Bandits.ArrayModel.stepsUntil_congr
No docstring.
Bandits.ArrayModel.stepsUntil_congr.{u_1, u_2} {π : Type u_1} {R : Type u_2} {mπ : MeasurableSpace π} {mR : MeasurableSpace R} [Nonempty π] [StandardBorelSpace π] [DecidableEq π] (alg : Learning.Algorithm π R) (a : π) (m n : β) {Ο Ο' : probSpace π R} (hΟ1 : β (i : β), Prod.fst Ο i = Prod.fst Ο' i) (hΟ2_ne : β (i : β) (b : π), b β a β Prod.snd Ο i b = Prod.snd Ο' i b) (hΟ2_eq : β (i : β), i + 1 β€ m β Prod.snd Ο i a = Prod.snd Ο' i a) : action alg (n + 1) Ο = a β§ Learning.pullCount (action alg) a (n + 1) Ο = m β action alg (n + 1) Ο' = a β§ Learning.pullCount (action alg) a (n + 1) Ο' = mBandits.ArrayModel.stepsUntil_congr.{u_1, u_2} {π : Type u_1} {R : Type u_2} {mπ : MeasurableSpace π} {mR : MeasurableSpace R} [Nonempty π] [StandardBorelSpace π] [DecidableEq π] (alg : Learning.Algorithm π R) (a : π) (m n : β) {Ο Ο' : probSpace π R} (hΟ1 : β (i : β), Prod.fst Ο i = Prod.fst Ο' i) (hΟ2_ne : β (i : β) (b : π), b β a β Prod.snd Ο i b = Prod.snd Ο' i b) (hΟ2_eq : β (i : β), i + 1 β€ m β Prod.snd Ο i a = Prod.snd Ο' i a) : action alg (n + 1) Ο = a β§ Learning.pullCount (action alg) a (n + 1) Ο = m β action alg (n + 1) Ο' = a β§ Learning.pullCount (action alg) a (n + 1) Ο' = m
Code
lemma stepsUntil_congr (alg : Algorithm π R) (a : π) (m n : β) {Ο Ο' : probSpace π R}
(hΟ1 : β i, Ο.1 i = Ο'.1 i) (hΟ2_ne : β i b, b β a β Ο.2 i b = Ο'.2 i b)
(hΟ2_eq : β i, i + 1 β€ m β Ο.2 i a = Ο'.2 i a) :
(action alg (n + 1) Ο = a β§ pullCount (action alg) a (n + 1) Ο = m) β
(action alg (n + 1) Ο' = a β§ pullCount (action alg) a (n + 1) Ο' = m)Proof
β¨stepsUntil_congr_aux alg a m n hΟ1 hΟ2_ne hΟ2_eq,
stepsUntil_congr_aux alg a m n (by grind) (by grind) (by grind)β©Actions: Source Β· Open Issue
Meaning last changed in v4.34.0-rc2-1-g439785b (2026-08-23), the 5th recorded change.
Self-contained, with its dependencies inlined and proofs replaced by sorry: download the raw file Β· open it in the Lean web editor.
Dependency graph
Audit surface: 10 project declarations, 78 external constants
β 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.