LeanMachineLearning exposition

Learning.IsDeterministicEnv.hasCondDistrib_feedback_zero๐Ÿ”—

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

hasCondDistrib_feedback_zero๐Ÿ”—

LemmaLearning.IsDeterministicEnv.hasCondDistrib_feedback_zero
Details

No docstring.

๐Ÿ”—theorem
Learning.IsDeterministicEnv.hasCondDistrib_feedback_zero.{u_1, u_2, u_3}
  {๐“ : Type u_1} {๐“จ : Type u_2} {m๐“ : MeasurableSpace ๐“}
  {m๐“จ : MeasurableSpace ๐“จ} {ฮฉ : Type u_3} {mฮฉ : MeasurableSpace ฮฉ}
  {alg : Algorithm ๐“ ๐“จ} {env : Environment ๐“ ๐“จ}
  {P : MeasureTheory.Measure ฮฉ} [MeasureTheory.IsFiniteMeasure P]
  {A : โ„• โ†’ ฮฉ โ†’ ๐“} {Y : โ„• โ†’ ฮฉ โ†’ ๐“จ} [h_det : IsDeterministicEnv env]
  (h : IsAlgEnvSeq A Y alg env P) :
  ProbabilityTheory.HasCondDistrib (Y 0) (A 0)
    (ProbabilityTheory.Kernel.deterministic (feedbackFunZero env) โ‹ฏ) P
Learning.IsDeterministicEnv.hasCondDistrib_feedback_zero.{u_1,
    u_2, u_3}
  {๐“ : Type u_1} {๐“จ : Type u_2}
  {m๐“ : MeasurableSpace ๐“}
  {m๐“จ : MeasurableSpace ๐“จ} {ฮฉ : Type u_3}
  {mฮฉ : MeasurableSpace ฮฉ}
  {alg : Algorithm ๐“ ๐“จ}
  {env : Environment ๐“ ๐“จ}
  {P : MeasureTheory.Measure ฮฉ}
  [MeasureTheory.IsFiniteMeasure P]
  {A : โ„• โ†’ ฮฉ โ†’ ๐“} {Y : โ„• โ†’ ฮฉ โ†’ ๐“จ}
  [h_det : IsDeterministicEnv env]
  (h : IsAlgEnvSeq A Y alg env P) :
  ProbabilityTheory.HasCondDistrib (Y 0)
    (A 0)
    (ProbabilityTheory.Kernel.deterministic
      (feedbackFunZero env) โ‹ฏ)
    P

Code

lemma hasCondDistrib_feedback_zero [h_det : IsDeterministicEnv env]
    (h : IsAlgEnvSeq A Y alg env P) :
    HasCondDistrib (Y 0) (A 0)
      (Kernel.deterministic (feedbackFunZero env) (measurable_feedbackFunZero env)) P
Type uses (6)
Body uses (1)

Actions: Source ยท Open Issue

Proof
by
  rw [โ† ฮฝ0_eq_deterministic]
  exact h.hasCondDistrib_feedback_zero

Dependency graph

Type dependencies (6)

Algorithm๐Ÿ”—

StructureLearning.Algorithm
Details

A stochastic, sequential algorithm.

๐Ÿ”—structure
Learning.Algorithm.{u_4, u_5} (๐“ : Type u_4) (๐“จ : Type u_5)
  [MeasurableSpace ๐“] [MeasurableSpace ๐“จ] : Type (max u_4 u_5)
Learning.Algorithm.{u_4, u_5}
  (๐“ : Type u_4) (๐“จ : Type u_5)
  [MeasurableSpace ๐“]
  [MeasurableSpace ๐“จ] : Type (max u_4 u_5)

Code

structure Algorithm (๐“ ๐“จ : Type*) [MeasurableSpace ๐“] [MeasurableSpace ๐“จ] where
  /-- Policy or sampling rule: distribution of the next action. -/
  policy : (n : โ„•) โ†’ Kernel (Iic n โ†’ ๐“ ร— ๐“จ) ๐“
  /-- The policy is a Markov kernel. -/
  [h_policy : โˆ€ n, IsMarkovKernel (policy n)]
  /-- Distribution of the first action. -/
  p0 : Measure ๐“
  /-- The first action distribution is a probability measure. -/
  [hp0 : IsProbabilityMeasure p0]
Used by (216)

Actions: Source ยท Open Issue

Environment๐Ÿ”—

StructureLearning.Environment
Details

A stochastic environment.

