中文
相关论文

相关论文: On the Complexity of Computing Sparse Equilibria a…

200 篇论文

We consider the problem of decentralized multi-agent reinforcement learning in Markov games. A fundamental question is whether there exist algorithms that, when adopted by all agents and run independently in a decentralized fashion, lead to…

机器学习 · 计算机科学 2023-03-23 Dylan J. Foster , Noah Golowich , Sham M. Kakade

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

A celebrated result in the interface of online learning and game theory guarantees that the repeated interaction of no-regret players leads to a coarse correlated equilibrium (CCE) -- a natural game-theoretic solution concept. Despite the…

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

No-regret learning dynamics play a central role in game theory, enabling decentralized convergence to equilibrium for concepts such as Coarse Correlated Equilibrium (CCE) or Correlated Equilibrium (CE). In this work, we improve the…

计算机科学与博弈论 · 计算机科学 2025-11-05 Asrin Efe Yorulmaz , Tamer Başar

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

The existence of simple uncoupled no-regret learning dynamics that converge to correlated equilibria in normal-form games is a celebrated result in the theory of multi-agent systems. Specifically, it has been known for more than 20 years…

计算机科学与博弈论 · 计算机科学 2021-05-28 Gabriele Farina , Andrea Celli , Alberto Marchesi , Nicola Gatti

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

A recent line of work has established uncoupled learning dynamics such that, when employed by all players in a game, each player's \emph{regret} after $T$ repetitions grows polylogarithmically in $T$, an exponential improvement over the…

计算机科学与博弈论 · 计算机科学 2022-10-18 Gabriele Farina , Ioannis Anagnostides , Haipeng Luo , Chung-Wei Lee , Christian Kroer , Tuomas Sandholm

A recent emerging trend in the literature on learning in games has been concerned with providing faster learning dynamics for correlated and coarse correlated equilibria in normal-form games. Much less is known about the significantly more…

计算机科学与博弈论 · 计算机科学 2022-02-14 Ioannis Anagnostides , Gabriele Farina , Christian Kroer , Andrea Celli , Tuomas Sandholm

In game-theoretic learning, several agents are simultaneously following their individual interests, so the environment is non-stationary from each player's perspective. In this context, the performance of a learning algorithm is often…

计算机科学与博弈论 · 计算机科学 2021-10-19 Yu-Guan Hsieh , Kimon Antonakopoulos , Panayotis Mertikopoulos

The existence of simple, uncoupled no-regret dynamics that converge to correlated equilibria in normal-form games is a celebrated result in the theory of multi-agent systems. Specifically, it has been known for more than 20 years that when…

计算机科学与博弈论 · 计算机科学 2022-09-05 Andrea Celli , Alberto Marchesi , Gabriele Farina , Nicola Gatti

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 show that Optimistic Hedge -- a common variant of multiplicative-weights-updates with recency bias -- attains ${\rm poly}(\log T)$ regret in multi-player general-sum games. In particular, when every player of the game uses Optimistic…

机器学习 · 计算机科学 2023-01-26 Constantinos Daskalakis , Maxwell Fishelson , Noah Golowich

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

A natural goal in multiagent learning besides finding equilibria is to learn rationalizable behavior, where players learn to avoid iteratively dominated actions. However, even in the basic setting of multiplayer general-sum games, existing…

机器学习 · 计算机科学 2022-10-21 Yuanhao Wang , Dingwen Kong , Yu Bai , Chi Jin

We consider the problem of simultaneous learning in stochastic games with many players in the finite-horizon setting. While the typical target solution for a stochastic game is a Nash equilibrium, this is intractable with many players. We…

计算机科学与博弈论 · 计算机科学 2022-10-27 William Brown

We propose efficient no-regret learning dynamics and ellipsoid-based methods for computing linear correlated equilibria$\unicode{x2014}$a relaxation of correlated equilibria and a strengthening of coarse correlated…

计算机科学与博弈论 · 计算机科学 2024-12-31 Constantinos Daskalakis , Gabriele Farina , Maxwell Fishelson , Charilaos Pipis , Jon Schneider

Nash equilibrium is perhaps the best-known solution concept in game theory. Such a solution assigns a strategy to each player which offers no incentive to unilaterally deviate. While a Nash equilibrium is guaranteed to always exist, the…

计算机科学与博弈论 · 计算机科学 2025-04-29 David Sychrovský , Christopher Solinas , Revan MacQueen , Kevin Wang , James R. Wright , Nathan R. Sturtevant , Michael Bowling

We show that, for any sufficiently small fixed $\epsilon > 0$, when both players in a general-sum two-player (bimatrix) game employ optimistic mirror descent (OMD) with smooth regularization, learning rate $\eta = O(\epsilon^2)$ and $T =…

计算机科学与博弈论 · 计算机科学 2022-10-10 Ioannis Anagnostides , Gabriele Farina , Ioannis Panageas , Tuomas Sandholm

We consider online no-regret learning in unknown games with bandit feedback, where each player can only observe its reward at each time -- determined by all players' current joint action -- rather than its gradient. We focus on the class of…

机器学习 · 计算机科学 2024-04-01 Wenjia Ba , Tianyi Lin , Jiawei Zhang , Zhengyuan Zhou
‹ 上一页 1 2 3 10 下一页 ›