Learning.IT.fst_comp_step
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.
fst_comp_step๐
Learning.IT.fst_comp_stepNo docstring.
Learning.IT.fst_comp_step.{u_1, u_2} {๐ : Type u_1} {๐จ : Type u_2} (n : โ) : Prod.fst โ step n = action nLearning.IT.fst_comp_step.{u_1, u_2} {๐ : Type u_1} {๐จ : Type u_2} (n : โ) : Prod.fst โ step n = action n
Code
lemma fst_comp_step (n : โ) : Prod.fst โ step (๐
Used by (2)
Actions: Source ยท Open Issue
Proof
๐) (๐จ := ๐จ) n = action n := rfl
Dependency graph
Type dependencies (2)
step๐
Learning.IT.step
Action and feedback at step n.
Learning.IT.step.{u_1, u_2} {๐ : Type u_1} {๐จ : Type u_2} (n : โ) (h : โ โ ๐ ร ๐จ) : ๐ ร ๐จLearning.IT.step.{u_1, u_2} {๐ : Type u_1} {๐จ : Type u_2} (n : โ) (h : โ โ ๐ ร ๐จ) : ๐ ร ๐จ
Code
def step (n : โ) (h : โ โ ๐ ร ๐จ) : ๐ ร ๐จ := h n
Used by (13)
Actions: Source ยท Open Issue
action๐
Learning.IT.action
action n is the action pulled at time n. This is a random variable on the measurable space
โ โ ๐ ร ๐จ.
Learning.IT.action.{u_1, u_2} {๐ : Type u_1} {๐จ : Type u_2} (n : โ) (h : โ โ ๐ ร ๐จ) : ๐Learning.IT.action.{u_1, u_2} {๐ : Type u_1} {๐จ : Type u_2} (n : โ) (h : โ โ ๐ ร ๐จ) : ๐
Code
def action (n : โ) (h : โ โ ๐ ร ๐จ) : ๐ := (h n).1
Actions: Source ยท Open Issue