๐Ÿ”—structure
Learning.Environment.{u_4, u_5} (๐“ : Type u_4) (๐“จ : Type u_5)
  [MeasurableSpace ๐“] [MeasurableSpace ๐“จ] : Type (max u_4 u_5)
Learning.Environment.{u_4, u_5}
  (๐“ : Type u_4) (๐“จ : Type u_5)
  [MeasurableSpace ๐“]
  [MeasurableSpace ๐“จ] : Type (max u_4 u_5)

Code

structure Environment (๐“ ๐“จ : Type*) [MeasurableSpace ๐“] [MeasurableSpace ๐“จ] where
  /-- Distribution of the next observation as function of the past history. -/
  feedback : (n : โ„•) โ†’ Kernel ((Iic n โ†’ ๐“ ร— ๐“จ) ร— ๐“) ๐“จ
  /-- The feedback kernels are Markov kernels. -/
  [h_feedback : โˆ€ n, IsMarkovKernel (feedback n)]
  /-- Distribution of the first observation given the first action. -/
  ฮฝ0 : Kernel ๐“ ๐“จ
  /-- The initial observation kernel is a Markov kernel. -/
  [hp0 : IsMarkovKernel ฮฝ0]
Used by (128)

Actions: Source ยท Open Issue

IsDeterministicEnv๐Ÿ”—

Type ClassLearning.IsDeterministicEnv
Details

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

๐Ÿ”—type class
Learning.IsDeterministicEnv.{u_1, u_2} {๐“ : Type u_1} {๐“จ : Type u_2}
  {m๐“ : MeasurableSpace ๐“} {m๐“จ : MeasurableSpace ๐“จ}
  (env : Environment ๐“ ๐“จ) : Prop
Learning.IsDeterministicEnv.{u_1, u_2}
  {๐“ : Type u_1} {๐“จ : Type u_2}
  {m๐“ : MeasurableSpace ๐“}
  {m๐“จ : MeasurableSpace ๐“จ}
  (env : Environment ๐“ ๐“จ) : Prop

Code

class IsDeterministicEnv (env : Environment ๐“ ๐“จ) : Prop where
  exists_f0 : โˆƒ (f0 : ๐“ โ†’ ๐“จ) (hf0 : Measurable f0), env.ฮฝ0 = Kernel.deterministic f0 hf0
  exists_f : โˆ€ n, โˆƒ (f : ((Iic n โ†’ ๐“ ร— ๐“จ) ร— ๐“) โ†’ ๐“จ) (hf : Measurable f),
    env.feedback n = Kernel.deterministic f hf
Type uses (1)
Used by (11)

Actions: Source ยท Open Issue

IsAlgEnvSeq๐Ÿ”—

StructureLearning.IsAlgEnvSeq
Details

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

๐Ÿ”—structure
Learning.IsAlgEnvSeq.{u_1, u_2, u_3} {๐“ : Type u_1} {๐“จ : Type u_2}
  {ฮฉ : Type u_3} {m๐“ : MeasurableSpace ๐“} {m๐“จ : MeasurableSpace ๐“จ}
  {mฮฉ : MeasurableSpace ฮฉ} (A : โ„• โ†’ ฮฉ โ†’ ๐“) (Y : โ„• โ†’ ฮฉ โ†’ ๐“จ)
  (alg : Algorithm ๐“ ๐“จ) (env : Environment ๐“ ๐“จ)
  (P : MeasureTheory.Measure ฮฉ) [MeasureTheory.IsFiniteMeasure P] : Prop
Learning.IsAlgEnvSeq.{u_1, u_2, u_3}
  {๐“ : Type u_1} {๐“จ : Type u_2}
  {ฮฉ : Type u_3} {m๐“ : MeasurableSpace ๐“}
  {m๐“จ : MeasurableSpace ๐“จ}
  {mฮฉ : MeasurableSpace ฮฉ} (A : โ„• โ†’ ฮฉ โ†’ ๐“)
  (Y : โ„• โ†’ ฮฉ โ†’ ๐“จ) (alg : Algorithm ๐“ ๐“จ)
  (env : Environment ๐“ ๐“จ)
  (P : MeasureTheory.Measure ฮฉ)
  [MeasureTheory.IsFiniteMeasure P] : Prop

