import Mathlib.MeasureTheory.Order.Lattice
import Mathlib.Probability.Kernel.IonescuTulcea.Traj
import Mathlib.Probability.Process.FiniteDimensionalLaws
import Mathlib.Probability.HasCondDistrib
import Mathlib.MeasureTheory.Measure.ProbabilityMeasure
import Mathlib.Probability.Independence.Basic
import Mathlib.Probability.Independence.Conditional
import Mathlib.MeasureTheory.Measure.SubFinite
import Mathlib.Probability.Kernel.RadonNikodym
import Mathlib.Analysis.Normed.Ring.Basic
import Mathlib.MeasureTheory.Constructions.BorelSpace.Basic
import Mathlib.Probability.Kernel.Composition.MapComap
import Mathlib.Probability.Kernel.Basic

/-! # Standalone extraction for `Learning.instIsDeterministicEnvOnlineEvalEnv`
Definitions are copied verbatim; theorem proofs are replaced by `sorry`.
Auto-generated by Referee. -/

set_option quotPrecheck false

-- Namespace stubs (so later `open`s resolve).
namespace Finset
end Finset
namespace MeasureTheory
end MeasureTheory
namespace ProbabilityTheory
end ProbabilityTheory
namespace ENNReal
end ENNReal
namespace Learning
end Learning

-- ═══ ForMathlib.MeasureTheory.Order.Lattice ═══
section
open Finset
variable {α δ : Type*} [MeasurableSpace δ] [SemilatticeInf α] {m : MeasurableSpace α} [MeasurableInf₂ α]
attribute [to_dual existing] MeasurableInf₂
end

-- ═══ SequentialLearning.Algorithm ═══
section
open MeasureTheory ProbabilityTheory Filter Real Finset
open scoped ENNReal NNReal
namespace Learning
variable {𝓐 𝓨 Ω : Type*} {m𝓐 : MeasurableSpace 𝓐} {m𝓨 : MeasurableSpace 𝓨} {mΩ : MeasurableSpace Ω}

/-- A stochastic environment. -/
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]

end Learning
end

-- ═══ SequentialLearning.StationaryEnv ═══
section
open MeasureTheory ProbabilityTheory Filter Real Finset
open scoped ENNReal NNReal
namespace Learning
variable {𝓐 𝓨 : Type*} {m𝓐 : MeasurableSpace 𝓐} {m𝓨 : MeasurableSpace 𝓨}

/-- An oblivious environment, in which the distribution of the next feedback depends only on
the last action, but in a possibly time-dependent manner. -/
@[simps]
def obliviousEnv (ν : ℕ → Kernel 𝓐 𝓨) [∀ n, IsMarkovKernel (ν n)] : Environment 𝓐 𝓨 where
  feedback n := (ν (n + 1)).prodMkLeft _
  ν0 := ν 0

variable {Ω : Type*} {mΩ : MeasurableSpace Ω} {ν : Kernel 𝓐 𝓨} [IsMarkovKernel ν] {P : Measure Ω} [IsProbabilityMeasure P] {A : ℕ → Ω → 𝓐} {Y : ℕ → Ω → 𝓨}
end Learning
end

-- ═══ SequentialLearning.Deterministic ═══
section
open MeasureTheory ProbabilityTheory Filter Real Finset
open scoped ENNReal NNReal
namespace Learning
variable {𝓐 𝓨 : Type*} {m𝓐 : MeasurableSpace 𝓐} {m𝓨 : MeasurableSpace 𝓨}

/-- An environment is deterministic if its initial feedbacks are determined by
measurable functions (and not possibly random kernels). -/
class IsDeterministicEnv (env : Environment 𝓐 𝓨) : Prop where
  exists_f0 : ∃ (f0 : 𝓐 → 𝓨) (hf0 : Measurable f0), env.ν0 = Kernel.deterministic f0 hf0
  exists_f : ∀ n, ∃ (f : ((Iic n → 𝓐 × 𝓨) × 𝓐) → 𝓨) (hf : Measurable f),
    env.feedback n = Kernel.deterministic f hf

variable {nextA : (n : ℕ) → (Iic n → 𝓐 × 𝓨) → 𝓐} {h_next : ∀ n, Measurable (nextA n)} {action0 : 𝓐} {env : Environment 𝓐 𝓨} {f0 : 𝓐 → 𝓨} {hf0 : Measurable f0} {f : (n : ℕ) → ((Iic n → 𝓐 × 𝓨) × 𝓐) → 𝓨} {hf : ∀ n, Measurable (f n)}
end Learning
end

-- ═══ SequentialLearning.EvaluationEnv ═══
section
open MeasureTheory ProbabilityTheory
namespace Learning
variable {𝓐 𝓨 : Type*} {m𝓐 : MeasurableSpace 𝓐} {m𝓨 : MeasurableSpace 𝓨} {g : ℕ → 𝓐 → 𝓨} {hg : ∀ n, Measurable (g n)} {f : 𝓐 → 𝓨} {hf : Measurable f}

/-- The evaluation environment where the feedback is given by evaluating a fixed measurable function
`f` at the chosen action. -/
noncomputable def onlineEvalEnv (g : ℕ → 𝓐 → 𝓨) (hg : ∀ n, Measurable (g n)) :=
  obliviousEnv (fun n ↦ Kernel.deterministic (g n) (hg n))

instance : IsDeterministicEnv (onlineEvalEnv g hg) where
  exists_f0 := ⟨g 0, hg 0, rfl⟩
  exists_f n := ⟨fun p ↦ g (n + 1) p.2, sorry, rfl⟩

end Learning
end