.prodLeft 𝓔 alg) (bayesStationaryEnv Q κ)
      P) :
  IsBayesAlgEnvSeq Q κ alg (fun ω => Prod.fst (Y 0 ω)) A
    (fun n ω => Prod.snd (Y n ω)) P
Learning.IsAlgEnvSeq.isBayesAlgEnvSeq.{u_1,
    u_2, u_3, u_4}
  {𝓔 : Type u_1} {𝓐 : Type u_2}
  {𝓨 : Type u_3} {Ω : Type u_4}
  [MeasurableSpace 𝓔] [MeasurableSpace 𝓐]
  [MeasurableSpace 𝓨] [MeasurableSpace Ω]
  {Q : MeasureTheory.Measure 𝓔}
  [MeasureTheory.IsProbabilityMeasure Q]
  {κ : ProbabilityTheory.Kernel (𝓔 × 𝓐) 𝓨}
  [ProbabilityTheory.IsMarkovKernel κ]
  {alg : Algorithm 𝓐 𝓨} {A : ℕ → Ω → 𝓐}
  {Y : ℕ → Ω → 𝓔 × 𝓨}
  {P : MeasureTheory.Measure Ω}
  [MeasureTheory.IsProbabilityMeasure P]
  (h :
    IsAlgEnvSeq A Y
      (Algorithm.prodLeft 𝓔 alg)
      (bayesStationaryEnv Q κ) P) :
  IsBayesAlgEnvSeq Q κ alg
    (fun ω => Prod.fst (Y 0 ω)) A
    (fun n ω => Prod.snd (Y n ω)) P

Code

lemma IsAlgEnvSeq.isBayesAlgEnvSeq
    (h : IsAlgEnvSeq A Y (alg.prodLeft 𝓔) (bayesStationaryEnv Q κ) P) :
    IsBayesAlgEnvSeq Q κ alg (fun ω ↦ (Y 0 ω).1) A (fun n ω ↦ (Y n ω).2) P where
  measurable_param

Type uses (5)

Body uses (6)

Used by (1)

isBayesAlgEnvSeq_bayesTrajMeasure

Actions: Source · Open Issue

Proof

(h.measurable_feedback 0).fst
  measurable_action := h.measurable_action
  measurable_feedback n := (h.measurable_feedback n).snd
  hasLaw_env := by
    apply HasCondDistrib.hasLaw_of_const
    simpa [bayesStationaryEnv] using h.hasCondDistrib_feedback_zero.fst
  hasCondDistrib_action_zero := by
    have hc : HasCondDistrib (fun ω ↦ (Y 0 ω).1) (A 0) (Kernel.const _ Q) P := by
      simpa [bayesStationaryEnv] using h.hasCondDistrib_feedback_zero.fst
    simpa [h.hasLaw_action_zero.map_eq, Algorithm.prodLeft] using hc.const_map_of_const
  hasCondDistrib_feedback_zero :=
    h.hasCondDistrib_feedback_zero.of_compProd.measurableEquiv_comp_right MeasurableEquiv.prodComm
  hasCondDistrib_action n := by
    let f : (Iic n → 𝓐 × 𝓔 × 𝓨) → 𝓔 × (Iic n → 𝓐 × 𝓨) :=
      fun h ↦ ((h ⟨0, by simp⟩).2.1, fun i ↦ ((h i).1, (h i).2.2))
    have hc : HasCondDistrib (A (n + 1)) (history A Y n)
        (((alg.policy n).comap Prod.snd (by fun_prop)).comap f (by fun_prop)) P :=
      h.hasCondDistrib_action n
    exact hc.comp_right (f := f)
  hasCondDistrib_feedback n := by
    let f : (Iic n → 𝓐 × 𝓔 × 𝓨) × 𝓐 → (Iic n → 𝓐 × 𝓨) × 𝓔 × 𝓐 :=
      fun p ↦ ((fun i ↦ ((p.1 i).1, (p.1 i).2.2)), (p.1 ⟨0, by simp⟩).2.1, p.2)
    have hc : HasCondDistrib (fun ω ↦ (Y (n + 1) ω).2)
        (fun ω ↦ (history A Y n ω, A (n + 1) ω))
        ((Kernel.prodMkLeft ((Iic n) → 𝓐 × 𝓨) κ).comap f (by fun_prop)) P := by
      simpa [bayesStationaryEnv, Kernel.prodMkLeft, ← Kernel.comap_comp_right, Function.comp_def]
        using (h.hasCondDistrib_feedback n).snd
    exact hc.comp_right

