中文
相关论文

相关论文: No-Regret Learning in Extensive-Form Games with Im…

200 篇论文

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

Online game playing algorithms produce high-quality strategies with a fraction of memory and computation required by their offline alternatives. Continual Resolving (CR) is a recent theoretically sound approach to online game playing that…

计算机科学与博弈论 · 计算机科学 2019-03-11 Michal Sustr , Vojtech Kovarik , Viliam Lisy

Counterfactual regret minimization (CFR) algorithms are a foundational class of methods for solving imperfect-information games, with the time average of their iterates converging to a Nash equilibrium in two-player zero-sum games. Prior…

计算机科学与博弈论 · 计算机科学 2026-02-10 Naifeng Zhang , Stephen McAleer , 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…

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

We develop an algorithmic framework for solving convex optimization problems using no-regret game dynamics. By converting the problem of minimizing a convex function into an auxiliary problem of solving a min-max game in a sequential…

机器学习 · 计算机科学 2023-02-21 Jun-Kun Wang , Jacob Abernethy , Kfir Y. Levy

This paper considers repeated games in which one player has more information about the game than the other players. In particular, we investigate repeated two-player zero-sum games where only the column player knows the payoff matrix A of…

计算机科学与博弈论 · 计算机科学 2023-02-16 Le Cong Dinh , Long Tran-Thanh , Tri-Dung Nguyen , Alain B. Zemkoho

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

We study the performance of optimistic regret-minimization algorithms for both minimizing regret in, and computing Nash equilibria of, zero-sum extensive-form games. In order to apply these algorithms to extensive-form games, a…

计算机科学与博弈论 · 计算机科学 2019-10-29 Gabriele Farina , Christian Kroer , Tuomas Sandholm

The notion of \emph{policy regret} in online learning is a well defined? performance measure for the common scenario of adaptive adversaries, which more traditional quantities such as external regret do not take into account. We revisit the…

机器学习 · 计算机科学 2020-03-24 Raman Arora , Michael Dinitz , Teodor V. Marinov , Mehryar Mohri

Learning from repeated play in a fixed two-player zero-sum game is a classic problem in game theory and online learning. We consider a variant of this problem where the game payoff matrix changes over time, possibly in an adversarial…

机器学习 · 计算机科学 2022-02-01 Mengxiao Zhang , Peng Zhao , Haipeng Luo , Zhi-Hua Zhou

Mechanism design has found considerable application to the construction of agent-interaction protocols. In the standard setting, the type (e.g., utility function) of an agent is not known by other agents, nor is it known by the mechanism…

计算机科学与博弈论 · 计算机科学 2012-07-19 Nathanael Hyafil , Craig Boutilier

Existing online learning algorithms for adversarial Markov Decision Processes achieve ${O}(\sqrt{T})$ regret after $T$ rounds of interactions even if the loss functions are chosen arbitrarily by an adversary, with the caveat that the…

机器学习 · 计算机科学 2023-10-27 Tiancheng Jin , Junyan Liu , Chloé Rouyer , William Chang , Chen-Yu Wei , Haipeng Luo

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

Monte Carlo Counterfactual Regret Minimization (MCCFR) has emerged as a cornerstone algorithm for solving extensive-form games, but its integration with deep neural networks introduces scale-dependent challenges that manifest differently…

人工智能 · 计算机科学 2026-01-29 Zakaria El Jaafari

This paper examines the convergence of no-regret learning in Cournot games with continuous actions. Cournot games are the essential model for many socio-economic systems, where players compete by strategically setting their output quantity.…

计算机科学与博弈论 · 计算机科学 2020-02-12 Yuanyuan Shi , Baosen Zhang

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 introduce DREAM, a deep reinforcement learning algorithm that finds optimal strategies in imperfect-information games with multiple agents. Formally, DREAM converges to a Nash Equilibrium in two-player zero-sum games and to an…

机器学习 · 计算机科学 2020-12-01 Eric Steinberger , Adam Lerer , Noam Brown

We examine the problem of regret minimization when the learner is involved in a continuous game with other optimizing agents: in this case, if all players follow a no-regret algorithm, it is possible to achieve significantly lower regret…

计算机科学与博弈论 · 计算机科学 2023-03-20 Yu-Guan Hsieh , Kimon Antonakopoulos , Volkan Cevher , Panayotis Mertikopoulos

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