English
Related papers

Related papers: $O(T^{-1})$ Convergence of Optimistic-Follow-the-R…

200 papers

No-regret learning has been widely used to compute a Nash equilibrium in two-person zero-sum games. However, there is still a lack of regret analysis for network stochastic zero-sum games, where players competing in two subnetworks only…

Optimization and Control · Mathematics 2022-05-31 Shijie Huang , Jinlong Lei , Yiguang Hong

Reinforcement Learning from Human Feedback (RLHF) has been highly successful in aligning large language models with human preferences. While prevalent methods like DPO have demonstrated strong performance, they frame interactions with the…

Machine Learning · Computer Science 2025-05-27 Yongtao Wu , Luca Viano , Yihang Chen , Zhenyu Zhu , Kimon Antonakopoulos , Quanquan Gu , Volkan Cevher

In this paper we investigate the Follow the Regularized Leader dynamics in sequential imperfect information games (IIG). We generalize existing results of Poincar\'e recurrence from normal-form games to zero-sum two-player imperfect…

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…

Machine Learning · Computer Science 2022-02-01 Mengxiao Zhang , Peng Zhao , Haipeng Luo , Zhi-Hua Zhou

We study the alternating gradient descent-ascent (AltGDA) algorithm in two-player zero-sum games. Alternating methods, where players take turns to update their strategies, have long been recognized as simple and practical approaches for…

Computer Science and Game Theory · Computer Science 2026-03-03 Tianlong Nan , Shuvomoy Das Gupta , Garud Iyengar , Christian Kroer

We consider the best-of-both-worlds problem for learning an episodic Markov Decision Process through $T$ episodes, with the goal of achieving $\widetilde{\mathcal{O}}(\sqrt{T})$ regret when the losses are adversarial and simultaneously…

Machine Learning · Computer Science 2021-10-19 Tiancheng Jin , Longbo Huang , Haipeng Luo

We revisit the Follow the Regularized Leader (FTRL) framework for Online Convex Optimization (OCO) over compact sets, focusing on achieving dynamic regret guarantees. Prior work has highlighted the framework's limitations in dynamic…

Machine Learning · Computer Science 2026-03-19 Naram Mhaisen , George Iosifidis

Policy gradient methods enjoy strong practical performance in numerous tasks in reinforcement learning. Their theoretical understanding in multiagent settings, however, remains limited, especially beyond two-player competitive and potential…

Computer Science and Game Theory · Computer Science 2023-12-22 Ioannis Anagnostides , Ioannis Panageas , Gabriele Farina , Tuomas Sandholm

We study the problem of finding the Nash equilibrium in a two-player zero-sum Markov game. Due to its formulation as a minimax optimization program, a natural approach to solve the problem is to perform gradient descent/ascent with respect…

Optimization and Control · Mathematics 2022-10-13 Sihan Zeng , Thinh T. Doan , Justin Romberg

In this paper, we study last-iterate convergence of learning algorithms in bilinear saddle-point problems, a preferable notion of convergence that captures the day-to-day behavior of learning dynamics. We focus on the challenging setting…

Follow-the-regularized-leader (FTRL) algorithms have become popular in the context of games, providing easy-to-implement methods for each agent, as well as theoretical guarantees that the strategies of all agents will converge to some…

Systems and Control · Electrical Eng. & Systems 2026-03-31 Heling Zhang , Siqi Du , Roy Dong

We introduce a generalization of zero-sum network multiagent matrix games and prove that alternating gradient descent converges to the set of Nash equilibria at rate $O(1/T)$ for this set of games. Alternating gradient descent obtains this…

Computer Science and Game Theory · Computer Science 2021-10-07 James P. Bailey

Reverse Kullback-Leibler (KL) divergence-based regularization with respect to a fixed reference policy is widely used in modern reinforcement learning to preserve the desired traits of the reference policy and sometimes to promote…

Machine Learning · Computer Science 2026-02-05 Anupam Nayak , Tong Yang , Osman Yagan , Gauri Joshi , Yuejie Chi

In this paper, we investigate the power of {\it regularization}, a common technique in reinforcement learning and optimization, in solving extensive-form games (EFGs). We propose a series of new algorithms based on regularizing the payoff…

Computer Science and Game Theory · Computer Science 2025-07-10 Mingyang Liu , Asuman Ozdaglar , Tiancheng Yu , Kaiqing Zhang

We derive the rate of convergence to Nash equilibria for the payoff-based algorithm proposed in \cite{tat_kam_TAC}. These rates are achieved under the standard assumption of convexity of the game, strong monotonicity and differentiability…

Optimization and Control · Mathematics 2022-02-24 Tatiana Tatarenko , Maryam Kamgarpour

This work studies the problem of learning episodic Markov Decision Processes with known transition and bandit feedback. We develop the first algorithm with a ``best-of-both-worlds'' guarantee: it achieves $\mathcal{O}(log T)$ regret when…

Machine Learning · Computer Science 2020-11-03 Tiancheng Jin , Haipeng Luo

In this paper, we consider two-player zero-sum matrix and stochastic games and develop learning dynamics that are payoff-based, convergent, rational, and symmetric between the two players. Specifically, the learning dynamics for matrix…

Machine Learning · Computer Science 2024-09-06 Zaiwei Chen , Kaiqing Zhang , Eric Mazumdar , Asuman Ozdaglar , Adam Wierman

We study offline learning in KL-regularized two-player zero-sum games, where policies are optimized with respect to a fixed reference policy through KL regularization. Prior work relies on pessimistic value estimation to handle distribution…

Computer Science and Game Theory · Computer Science 2026-05-11 Yuheng Zhang , Claire Chen , Nan Jiang

We provide several applications of Optimistic Mirror Descent, an online learning algorithm based on the idea of predictable sequences. First, we recover the Mirror Prox algorithm for offline optimization, prove an extension to Holder-smooth…

Machine Learning · Computer Science 2013-11-11 Alexander Rakhlin , Karthik Sridharan

We revisit the problem of solving two-player zero-sum games in the decentralized setting. We propose a simple algorithmic framework that simultaneously achieves the best rates for honest regret as well as adversarial regret, and in addition…

Computer Science and Game Theory · Computer Science 2018-06-07 Ehsan Asadi Kangarshahi , Ya-Ping Hsieh , Mehmet Fatih Sahin , Volkan Cevher