Dependency graph

Type dependencies (5)

`Algorithm`🔗

StructureLearning.Algorithm

Details

A stochastic, sequential algorithm.

structure

Learning.Algorithm.{u_4, u_5} (𝓐 : Type u_4) (𝓨 : Type u_5)
  [MeasurableSpace 𝓐] [MeasurableSpace 𝓨] : Type (max u_4 u_5)
Learning.Algorithm.{u_4, u_5}
  (𝓐 : Type u_4) (𝓨 : Type u_5)
  [MeasurableSpace 𝓐]
  [MeasurableSpace 𝓨] : Type (max u_4 u_5)

Code

structure Algorithm (𝓐 𝓨 : Type*) [MeasurableSpace 𝓐] [MeasurableSpace 𝓨] where
  /-- Policy or sampling rule: distribution of the next action. -/
  policy : (n : ℕ) → Kernel (Iic n → 𝓐 × 𝓨) 𝓐
  /-- The policy is a Markov kernel. -/
  [h_policy : ∀ n, IsMarkovKernel (policy n)]
  /-- Distribution of the first action. -/
  p0 : Measure 𝓐
  /-- The first action distribution is a probability measure. -/
  [hp0 : IsProbabilityMeasure p0]

Used by (216)

Actions: Source · Open Issue

`IsAlgEnvSeq`🔗

StructureLearning.IsAlgEnvSeq

Details

An algorithm-environment sequence: a sequence of actions and feedbacks generated by an algorithm interacting with an environment.

structure

Learning.IsAlgEnvSeq.{u_1, u_2, u_3} {𝓐 : Type u_1} {𝓨 : Type u_2}
  {Ω : Type u_3} {m𝓐 : MeasurableSpace 𝓐} {m𝓨 : MeasurableSpace 𝓨}
  {mΩ : MeasurableSpace Ω} (A : ℕ → Ω → 𝓐) (Y : ℕ → Ω → 𝓨)
  (alg : Algorithm 𝓐 𝓨) (env : Environment 𝓐 𝓨)
  (P : MeasureTheory.Measure Ω) [MeasureTheory.IsFiniteMeasure P] : Prop
Learning.IsAlgEnvSeq.{u_1, u_2, u_3}
  {𝓐 : Type u_1} {𝓨 : Type u_2}
  {Ω : Type u_3} {m𝓐 : MeasurableSpace 𝓐}
  {m𝓨 : MeasurableSpace 𝓨}
  {mΩ : MeasurableSpace Ω} (A : ℕ → Ω → 𝓐)
  (Y : ℕ → Ω → 𝓨) (alg : Algorithm 𝓐 𝓨)
  (env : Environment 𝓐 𝓨)
  (P : MeasureTheory.Measure Ω)
  [MeasureTheory.IsFiniteMeasure P] : Prop

Code

structure IsAlgEnvSeq
    (A : ℕ → Ω → 𝓐) (Y : ℕ → Ω → 𝓨) (alg : Algorithm 𝓐 𝓨) (env : Environment 𝓐 𝓨)
    (P : Measure Ω) [IsFiniteMeasure P] : Prop where
  /-- The action sequence is measurable. -/
  measurable_action n : Measurable (A n) := by fun_prop
  /-- The feedback sequence is measurable. -/
  measurable_feedback n : Measurable (Y n) := by fun_prop
  /-- The first action has the correct law. -/
  hasLaw_action_zero : HasLaw (fun ω ↦ (A 0 ω)) alg.p0 P
  /-- The first feedback has the correct conditional distribution. -/
  hasCondDistrib_feedback_zero : HasCondDistrib (Y 0) (A 0) env.ν0 P
  /-- The next action has the correct conditional distribution given the history. -/
  hasCondDistrib_action n :
    HasCondDistrib (A (n + 1)) (history A Y n) (alg.policy n) P
  /-- The next feedback has the correct conditional distribution given the history and
  next action. -/
  hasCondDistrib_feedback n :
    HasCondDistrib (Y (n + 1)) (fun ω ↦ (history A Y n ω, A (n + 1) ω))
      (env.feedback n) P

Type uses (3)

Used by (111)

