hedgeResponseNat
defimported Lean
The sequence of column best responses generated online against Hedge: at time $t$, given the history $a_0, \dots, a_{t-1}$ of prior column choices, the column player responds with $a_t = \mathrm{bestColumn}(G, p_t)$, where $p_t$ is the prefix Hedge mixed strategy. This is defined by well-founded recursion on $t$.
Statement
set_option relaxedAutoImplicit false in set_option autoImplicit false in open Real Finset BigOperators in noncomputable def hedgeResponseNat {M N : ℕ} [NeZero M] [NeZero N] (G : ZeroSumGame M N) (η : ℝ) : ℕ → Fin N
- Defined in
- TCSlib, `hedgeResponseNat`
- 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.hedgeResponseNat← hedgeResponseNat (TCSlib/LearningTheory/Minimax/HedgeInteraction.lean:257): verbatim
- Verified
- 07 Oct 2026
- Axioms
- none listed
- Built on 3
- bestColumnGiven a game $G$ and a mixed row strategy $p$,
bestColumnis the pure column $j^* \in \mathrm{Fin}\,N$ that minimises… - ZeroSumGameA finite two-player zero-sum game with $M$ row actions and $N$ column actions is a record consisting of a payoff matrix…
- prefixHedgeMixedStrategyThe normalised Hedge distribution after a prefix of $t$ column actions is the mixed row strategy with weights…
- bestColumnGiven a game $G$ and a mixed row strategy $p$,
- Used by 2
- hedgeResponseNat_isBestResponseOnline column response is a best response. Let $G$ be a finite zero-sum game with $M \ge 1$ row actions and $N \ge 1$ column actions, let…
- hedge_constructionHedge yields an approximate minimax pair. Let $G$ be a finite two-player zero-sum game with $M \ge 2$ row actions and $N \ge 1$ column…
Lean source view module on GitHub
set_option relaxedAutoImplicit false in set_option autoImplicit false in open Real Finset BigOperators in /-- The column responses generated online against Hedge: at time `t`, the history consists of the earlier responses `s < t`; Hedge forms its mixed row strategy from that prefix, and the column player plays a pure best response (`bestColumn`) to that mixed strategy. Defined by well-founded recursion on `t`. [FS99, §5, Eq. (10) (the column player plays a best response to the row's multiplicative-weights distribution)]; [CBL06, proof of Thm 7.1]. -/ noncomputable def hedgeResponseNat {M N : ℕ} [NeZero M] [NeZero N] (G : ZeroSumGame M N) (η : ℝ) : ℕ → Fin N | t => bestColumn G (prefixHedgeMixedStrategy G η (t := t) (fun s : Fin t => hedgeResponseNat G η s.val)) termination_by t => t decreasing_by exact s.isLt