AFTD Auto-Formalizing Theoretical Domains

prefixHedgeMixedStrategy_weight_eq_hedgeDist

theoremverifiedimported Lean

Prefix Hedge strategy agrees with the abstract Hedge distribution. Let $G$ be a finite two-player zero-sum game with $M \ge 1$ row actions and $N$ column actions, fix a learning rate $\eta \in \bbr$, and let $a_0, \dots, a_{T-1}$ be a sequence of column actions. For any round $t < T$ and any row $i$, the weight assigned to $i$ by the prefix Hedge mixed strategy built from the length-$t$ prefix $a_0, \dots, a_{t-1}$ equals the Hedge distribution value $p_t(i)$ obtained by running abstract Hedge, at the same learning rate $\eta$, on the loss sequence $\ell$ induced by $G$ and $a$, namely $\ell_s(i) = 1 - A_{i, a_s}$. In symbols, both sides equal $w_t(i)/\Phi_t$, where $w_t(i) = \exp(-\eta \sum_{s<t}(1 - A_{i,a_s}))$ and $\Phi_t = \sum_{k} w_t(k)$.

Statement

set_option relaxedAutoImplicit false in
set_option autoImplicit false in
open Real Finset BigOperators in
lemma prefixHedgeMixedStrategy_weight_eq_hedgeDist {M N T : ℕ} [NeZero M]
    (G : ZeroSumGame M N) (η : ℝ) (actions : Fin T → Fin N) (t : Fin T) (i : Fin M) :
    (prefixHedgeMixedStrategy G η
        (t := t.val) (fun s : Fin t.val => actions ⟨s.val, lt_trans s.isLt t.isLt⟩)).weights i =
      hedgeDist η (G.toLossSeq actions) t.val i
Source
TCSlib, `prefixHedgeMixedStrategy_weight_eq_hedgeDist`
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.
Verified
07 Oct 2026
Axioms
Classical.choiceQuot.soundpropext
Built on 7
  • 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…
  • prefixHedgeWeight_eq_hedgeWeightPrefix Hedge weight agrees with the induced-loss Hedge weight. Let $G$ be a finite two-player zero-sum game with $M$ row actions and $N$…
  • hedgeDistThe Hedge distribution at round $t$ is the normalization of the weight vector: \[ p_t(i) \;=\; \frac{w_t(i)}{W_t}. \]
  • prefixPotential_eq_potentialPrefix potential equals the induced Hedge potential. Let $G$ be a finite two-player zero-sum game with payoff matrix $A$ having $M$ rows…
  • ZeroSumGame.toLossSeqGiven a game $G$ and a sequence of column responses $j_0, \dots, j_{T-1}$, the induced loss sequence for the row player is…
  • prefixHedgeMixedStrategyThe normalised Hedge distribution after a prefix of $t$ column actions is the mixed row strategy with weights…
Used by 1
  • 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…

Lean source view module on GitHub

set_option relaxedAutoImplicit false inset_option autoImplicit false inopen Real Finset BigOperators in/-- The weights of the prefix Hedge mixed strategy over the first `t` actions equal `hedgeDist` at time `t` of the induced loss sequence. -/lemma prefixHedgeMixedStrategy_weight_eq_hedgeDist {M N T : ℕ} [NeZero M]    (G : ZeroSumGame M N) (η : ℝ) (actions : Fin T → Fin N) (t : Fin T) (i : Fin M) :    (prefixHedgeMixedStrategy G η        (t := t.val) (fun s : Fin t.val => actions ⟨s.val, lt_trans s.isLt t.isLt⟩)).weights i =      hedgeDist η (G.toLossSeq actions) t.val i := by  simp only [prefixHedgeMixedStrategy, hedgeDist]  rw [prefixHedgeWeight_eq_hedgeWeight, prefixPotential_eq_potential]
See it in the graphDiscuss this resultChallenge it