`Learning.IsObliviousEnv.hasLaw_feedback_cond`🔗

Lemma

From the authors

Conditionally on an event determined by the history before time n and the action at time n, on which that action is equal to b, the feedback at time n has law feedbackCondAction env n b.

Types

𝓞 : Type u_1m𝓞 : MeasurableSpace 𝓞A measurable space is a space equipped with a σ-algebra.
𝓐 : Type u_2m𝓐 : MeasurableSpace 𝓐
𝓨 : Type u_3m𝓨 : MeasurableSpace 𝓨
Ω : Type u_4mΩ : MeasurableSpace Ω

Given

alg : Algorithm 𝓞 𝓐 𝓨A stochastic, sequential algorithm.
env : Environment 𝓞 𝓐 𝓨A stochastic environment.IsObliviousEnv envAn environment is oblivious if the distribution of the next feedback depends only on the last action and not on the past history nor on the current observation.
P : MeasureTheory.Measure ΩA measure is defined to be an outer measure that is countably additive on measurable sets, with the additional assumption that the outer measure is the canonical extension of the restricted measure.MeasureTheory.IsFiniteMeasure PA measure μ is called finite if μ univ < ∞.
O : ℕ → Ω → 𝓞
A : ℕ → Ω → 𝓐
Y : ℕ → Ω → 𝓨
n : ℕ
s : Set ((Hist 𝓞 𝓐 𝓨 n × 𝓞) × 𝓐)A set is a collection of elements of some type α.
b : 𝓐

Assuming

h : IsAlgEnvSeq O A Y alg env PAn algorithm-environment sequence: a sequence of observations, actions and feedbacks generated by an algorithm interacting with an environment.
hs : MeasurableSet sMeasurableSet s means that s is measurable (in the ambient measure space on α)
hsb : ∀ u ∈ s, u.2 = b
hP : P ((fun ω => ((history O A Y n ω, O n ω), A n ω)) ⁻¹' s) ≠ 0

Then

ProbabilityTheory.HasLaw (Y n) ((feedbackCondAction env n) b) P[|(fun ω => ((history O A Y n ω, O n ω), A n ω)) ⁻¹' s]

The predicate HasLaw X μ P registers the fact that the random variable X has law μ under the measure P, in other words that P.map X = μ.

MeasurableSpace : Type u_6 → Type u_6

A measurable space is a space equipped with a σ-algebra.

Learning.Algorithm : (𝓞 : Type u_5) →
  (𝓐 : Type u_6) →
    (𝓨 : Type u_7) → [MeasurableSpace 𝓞] → [MeasurableSpace 𝓐] → [MeasurableSpace 𝓨] → Type (max (max u_5 u_6) u_7)

A stochastic, sequential algorithm.
At each round, it sees an observation in `𝓞`, then takes an action in `𝓐`, and finally receives
feedback in `𝓨`. The action is a random function of the past rounds and the current observation.

Go to its page

Learning.IsObliviousEnv : {𝓞 : Type u_1} →
  {𝓐 : Type u_2} →
    {𝓨 : Type u_3} →
      {m𝓞 : MeasurableSpace 𝓞} → {m𝓐 : MeasurableSpace 𝓐} → {m𝓨 : MeasurableSpace 𝓨} → Learning.Environment 𝓞 𝓐 𝓨 → Prop

An environment is oblivious if the distribution of the next feedback depends only on
the last action and not on the past history nor on the current observation.

Go to its page

Learning.Environment : (𝓞 : Type u_5) →
  (𝓐 : Type u_6) →
    (𝓨 : Type u_7) → [MeasurableSpace 𝓞] → [MeasurableSpace 𝓐] → [MeasurableSpace 𝓨] → Type (max (max u_5 u_6) u_7)

A stochastic environment.
At each round, an observation is drawn prior to the algorithm taking an action. Then the environment
provides feedback based on the observation and the action.

Go to its page

MeasureTheory.IsFiniteMeasure : {α : Type u_1} → {m0 : MeasurableSpace α} → MeasureTheory.Measure α → Prop

A measure `μ` is called finite if `μ univ < ∞`.