Actions: Source · Open Issue

`prodLeft`🔗

DefinitionLearning.Algorithm.prodLeft

Details

An algorithm with observations in 𝓧 × 𝓨 obtained from an algorithm with observations in 𝓨 by ignoring the 𝓧 component of each observation.

def

Learning.Algorithm.prodLeft.{u_1, u_2, u_4} {𝓐 : Type u_1}
  {𝓨 : Type u_2} {m𝓐 : MeasurableSpace 𝓐} {m𝓨 : MeasurableSpace 𝓨}
  (𝓧 : Type u_4) [MeasurableSpace 𝓧] (alg : Algorithm 𝓐 𝓨) :
  Algorithm 𝓐 (𝓧 × 𝓨)
Learning.Algorithm.prodLeft.{u_1, u_2,
    u_4}
  {𝓐 : Type u_1} {𝓨 : Type u_2}
  {m𝓐 : MeasurableSpace 𝓐}
  {m𝓨 : MeasurableSpace 𝓨} (𝓧 : Type u_4)
  [MeasurableSpace 𝓧]
  (alg : Algorithm 𝓐 𝓨) :
  Algorithm 𝓐 (𝓧 × 𝓨)

Code

def Algorithm.prodLeft (𝓧 : Type*) [MeasurableSpace 𝓧] (alg : Algorithm 𝓐 𝓨) :
    Algorithm 𝓐 (𝓧 × 𝓨) where
  policy n := (alg.policy n).comap (fun h i ↦ ((h i).1, (h i).2.2)) (by fun_prop)
  p0 := alg.p0

Type uses (1)

Algorithm

Body uses (2)

Used by (6)

Actions: Source · Open Issue

`bayesStationaryEnv`🔗

DefinitionLearning.bayesStationaryEnv

Details

An environment with observations in 𝓔 × 𝓨. The first element e of an observation is sampled from Q once and remains constant. The second element of an observation is sampled from κ (e, a), where a is the corresponding action.

def

Learning.bayesStationaryEnv.{u_1, u_2, u_3} {𝓔 : Type u_1}
  {𝓐 : Type u_2} {𝓨 : Type u_3} [MeasurableSpace 𝓔] [MeasurableSpace 𝓐]
  [MeasurableSpace 𝓨] (Q : MeasureTheory.Measure 𝓔)
  [MeasureTheory.IsProbabilityMeasure Q]
  (κ : ProbabilityTheory.Kernel (𝓔 × 𝓐) 𝓨)
  [ProbabilityTheory.IsMarkovKernel κ] : Environment 𝓐 (𝓔 × 𝓨)
Learning.bayesStationaryEnv.{u_1, u_2,
    u_3}
  {𝓔 : Type u_1} {𝓐 : Type u_2}
  {𝓨 : Type u_3} [MeasurableSpace 𝓔]
  [MeasurableSpace 𝓐] [MeasurableSpace 𝓨]
  (Q : MeasureTheory.Measure 𝓔)
  [MeasureTheory.IsProbabilityMeasure Q]
  (κ : ProbabilityTheory.Kernel (𝓔 × 𝓐) 𝓨)
  [ProbabilityTheory.IsMarkovKernel κ] :
  Environment 𝓐 (𝓔 × 𝓨)

Code

noncomputable
def bayesStationaryEnv (Q : Measure 𝓔) [IsProbabilityMeasure Q] (κ : Kernel (𝓔 × 𝓐) 𝓨)
    [IsMarkovKernel κ] : Environment 𝓐 (𝓔 × 𝓨) where
  feedback n :=
    let g : (Iic n → 𝓐 × 𝓔 × 𝓨) × 𝓐 → 𝓔 × 𝓐 := fun (h, a) => ((h ⟨0, by simp⟩).2.1, a)
    (Kernel.deterministic (Prod.fst ∘ g) (by fun_prop)) ×ₖ (κ.comap g (by fun_prop))
  ν0 := (Kernel.const _ Q) ⊗ₖ κ.swapLeft

Type uses (1)

Environment

Used by (4)

Actions: Source · Open Issue

`IsBayesAlgEnvSeq`🔗

StructureLearning.IsBayesAlgEnvSeq

Details

IsBayesAlgEnvSeq Q κ alg E A Y P states that there is a measure P : Measure Ω such that the parameter E : Ω → 𝓔 has law Q and that the sequences of actions A : ℕ → Ω → 𝓐 and feedbacks Y : ℕ → Ω → 𝓨 are generated by the algorithm alg : Algorithm 𝓐 𝓨 interacting with an underlying environment that depends on E and κ (stationaryEnv (κ.sectR (E ω))).

