OnlineLearning.finiteUpperValue
defimported Lean
The upper value of $G$ is \[ v^+(G) \;=\; \inf_{q \in \Delta_N}\; \sup_{i \in [M]}\; \mathrm{pureVsPayoff}(G,i,q), \] where the column player minimises over mixed strategies and the row player maximises over pure responses.
Statement
set_option relaxedAutoImplicit false in set_option autoImplicit false in open Real Finset BigOperators in noncomputable def OnlineLearning.finiteUpperValue {M N : ℕ} (G : ZeroSumGame M N) : ℝ
- Defined in
- TCSlib, `OnlineLearning.finiteUpperValue`
- Lean proof
- By Karim Abdel Sadek, Mark Bedaywi, from github.com/Shilun-Allan-Li/tcslib at
c8a02591b1e5(Copyright (c) 2026 Karim Abdel Sadek and Mark Bedaywi. All rights reserved, Apache-2.0). Compiled here against leanprover/lean4:v4.33.1, Mathlib v4.33.1; written for leanprover/lean4:v4.25.0.OnlineLearning.finiteUpperValue← OnlineLearning.finiteUpperValue (TCSlib/LearningTheory/Minimax/ConvexMinimaxCore.lean:92): verbatim
- Verified
- 07 Oct 2026
- Axioms
- none listed
- Built on 3
- pureVsPayoffGiven a game $G$, a pure row $i$, and a mixed column strategy $q$, the expected payoff of row $i$ against $q$ is…
- MixedStrategyA mixed strategy over $n$ actions is a record consisting of a weight function $w : \mathrm{Fin}\,n \to \mathbb{R}$ together with…
- ZeroSumGameA finite two-player zero-sum game with $M$ row actions and $N$ column actions is a record consisting of a payoff matrix…
- Used by 2
- OnlineLearning.finite_minimax_valueMinimax theorem for finite zero-sum games. Let $G$ be a finite two-player zero-sum game with $M$ row actions and $N$ column actions, whose…
- OnlineLearning.finiteLowerValue_le_upperValueWeak duality for finite zero-sum games. Let $G$ be a finite two-player zero-sum game with $M \geq 1$ row actions and $N \geq 1$ column…
Lean source view module on GitHub
set_option relaxedAutoImplicit false in set_option autoImplicit false in open Real Finset BigOperators in /-- The upper value of a finite zero-sum game: the infimum over column mixed strategies `q` of the supremum over pure rows `i` of the payoff of `i` against `q` (column commits to a mixed strategy, then row chooses the best pure response). [CBL06, §7.2]. -/ noncomputable def OnlineLearning.finiteUpperValue {M N : ℕ} (G : ZeroSumGame M N) : ℝ := ⨅ q : MixedStrategy N, ⨆ i : Fin M, pureVsPayoff G i q