MeasureTheory.Measure : (α : Type u_5) → [MeasurableSpace α] → Type u_5

A measure is defined to be an outer measure that is countably additive on
measurable sets, with the additional assumption that the outer measure is the canonical
extension of the restricted measure.

The measure of a set `s`, denoted `μ s`, is an extended nonnegative real. The real-valued version
is written `μ.real s`.

Nat : Type

The natural numbers, starting at zero.

This type is special-cased by both the kernel and the compiler, and overridden with an efficient
implementation. Both use a fast arbitrary-precision arithmetic library (usually
[GMP](https://gmplib.org/)); at runtime, `Nat` values that are sufficiently small are unboxed.

Set : Type u → Type u

A set is a collection of elements of some type `α`.

Although `Set` is defined as `α → Prop`, this is an implementation detail which should not be
relied on. Instead, `Set.ofPred` (also written `{x | p x}`) and membership of a set (`∈`) should be
used to convert between sets and predicates.

Learning.Hist : Type u_5 → Type u_6 → Type u_7 → ℕ → Type (max (max u_7 u_6) u_5)

History of `n` complete rounds; `n = 0` is the empty history.

Go to its page

Prod : Type u → Type v → Type (max u v)

The product type, usually written `α × β`. Product types are also called pair or tuple types.
Elements of this type are pairs in which the first element is an `α` and the second element is a
`β`.

Products nest to the right, so `(x, y, z) : α × β × γ` is equivalent to `(x, (y, z)) : α × (β × γ)`.


Conventions for notations in identifiers:

 * The recommended spelling of `×` in identifiers is `Prod`.

Learning.IsAlgEnvSeq : {𝓞 : Type u_1} →
  {𝓐 : Type u_2} →
    {𝓨 : Type u_3} →
      {Ω : Type u_4} →
        {m𝓞 : MeasurableSpace 𝓞} →
          {m𝓐 : MeasurableSpace 𝓐} →
            {m𝓨 : MeasurableSpace 𝓨} →
              {mΩ : MeasurableSpace Ω} →
                (ℕ → Ω → 𝓞) →
                  (ℕ → Ω → 𝓐) →
                    (ℕ → Ω → 𝓨) →
                      Learning.Algorithm 𝓞 𝓐 𝓨 →…

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

Go to its page

MeasurableSet : {α : Type u_1} → [MeasurableSpace α] → Set α → Prop

`MeasurableSet s` means that `s` is measurable (in the ambient measure space on `α`)

Eq : {α : Sort u_1} → α → α → Prop

The equality relation. It has one introduction rule, `Eq.refl`.
We use `a = b` as notation for `Eq a b`.
A fundamental property of equality is that it is an equivalence relation.
```
variable (α : Type) (a b c d : α)
variable (hab : a = b) (hcb : c = b) (hcd : c = d)

example : a = d :=
  Eq.trans (Eq.trans hab (Eq.symm hcb)) hcd
```
Equality is much more than an equivalence relation, however. It has the important property that every assertion
respects the equivalence, in the sense that we can substitute equal expressions without changing the truth value.
That is, given `h1 : a = b` and `h2 : p a`, we can construct a proof for `p b` using substitution: `Eq.subst h1 h2`.
Example:
```
example (α : Type) (a b : α) (p : α → Prop)
        (h1 : a = b) (h2 : p a) : p b :=
  Eq.subst h1 h2

example (α : Type) (a b : α) (p : α → Prop)
    (h1 : a = b) (h2 : p a) : p b :=
  h1 ▸ h2
```
The triangle in the second presentation is a macro built on top of `Eq.subst` and `Eq.symm`, and you can enter it by typing `\t`.
For more information: [Equality](https://lean-lang.org/theorem_proving_in_lean4/quantifiers_and_equality.html#equality)


Conventions for notations in identifiers:

 * The recommended spelling of `=` in identifiers is `eq`.

Ne : {α : Sort u} → α → α → Prop

`a ≠ b`, or `Ne a b` is defined as `¬ (a = b)` or `a = b → False`,
and asserts that `a` and `b` are not equal.


Conventions for notations in identifiers:

 * The recommended spelling of `≠` in identifiers is `ne`.

Prod.mk : {α : Type u} → {β : Type v} → α → β → α × β

Constructs a pair. This is usually written `(x, y)` instead of `Prod.mk x y`.