Code

structure IsAlgEnvSeq
    (A : โ„• โ†’ ฮฉ โ†’ ๐“) (Y : โ„• โ†’ ฮฉ โ†’ ๐“จ) (alg : Algorithm ๐“ ๐“จ) (env : Environment ๐“ ๐“จ)
    (P : Measure ฮฉ) [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 ฯ‰ โ†ฆ (A 0 ฯ‰)) alg.p0 P
  /-- The first feedback has the correct conditional distribution. -/
  hasCondDistrib_feedback_zero : HasCondDistrib (Y 0) (A 0) env.ฮฝ0 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 ฯ‰ โ†ฆ (history A Y n ฯ‰, A (n + 1) ฯ‰))
      (env.feedback n) P
Type uses (3)
Used by (111)

Actions: Source ยท Open Issue

feedbackFunZero๐Ÿ”—

DefinitionLearning.feedbackFunZero
Details

The initial feedback function of a deterministic environment.

๐Ÿ”—def
Learning.feedbackFunZero.{u_1, u_2} {๐“ : Type u_1} {๐“จ : Type u_2}
  {m๐“ : MeasurableSpace ๐“} {m๐“จ : MeasurableSpace ๐“จ}
  (env : Environment ๐“ ๐“จ) [h_det : IsDeterministicEnv env] : ๐“ โ†’ ๐“จ
Learning.feedbackFunZero.{u_1, u_2}
  {๐“ : Type u_1} {๐“จ : Type u_2}
  {m๐“ : MeasurableSpace ๐“}
  {m๐“จ : MeasurableSpace ๐“จ}
  (env : Environment ๐“ ๐“จ)
  [h_det : IsDeterministicEnv env] : ๐“ โ†’ ๐“จ

Code

noncomputable
def feedbackFunZero (env : Environment ๐“ ๐“จ) [h_det : IsDeterministicEnv env] : ๐“ โ†’ ๐“จ :=
  h_det.exists_f0.choose
Type uses (2)
Used by (6)

Actions: Source ยท Open Issue

measurable_feedbackFunZero๐Ÿ”—

LemmaLearning.measurable_feedbackFunZero
Details

No docstring.

๐Ÿ”—theorem
Learning.measurable_feedbackFunZero.{u_1, u_2} {๐“ : Type u_1}
  {๐“จ : Type u_2} {m๐“ : MeasurableSpace ๐“} {m๐“จ : MeasurableSpace ๐“จ}
  (env : Environment ๐“ ๐“จ) [IsDeterministicEnv env] :
  Measurable (feedbackFunZero env)
Learning.measurable_feedbackFunZero.{u_1,
    u_2}
  {๐“ : Type u_1} {๐“จ : Type u_2}
  {m๐“ : MeasurableSpace ๐“}
  {m๐“จ : MeasurableSpace ๐“จ}
  (env : Environment ๐“ ๐“จ)
  [IsDeterministicEnv env] :
  Measurable (feedbackFunZero env)

Code

lemma measurable_feedbackFunZero (env : Environment ๐“ ๐“จ) [IsDeterministicEnv env] :
    Measurable (feedbackFunZero env)
Type uses (3)
Used by (4)

Actions: Source ยท Open Issue

Proof
(IsDeterministicEnv.exists_f0).choose_spec.choose

All dependencies, transitively (1)

history๐Ÿ”—

DefinitionLearning.history
Details

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

๐Ÿ”—def
Learning.history.{u_1, u_2, u_3} {๐“ : Type u_1} {๐“จ : Type u_2}
  {ฮฉ : Type u_3} (A : โ„• โ†’ ฮฉ โ†’ ๐“) (Y : โ„• โ†’ ฮฉ โ†’ ๐“จ) (n : โ„•) (ฯ‰ : ฮฉ) :
  โ†ฅ(Finset.Iic n) โ†’ ๐“ ร— ๐“จ
Learning.history.{u_1, u_2, u_3}
  {๐“ : Type u_1} {๐“จ : Type u_2}
  {ฮฉ : Type u_3} (A : โ„• โ†’ ฮฉ โ†’ ๐“)
  (Y : โ„• โ†’ ฮฉ โ†’ ๐“จ) (n : โ„•) (ฯ‰ : ฮฉ) :
  โ†ฅ(Finset.Iic n) โ†’ ๐“ ร— ๐“จ

Code

def history (A : โ„• โ†’ ฮฉ โ†’ ๐“) (Y : โ„• โ†’ ฮฉ โ†’ ๐“จ) (n : โ„•) (ฯ‰ : ฮฉ) : Iic n โ†’ ๐“ ร— ๐“จ :=
  fun i โ†ฆ (A i ฯ‰, Y i ฯ‰)
Used by (72)

Actions: Source ยท Open Issue