prefixHedgeMixedStrategy
defimported Lean
The normalised Hedge distribution after a prefix of $t$ column actions is the mixed row strategy with weights \[ p_t(i) \;=\; \frac{w_t(i)}{\Phi_t}, \] where $w_t(i)$ is the prefix Hedge weight and $\Phi_t$ the prefix potential.
Statement
set_option relaxedAutoImplicit false in set_option autoImplicit false in open Real Finset BigOperators in noncomputable def prefixHedgeMixedStrategy {M N : ℕ} [NeZero M] (G : ZeroSumGame M N) (η : ℝ) {t : ℕ} (actions : Fin t → Fin N) : MixedStrategy M
- Defined in
- TCSlib, `prefixHedgeMixedStrategy`
- 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.prefixHedgeMixedStrategy← prefixHedgeMixedStrategy (TCSlib/LearningTheory/Minimax/HedgeInteraction.lean:242): verbatim
- Verified
- 07 Oct 2026
- Axioms
- none listed
- Built on 6
- MixedStrategyA mixed strategy over $n$ actions is a record consisting of a weight function $w : \mathrm{Fin}\,n \to \mathbb{R}$ together with…
- prefixPotentialThe prefix potential is the sum of prefix Hedge weights over all rows: \[ \Phi_t \;=\; \sum_{i \in \mathrm{Fin}\,M} w_t(i). \]
- ZeroSumGameA finite two-player zero-sum game with $M$ row actions and $N$ column actions is a record consisting of a payoff matrix…
- prefixHedgeWeightThe unnormalised Hedge weight of row $i$ after seeing a prefix of column actions at learning rate $\eta$ is…
- prefixHedgeWeight_posPositivity of the prefix Hedge weight. Let $G$ be a finite two-player zero-sum game with $M$ row actions and $N$ column actions, let…
- prefixPotential_posPositivity of the prefix potential. Let $G$ be a finite two-player zero-sum game with at least one row action, fix a learning rate…
- Used by 3
- 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…
- hedgeResponseNatThe sequence of column best responses generated online against Hedge: at time $t$, given the history $a_0, \dots, a_{t-1}$ of prior column…
- prefixHedgeMixedStrategy_weight_eq_hedgeDistPrefix Hedge strategy agrees with the abstract Hedge distribution. Let $G$ be a finite two-player zero-sum game with $M \ge 1$ row actions…
Lean source view module on GitHub
set_option relaxedAutoImplicit false in set_option autoImplicit false in open Real Finset BigOperators in /-- The row player's Hedge mixed strategy after seeing a prefix of column actions: row `i` gets weight `prefixHedgeWeight i / prefixPotential`. -/ noncomputable def prefixHedgeMixedStrategy {M N : ℕ} [NeZero M] (G : ZeroSumGame M N) (η : ℝ) {t : ℕ} (actions : Fin t → Fin N) : MixedStrategy M where weights i := prefixHedgeWeight G η actions i / prefixPotential G η actions nonneg i := div_nonneg (prefixHedgeWeight_pos G η actions i).le (prefixPotential_pos G η actions).le sum_one := by rw [← Finset.sum_div] exact div_self (ne_of_gt (prefixPotential_pos G η actions))