Conventions for notations in identifiers:

 * The recommended spelling of `(a, b)` in identifiers is `mk`.

Learning.history : {𝓞 : Type u_1} →
  {𝓐 : Type u_2} →
    {𝓨 : Type u_3} → {Ω : Type u_4} → (ℕ → Ω → 𝓞) → (ℕ → Ω → 𝓐) → (ℕ → Ω → 𝓨) → (n : ℕ) → Ω → Learning.Hist 𝓞 𝓐 𝓨 n

History of the algorithm-environment sequence before time `n`: the rounds at
times `0, ..., n - 1`.

Go to its page

Set.preimage : {α : Type u} → {β : Type v} → (α → β) → Set β → Set α

The preimage of `s : Set β` by `f : α → β`, written `f ⁻¹' s`,
is the set of `x : α` such that `f x ∈ s`.

ProbabilityTheory.HasLaw : {Ω : Type u_1} →
  {𝓧 : Type u_2} →
    {mΩ : MeasurableSpace Ω} →
      {m𝓧 : MeasurableSpace 𝓧} →
        (Ω → 𝓧) → MeasureTheory.Measure 𝓧 → autoParam (MeasureTheory.Measure Ω) ProbabilityTheory.HasLaw._auto_1 → Prop

The predicate `HasLaw X μ P` registers the fact that the random variable `X` has law `μ` under
the measure `P`, in other words that `P.map X = μ`. We also require `X` to be `AEMeasurable`,
to allow for nice interactions with operations on the codomain of `X`. See for instance
`HasLaw.comp`, `IndepFun.hasLaw_mul` and `IndepFun.hasLaw_add`.

Learning.feedbackCondAction : {𝓞 : Type u_1} →
  {𝓐 : Type u_2} →
    {𝓨 : Type u_3} →
      {m𝓞 : MeasurableSpace 𝓞} →
        {m𝓐 : MeasurableSpace 𝓐} →
          {m𝓨 : MeasurableSpace 𝓨} →
            (env : Learning.Environment 𝓞 𝓐 𝓨) →
              [h_obl : Learning.IsObliviousEnv env] → ℕ → ProbabilityTheory.Kernel 𝓐 𝓨

The kernel representing the conditional distribution of the feedback given the action
at time `n` in an oblivious environment.

Go to its page

ProbabilityTheory.cond : {Ω : Type u_1} → {m : MeasurableSpace Ω} → MeasureTheory.Measure Ω → Set Ω → MeasureTheory.Measure Ω

The conditional probability measure of measure `μ` on set `s` is `μ` restricted to `s`
and scaled by the inverse of `μ s` (to make it a probability measure):
`(μ s)⁻¹ • μ.restrict s`.

Code

lemma hasLaw_feedback_cond [IsObliviousEnv env] (h : IsAlgEnvSeq O A Y alg env P) (n : ℕ)
    {s : Set ((Hist 𝓞 𝓐 𝓨 n × 𝓞) × 𝓐)} (hs : MeasurableSet s) {b : 𝓐} (hsb : ∀ u ∈ s, u.2 = b)
    (hP : P ((fun ω ↦ ((history O A Y n ω, O n ω), A n ω)) ⁻¹' s) ≠ 0) :
    HasLaw (Y n) (feedbackCondAction env n b)
      P[|(fun ω ↦ ((history O A Y n ω, O n ω), A n ω)) ⁻¹' s]

Proof

by
  refine (hasCondDistrib_feedback_history_action h n).hasLaw_cond (h.measurable_feedback _) hs
    (fun u hu ↦ ?_) hP
  rw [Kernel.prodMkLeft_apply, hsb u hu]

Meaning last changed in v4.34.0-rc2-76-g565f652 (2026-09-10), the 3th recorded change.

Self-contained, with its dependencies inlined and proofs replaced by sorry: download the raw file · open it in the Lean web editor.

Dependency graph

Audit surface: 8 project declarations, 44 external constants

✓ 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.

Learning.IsObliviousEnv.hasLaw_feedback_cond🔗

`Learning.IsObliviousEnv.hasLaw_feedback_cond`🔗