中文
相关论文

相关论文: Online Optimization in Games via Control Theory: C…

200 篇论文

We investigate the interplay between passivity, no-regret, and convergence in contractive games for various learning dynamic models and their higher-order variants. Our setting is continuous time. Building on prior work for replicator…

系统与控制 · 电气工程与系统科学 2025-04-01 Hassan Abdelraouf , Georgios Piliouras , Jeff S. Shamma

The long-run behavior of multi-agent learning - and, in particular, no-regret learning - is relatively well-understood in potential games, where players have aligned interests. By contrast, in harmonic games - the strategic counterpart of…

计算机科学与博弈论 · 计算机科学 2024-12-31 Davide Legacci , Panayotis Mertikopoulos , Christos H. Papadimitriou , Georgios Piliouras , Bary S. R. Pradelski

Understanding the behavior of no-regret dynamics in general $N$-player games is a fundamental question in online learning and game theory. A folk result in the field states that, in finite games, the empirical frequency of play under…

A seminal result in game theory is von Neumann's minmax theorem, which states that zero-sum games admit an essentially unique equilibrium solution. Classical learning results build on this theorem to show that online no-regret dynamics…

计算机科学与博弈论 · 计算机科学 2021-11-08 Tanner Fiez , Ryann Sim , Stratis Skoulakis , Georgios Piliouras , Lillian Ratliff

This paper presents a new framework for analyzing and designing no-regret algorithms for dynamic (possibly adversarial) systems. The proposed framework generalizes the popular online convex optimization framework and extends it to its…

机器学习 · 计算机科学 2016-08-30 Ian Gemp , Sridhar Mahadevan

This paper studies the optimistic variant of Fictitious Play for learning in two-player zero-sum games. While it is known that Optimistic FTRL -- a regularized algorithm with a bounded stepsize parameter -- obtains constant regret in this…

机器学习 · 计算机科学 2026-01-15 John Lazarsfeld , Georgios Piliouras , Ryann Sim , Stratis Skoulakis

Learning in games refers to scenarios where multiple players interact in a shared environment, each aiming to minimize their regret. An equilibrium can be computed at a fast rate of $O(1/T)$ when all players follow the optimistic…

计算机科学与博弈论 · 计算机科学 2025-02-18 Taira Tsuchiya , Shinji Ito , Haipeng Luo

We introduce Cautious Optimism, a framework for substantially faster regularized learning in general games. Cautious Optimism, as a variant of Optimism, adaptively controls the learning pace in a dynamic, non-monotone manner to accelerate…

机器学习 · 计算机科学 2025-11-17 Ashkan Soleymani , Georgios Piliouras , Gabriele Farina

Regret has been established as a foundational concept in online learning, and likewise has important applications in the analysis of learning dynamics in games. Regret quantifies the difference between a learner's performance against a…

计算机科学与博弈论 · 计算机科学 2021-06-29 Georgios Piliouras , Mark Rowland , Shayegan Omidshafiei , Romuald Elie , Daniel Hennes , Jerome Connor , Karl Tuyls

We study online learning problems in which the learner has extra knowledge about the adversary's behaviour, i.e., in game-theoretic settings where opponents typically follow some no-external regret learning algorithms. Under this…

机器学习 · 计算机科学 2023-02-15 Le Cong Dinh , Tri-Dung Nguyen , Alain Zemkoho , Long Tran-Thanh

In this paper, we establish efficient and uncoupled learning dynamics so that, when employed by all players in multiplayer perfect-recall imperfect-information extensive-form games, the trigger regret of each player grows as $O(\log T)$…

计算机科学与博弈论 · 计算机科学 2023-09-20 Ioannis Anagnostides , Gabriele Farina , Tuomas Sandholm

Online learning is a powerful tool for analyzing iterative algorithms. However, the classic adversarial setup sometimes fails to capture certain regularity in online problems in practice. Motivated by this, we establish a new setup, called…

机器学习 · 计算机科学 2022-04-06 Ching-An Cheng , Jonathan Lee , Ken Goldberg , Byron Boots

We show for the first time, to our knowledge, that it is possible to reconcile in online learning in zero-sum games two seemingly contradictory objectives: vanishing time-average regret and non-vanishing step sizes. This phenomenon, that we…

计算机科学与博弈论 · 计算机科学 2019-05-14 James P. Bailey , Georgios Piliouras

Many online decision problems over combinatorial actions are addressed via convex relaxations, leading to online convex optimization with piecewise linear objectives and induced polyhedral structure. We show that regret in such problems is…

In this paper, we propose a learning approach to analyze dynamic systems with asymmetric information structure. Instead of adopting a game theoretic setting, we investigate an online quadratic optimization problem driven by system noises…

最优化与控制 · 数学 2018-11-05 Cheng Tan , Wing Shing Wong

Online learning and model reference adaptive control have many interesting intersections. One area where they differ however is in how the algorithms are analyzed and what objective or metric is used to discriminate "good" algorithms from…

系统与控制 · 电气工程与系统科学 2025-01-24 Travis E. Gibson , Sawal Acharya

Regret minimization has proved to be a versatile tool for tree-form sequential decision making and extensive-form games. In large two-player zero-sum imperfect-information games, modern extensions of counterfactual regret minimization (CFR)…

计算机科学与博弈论 · 计算机科学 2021-03-09 Gabriele Farina , Tuomas Sandholm

Follow-the-Regularized-Leader (FTRL) algorithms are a popular class of learning algorithms for online linear optimization (OLO) that guarantee sub-linear regret, but the choice of regularizer can significantly impact dimension-dependent…

机器学习 · 计算机科学 2024-10-24 Khashayar Gatmiry , Jon Schneider , Stefanie Jegelka

This paper investigates the sublinear regret guarantees of two non-no-regret algorithms in zero-sum games: Fictitious Play, and Online Gradient Descent with constant stepsizes. In general adversarial online learning settings, both…

机器学习 · 计算机科学 2025-06-17 John Lazarsfeld , Georgios Piliouras , Ryann Sim , Andre Wibisono

Online learning is a powerful tool for analyzing iterative algorithms. However, the classic adversarial setup sometimes fails to capture certain regularity in online problems in practice. Motivated by this, we establish a new setup, called…

机器学习 · 计算机科学 2022-04-06 Jonathan Lee , Ching-An Cheng , Ken Goldberg , Byron Boots
‹ 上一页 1 2 3 10 下一页 ›