跳到正文
研踪PaperTrail
← 研踪 PaperTrail

arXiv:2611.22977 · v1

A Common Exponential Lower Bound for Dantzig and Modified Simplex in Deterministic Discounted Games

首次提交 2026-11-17 23:58
版本更新 2026-11-17 23:58
雷达观测 2026-11-18 16:38
arXiv ↗PDF ↗

摘要

On a family of NN-state deterministic two-player discounted games, every run that chooses adaptively between Dantzig's rule and modified simplex requires 2Ω(N)2^{Ω(N)} switches from a specified initial strategy, regardless of tie breaking. More generally, a return-gate construction lets Dantzig reproduce any finite Bland prefix in an undiscounted deterministic Markov decision process with rational rewards whenever every visited policy reaches a common sink from all states. Applied to an acyclic binary counter, deleting the minimizer's return actions preserves every fixed maximizing strategy's value at each original state while reducing Dantzig's switch count from exponential to linear. With returns, halving the total optimality gap can take Ω(h/log⁡h)Ω(h/\log h) switches at discount horizon h=(1−γ)−1h=(1-γ)^{-1}, even on games solvable in linear arithmetic time. Conversely, Dantzig is strongly polynomial when strongly connected components have bounded size, each state has a bounded number of actions, and the condensation graph has height O(log⁡N)O(\log N).

AI 论文解读

基于摘要 · 非全文审阅

此版本尚未生成 AI 解读。解读由后台任务生成并按论文版本保存,登录后共享已有结果。

版本差异

目前只收录了一个版本。收录下一版后,可以对照标题、作者、分类和摘要。

观测到的版本

相邻记录可能跳过中间版本;首次发现 v2 及以上也会标为版本更新。

v1 · 2026-11-17 23:58 · 最新观测版本

A Common Exponential Lower Bound for Dantzig and Modified Simplex in Deterministic Discounted Games

On a family of NN-state deterministic two-player discounted games, every run that chooses adaptively between Dantzig's rule and modified simplex requires 2Ω(N)2^{Ω(N)} switches from a specified initial strategy, regardless of tie breaking. More generally, a return-gate construction lets Dantzig reproduce any finite Bland prefix in an undiscounted deterministic Markov decision process with rational rewards whenever every visited policy reaches a common sink from all states. Applied to an acyclic binary counter, deleting the minimizer's return actions preserves every fixed maximizing strategy's value at each original state while reducing Dantzig's switch count from exponential to linear. With returns, halving the total optimality gap can take Ω(h/log⁡h)Ω(h/\log h) switches at discount horizon h=(1−γ)−1h=(1-γ)^{-1}, even on games solvable in linear arithmetic time. Conversely, Dantzig is strongly polynomial when strongly connected components have bounded size, each state has a bounded number of actions, and the condensation graph has height O(log⁡N)O(\log N).

查看此版本解读 →查看此版本原文 ↗