structure

Learning.IsBayesAlgEnvSeq.{u_1, u_2, u_3, u_4} {𝓔 : Type u_1}
  {𝓐 : Type u_2} {𝓨 : Type u_3} {Ω : Type u_4} [MeasurableSpace 𝓔]
  [MeasurableSpace 𝓐] [MeasurableSpace 𝓨] [MeasurableSpace Ω]
  (Q : MeasureTheory.Measure 𝓔) (κ : ProbabilityTheory.Kernel (𝓔 × 𝓐) 𝓨)
  (alg : Algorithm 𝓐 𝓨) (E : Ω → 𝓔) (A : ℕ → Ω → 𝓐) (Y : ℕ → Ω → 𝓨)
  (P : MeasureTheory.Measure Ω) [MeasureTheory.IsFiniteMeasure P] : Prop
Learning.IsBayesAlgEnvSeq.{u_1, u_2, u_3,
    u_4}
  {𝓔 : Type u_1} {𝓐 : Type u_2}
  {𝓨 : Type u_3} {Ω : Type u_4}
  [MeasurableSpace 𝓔] [MeasurableSpace 𝓐]
  [MeasurableSpace 𝓨] [MeasurableSpace Ω]
  (Q : MeasureTheory.Measure 𝓔)
  (κ : ProbabilityTheory.Kernel (𝓔 × 𝓐) 𝓨)
  (alg : Algorithm 𝓐 𝓨) (E : Ω → 𝓔)
  (A : ℕ → Ω → 𝓐) (Y : ℕ → Ω → 𝓨)
  (P : MeasureTheory.Measure Ω)
  [MeasureTheory.IsFiniteMeasure P] : Prop

Code

structure IsBayesAlgEnvSeq
    (Q : Measure 𝓔) (κ : Kernel (𝓔 × 𝓐) 𝓨) (alg : Algorithm 𝓐 𝓨)
    (E : Ω → 𝓔) (A : ℕ → Ω → 𝓐) (Y : ℕ → Ω → 𝓨)
    (P : Measure Ω) [IsFiniteMeasure P] : Prop where
  measurable_param : Measurable E := by fun_prop
  measurable_action n : Measurable (A n) := by fun_prop
  measurable_feedback n : Measurable (Y n) := by fun_prop
  hasLaw_env : HasLaw E Q P
  hasCondDistrib_action_zero : HasCondDistrib (A 0) E (Kernel.const _ alg.p0) P
  hasCondDistrib_feedback_zero : HasCondDistrib (Y 0) (fun ω ↦ (E ω, A 0 ω)) κ P
  hasCondDistrib_action n :
    HasCondDistrib (A (n + 1)) (fun ω ↦ (E ω, history A Y n ω))
      ((alg.policy n).prodMkLeft _) P
  hasCondDistrib_feedback n :
    HasCondDistrib (Y (n + 1)) (fun ω ↦ (history A Y n ω, E ω, A (n + 1) ω))
      (κ.prodMkLeft _) P

Type uses (2)

Used by (22)

Actions: Source · Open Issue

All dependencies, transitively (4)

`Environment`🔗

StructureLearning.Environment

Details

A stochastic environment.

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 : ℕ) → Kernel ((Iic n → 𝓐 × 𝓨) × 𝓐) 𝓨
  /-- The feedback kernels are Markov kernels. -/
  [h_feedback : ∀ n, IsMarkovKernel (feedback n)]
  /-- Distribution of the first observation given the first action. -/
  ν0 : Kernel 𝓐 𝓨
  /-- The initial observation kernel is a Markov kernel. -/
  [hp0 : IsMarkovKernel ν0]

Used by (128)

Actions: Source · Open Issue

`history`🔗

DefinitionLearning.history

Details

History of the algorithm-environment sequence up to time n.

