中文
相关论文

相关论文: From External to Swap Regret 2.0: An Efficient Red…

200 篇论文

Recent simultaneous works by Peng and Rubinstein [2024] and Dagan et al. [2024] have demonstrated the existence of a no-swap-regret learning algorithm that can reach $\epsilon$ average swap regret against an adversary in any extensive-form…

计算机科学与博弈论 · 计算机科学 2024-06-21 Constantinos Daskalakis , Gabriele Farina , Noah Golowich , Tuomas Sandholm , Brian Hu Zhang

We consider the problem of minimizing different notions of swap regret in online optimization. These forms of regret are tightly connected to correlated equilibrium concepts in games, and have been more recently shown to guarantee…

机器学习 · 计算机科学 2026-05-22 Ioannis Anagnostides , Gabriele Farina , Maxwell Fishelson , Haipeng Luo , Jon Schneider

Recently, Daskalakis, Fishelson, and Golowich (DFG) (NeurIPS`21) showed that if all agents in a multi-player general-sum normal-form game employ Optimistic Multiplicative Weights Update (OMWU), the external regret of every player is…

Swap regret is a notion that has proven itself to be central to the study of general-sum normal-form games, with swap-regret minimization leading to convergence to the set of correlated equilibria and guaranteeing non-manipulability against…

计算机科学与博弈论 · 计算机科学 2025-02-28 Eshwar Ram Arunachaleswaran , Natalie Collina , Yishay Mansour , Mehryar Mohri , Jon Schneider , Balasubramanian Sivan

We give a simple and computationally efficient algorithm that, for any constant $\varepsilon>0$, obtains $\varepsilon T$-swap regret within only $T = \mathsf{polylog}(n)$ rounds; this is an exponential improvement compared to the…

计算机科学与博弈论 · 计算机科学 2023-11-15 Binghui Peng , Aviad Rubinstein

No-regret learners seek to minimize the difference between the loss they cumulated through the actions they played, and the loss they would have cumulated in hindsight had they consistently modified their behavior according to some strategy…

计算机科学与博弈论 · 计算机科学 2023-11-09 Gabriele Farina , Charilaos Pipis

An abundance of recent impossibility results establish that regret minimization in Markov games with adversarial opponents is both statistically and computationally intractable. Nevertheless, none of these results preclude the possibility…

机器学习 · 计算机科学 2025-06-17 Liad Erez , Tal Lancewicki , Uri Sherman , Tomer Koren , Yishay Mansour

Characterizing the performance of no-regret dynamics in multi-player games is a foundational problem at the interface of online learning and game theory. Recent results have revealed that when all players adopt specific learning algorithms,…

计算机科学与博弈论 · 计算机科学 2023-11-28 Ioannis Anagnostides , Alkis Kalavasis , Tuomas Sandholm , Manolis Zampetakis

Focusing on the expert problem in online learning, this paper studies the interpolation of several performance metrics via $\phi$-regret minimization, which measures the total loss of an algorithm by its regret with respect to an arbitrary…

机器学习 · 统计学 2025-06-19 Zhou Lu , Y. Jennifer Sun , Zhiyu Zhang

In the experts problem, on each of $T$ days, an agent needs to follow the advice of one of $n$ ``experts''. After each day, the loss associated with each expert's advice is revealed. A fundamental result in learning theory says that the…

数据结构与算法 · 计算机科学 2023-03-10 Binghui Peng , Aviad Rubinstein

This paper addresses the problem of designing efficient no-swap regret algorithms for combinatorial bandits, where the number of actions $N$ is exponentially large in the dimensionality of the problem. In this setting, designing efficient…

机器学习 · 计算机科学 2026-02-03 Andreas Kontogiannis , Vasilis Pollatos , Panayotis Mertikopoulos , Ioannis Panageas

A celebrated connection in the interface of online learning and game theory establishes that players minimizing swap regret converge to correlated equilibria (CE) -- a seminal game-theoretic solution concept. Despite the long history of…

计算机科学与博弈论 · 计算机科学 2024-11-05 Ioannis Anagnostides , Alkis Kalavasis , Tuomas Sandholm

We study the problem of minimizing swap regret in structured normal-form games. Players have a very large (potentially infinite) number of pure actions, but each action has an embedding into $d$-dimensional space and payoffs are given by…

We consider regret minimization in repeated games with non-convex loss functions. Minimizing the standard notion of regret is computationally intractable. Thus, we define a natural notion of regret which permits efficient optimization and…

机器学习 · 计算机科学 2017-11-06 Elad Hazan , Karan Singh , Cyril Zhang

We revisit the problem of online learning with sleeping experts/bandits: in each time step, only a subset of the actions are available for the algorithm to choose from (and learn about). The work of Kleinberg et al. (2010) showed that there…

机器学习 · 计算机科学 2021-04-27 Ehsan Emamjomeh-Zadeh , Chen-Yu Wei , Haipeng Luo , David Kempe

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

Achieving sample efficiency in online episodic reinforcement learning (RL) requires optimally balancing exploration and exploitation. When it comes to a finite-horizon episodic Markov decision process with $S$ states, $A$ actions and…

机器学习 · 计算机科学 2022-10-18 Gen Li , Laixi Shi , Yuxin Chen , Yuejie Chi

We provide the first sub-linear space and sub-linear regret algorithm for online learning with expert advice (against an oblivious adversary), addressing an open question raised recently by Srinivas, Woodruff, Xu and Zhou (STOC 2022). We…

数据结构与算法 · 计算机科学 2022-11-09 Binghui Peng , Fred Zhang

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

Regret minimization is a general approach to online optimization which plays a crucial role in many algorithms for approximating Nash equilibria in two-player zero-sum games. The literature mainly focuses on solving individual games in…

计算机科学与博弈论 · 计算机科学 2025-04-29 David Sychrovský , Martin Schmid , Michal Šustr , Michael Bowling
‹ 上一页 1 2 3 10 下一页 ›