Problem
Research questions and friction points this paper is trying to address.
no-regret dynamics
individual regret
full-information feedback
normal-form game
optimism
Constant Individual Regret in General Games
🤖 AI Summary
本文提出ECHO-OFTRL算法，通过引入高阶乐观机制，在全信息反馈下为任意有限N玩家正常形式游戏中的每个玩家提供常数级别的个人后悔上界。
📝 Abstract
Uncoupled no-regret dynamics provide a decentralized route to equilibrium, but prior guarantees for individual regret retain a polylogarithmic dependence on the horizon. We remove this dependence for every finite $N$-player normal-form game under full-information feedback. We introduce \emph{ECHO-OFTRL}: optimistic follow-the-regularized-leader (OFTRL) equipped with an EMA cascade for high-order optimism (ECHO), where EMA denotes exponential moving average. The algorithm is deterministic and fully uncoupled. If $m_{\max}$ denotes the largest action-set size, then, simultaneously for every horizon $T\geq1$, it guarantees that each of the $N$ players in the game incurs regret upper bounded by $O(\textrm{poly}(N, \log m_{\max}))$. Our algorithm leverages a new form of optimism inspired by modern filter design.
Innovation
Methods, ideas, or system contributions that make the work stand out.
ECHO-OFTRL
optimistic follow-the-regularized-leader (OFTRL)
exponential moving average (EMA)
uncoupled no-regret dynamics
🔎 Similar Papers
No similar papers found.