def

Learning.history.{u_1, u_2, u_3} {𝓐 : Type u_1} {𝓨 : Type u_2}
  {Ω : Type u_3} (A : ℕ → Ω → 𝓐) (Y : ℕ → Ω → 𝓨) (n : ℕ) (ω : Ω) :
  ↥(Finset.Iic n) → 𝓐 × 𝓨
Learning.history.{u_1, u_2, u_3}
  {𝓐 : Type u_1} {𝓨 : Type u_2}
  {Ω : Type u_3} (A : ℕ → Ω → 𝓐)
  (Y : ℕ → Ω → 𝓨) (n : ℕ) (ω : Ω) :
  ↥(Finset.Iic n) → 𝓐 × 𝓨

Code

def history (A : ℕ → Ω → 𝓐) (Y : ℕ → Ω → 𝓨) (n : ℕ) (ω : Ω) : Iic n → 𝓐 × 𝓨 :=
  fun i ↦ (A i ω, Y i ω)

Used by (72)

Actions: Source · Open Issue

`instIsProbabilityMeasureP0`🔗

InstanceLearning.instIsProbabilityMeasureP0

Details

No docstring.

theorem

Learning.instIsProbabilityMeasureP0.{u_1, u_2} {𝓐 : Type u_1}
  {𝓨 : Type u_2} {m𝓐 : MeasurableSpace 𝓐} {m𝓨 : MeasurableSpace 𝓨}
  (alg : Algorithm 𝓐 𝓨) :
  MeasureTheory.IsProbabilityMeasure (Algorithm.p0 alg)
Learning.instIsProbabilityMeasureP0.{u_1,
    u_2}
  {𝓐 : Type u_1} {𝓨 : Type u_2}
  {m𝓐 : MeasurableSpace 𝓐}
  {m𝓨 : MeasurableSpace 𝓨}
  (alg : Algorithm 𝓐 𝓨) :
  MeasureTheory.IsProbabilityMeasure
    (Algorithm.p0 alg)

Code

instance (alg : Algorithm 𝓐 𝓨) : IsProbabilityMeasure alg.p0

Type uses (1)

Algorithm

Used by (13)

Actions: Source · Open Issue

Proof

alg.hp0

`instIsMarkovKernelForallSubtypeNatMemFinsetIicProdPolicy`🔗

InstanceLearning.instIsMarkovKernelForallSubtypeNatMemFinsetIicProdPolicy

Details

No docstring.

theorem

Learning.instIsMarkovKernelForallSubtypeNatMemFinsetIicProdPolicy.{u_1,
    u_2}
  {𝓐 : Type u_1} {𝓨 : Type u_2} {m𝓐 : MeasurableSpace 𝓐}
  {m𝓨 : MeasurableSpace 𝓨} (alg : Algorithm 𝓐 𝓨) (n : ℕ) :
  ProbabilityTheory.IsMarkovKernel (Algorithm.policy alg n)
Learning.instIsMarkovKernelForallSubtypeNatMemFinsetIicProdPolicy.{u_1,
    u_2}
  {𝓐 : Type u_1} {𝓨 : Type u_2}
  {m𝓐 : MeasurableSpace 𝓐}
  {m𝓨 : MeasurableSpace 𝓨}
  (alg : Algorithm 𝓐 𝓨) (n : ℕ) :
  ProbabilityTheory.IsMarkovKernel
    (Algorithm.policy alg n)

Code

instance (alg : Algorithm 𝓐 𝓨) (n : ℕ) : IsMarkovKernel (alg.policy n)

Type uses (1)

Algorithm

Used by (14)

Actions: Source · Open Issue

Proof

alg.h_policy n

Learning.IsAlgEnvSeq.isBayesAlgEnvSeq🔗

isBayesAlgEnvSeq🔗

Algorithm🔗

IsAlgEnvSeq🔗

prodLeft🔗

bayesStationaryEnv🔗

IsBayesAlgEnvSeq🔗

Environment🔗

history🔗

instIsProbabilityMeasureP0🔗

instIsMarkovKernelForallSubtypeNatMemFinsetIicProdPolicy🔗

`Learning.IsAlgEnvSeq.isBayesAlgEnvSeq`🔗

`isBayesAlgEnvSeq`🔗

`Algorithm`🔗

`IsAlgEnvSeq`🔗

`prodLeft`🔗

`bayesStationaryEnv`🔗

`IsBayesAlgEnvSeq`🔗

`Environment`🔗

`history`🔗

`instIsProbabilityMeasureP0`🔗

`instIsMarkovKernelForallSubtypeNatMemFinsetIicProdPolicy`🔗