English
Related papers

Related papers: Pessimistic Minimax Value Iteration: Provably Effi…

200 papers

This paper studies policy optimization algorithms for multi-agent reinforcement learning. We begin by proposing an algorithm framework for two-player zero-sum Markov Games in the full-information setting, where each iteration consists of a…

Machine Learning · Computer Science 2022-07-26 Runyu Zhang , Qinghua Liu , Huan Wang , Caiming Xiong , Na Li , Yu Bai

We study online optimization methods for zero-sum games, a fundamental problem in adversarial learning in machine learning, economics, and many other domains. Traditional methods approximate Nash equilibria (NE) using either regret-based…

Computer Science and Game Theory · Computer Science 2025-07-16 Taemin Kim , James P. Bailey

Computing Nash equilibrium policies is a central problem in multi-agent reinforcement learning that has received extensive attention both in theory and in practice. However, provable guarantees have been thus far either limited to fully…

We study distributionally robust Markov games (DR-MGs) with the average-reward criterion, a framework for multi-agent decision-making under uncertainty over extended horizons. In average reward DR-MGs, agents aim to maximize their…

Multiagent Systems · Computer Science 2025-12-12 Zachary Roch , Yue Wang

Multi-agent robust reinforcement learning, also known as multi-player robust Markov games (RMGs), is a crucial framework for modeling competitive interactions under environmental uncertainties, with wide applications in multi-agent systems.…

Machine Learning · Computer Science 2024-12-31 Yuchen Jiao , Gen Li

Distributionally robust offline reinforcement learning (RL), which seeks robust policy training against environment perturbation by modeling dynamics uncertainty, calls for function approximations when facing large state-action spaces.…

Machine Learning · Computer Science 2025-11-03 Zhishuai Liu , Pan Xu

We design and analyze minimax-optimal algorithms for online linear optimization games where the player's choice is unconstrained. The player strives to minimize regret, the difference between his loss and the loss of a post-hoc benchmark…

Machine Learning · Computer Science 2013-02-12 H. Brendan McMahan

We study risk-aware offline policy learning, aiming to learn a decision rule from logged data that is optimal under general risk criteria. This problem is crucial in high-stakes domains where online interaction is infeasible and adverse…

Machine Learning · Statistics 2026-05-18 Yilong Wan , Yuqiang Li , Xianyi Wu

Modern reinforcement learning (RL) commonly engages practical problems with large state spaces, where function approximation must be deployed to approximate either the value function or the policy. While recent progresses in RL theory…

Machine Learning · Computer Science 2021-10-14 Chi Jin , Qinghua Liu , Tiancheng Yu

Decoding how rational agents should behave in shared systems remains a critical challenge within theoretical computer science, artificial intelligence and economics studies. Central to this challenge is the task of computing the solution…

Computer Science and Game Theory · Computer Science 2025-01-07 Dongge Wang , Xiang Yan , Zehao Dou , Wenhan Huang , Yaodong Yang , Xiaotie Deng

We study the problem of repeated play in a zero-sum game in which the payoff matrix may change, in a possibly adversarial fashion, on each round; we call these Online Matrix Games. Finding the Nash Equilibrium (NE) of a two player zero-sum…

Machine Learning · Computer Science 2020-04-06 Adrian Rivera Cardoso , Jacob Abernethy , He Wang , Huan Xu

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

This paper addresses the problem of learning a Nash equilibrium in $\gamma$-discounted multiplayer general-sum Markov Games (MG). A key component of this model is the possibility for the players to either collaborate or team apart to…

Computer Science and Game Theory · Computer Science 2017-03-07 Julien Pérolat , Florian Strub , Bilal Piot , Olivier Pietquin

This paper studies offline policy learning, which aims at utilizing observations collected a priori (from either fixed or adaptively evolving behavior policies) to learn an optimal individualized decision rule that achieves the best overall…

Machine Learning · Computer Science 2025-06-06 Ying Jin , Zhimei Ren , Zhuoran Yang , Zhaoran Wang

We examine online safe multi-agent reinforcement learning using constrained Markov games in which agents compete by maximizing their expected total rewards under a constraint on expected total utilities. Our focus is confined to an episodic…

Machine Learning · Computer Science 2023-06-02 Dongsheng Ding , Xiaohan Wei , Zhuoran Yang , Zhaoran Wang , Mihailo R. Jovanović

We consider a variant of continuous-state partially-observable stochastic games with neural perception mechanisms and an asymmetric information structure. One agent has partial information, with the observation function implemented as a…

Computer Science and Game Theory · Computer Science 2024-04-17 Rui Yan , Gabriel Santos , Gethin Norman , David Parker , Marta Kwiatkowska

We examine global non-asymptotic convergence properties of policy gradient methods for multi-agent reinforcement learning (RL) problems in Markov potential games (MPG). To learn a Nash equilibrium of an MPG in which the size of state space…

Machine Learning · Computer Science 2022-08-08 Dongsheng Ding , Chen-Yu Wei , Kaiqing Zhang , Mihailo R. Jovanović

We study risk-sensitive reinforcement learning (RL), a crucial field due to its ability to enhance decision-making in scenarios where it is essential to manage uncertainty and minimize potential adverse outcomes. Particularly, our work…

Machine Learning · Computer Science 2024-07-11 Dake Zhang , Boxiang Lyu , Shuang Qiu , Mladen Kolar , Tong Zhang

We propose a novel algorithm for offline reinforcement learning called Value Iteration with Perturbed Rewards (VIPeR), which amalgamates the pessimism principle with random perturbations of the value function. Most current offline RL…

Machine Learning · Computer Science 2023-03-07 Thanh Nguyen-Tang , Raman Arora

We consider the problem of finding Nash equilibrium for two-player turn-based zero-sum games. Inspired by the AlphaGo Zero (AGZ) algorithm, we develop a Reinforcement Learning based approach. Specifically, we propose…

Machine Learning · Computer Science 2020-02-26 Devavrat Shah , Varun Somani , Qiaomin Xie , Zhi Xu