English
Related papers

Related papers: Finite-sample Guarantees for Nash Q-learning with …

200 papers

One of the challenges for multi-agent reinforcement learning (MARL) is designing efficient learning algorithms for a large system in which each agent has only limited or partial information of the entire system. While exciting progress has…

Machine Learning · Computer Science 2022-02-22 Haotian Gu , Xin Guo , Xiaoli Wei , Renyuan Xu

In multi-agent reinforcement learning (MARL), self-interested agents attempt to establish equilibrium and achieve coordination depending on game structure. However, existing MARL approaches are mostly bound by the simultaneous actions of…

Multiagent Systems · Computer Science 2023-12-12 Bin Zhang , Lijuan Li , Zhiwei Xu , Dapeng Li , Guoliang Fan

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

Training multi-agent systems (MAS) to achieve realistic equilibria gives us a useful tool to understand and model real-world systems. We consider a general sum partially observable Markov game where agents of different types share a single…

Multiagent Systems · Computer Science 2020-10-26 Nelson Vadori , Sumitra Ganesh , Prashant Reddy , Manuela Veloso

Traditional Reinforcement Learning from Human Feedback (RLHF) often relies on reward models, frequently assuming preference structures like the Bradley--Terry model, which may not accurately capture the complexities of real human…

Real-world games, which concern imperfect information, multiple players, and simultaneous moves, are less frequently discussed in the existing literature of game theory. While reinforcement learning (RL) provides a general framework to…

Computer Science and Game Theory · Computer Science 2023-06-02 Runyu Lu , Yuanheng Zhu , Dongbin Zhao

This paper presents a novel approach to reinforcement learning (RL) for control systems that provides probabilistic stability guarantees using finite data. Leveraging Lyapunov's method, we propose a probabilistic stability theorem that…

Machine Learning · Computer Science 2026-03-03 Minghao Han , Lixian Zhang , Chenliang Liu , Zhipeng Zhou , Jun Wang , Wei Pan

We develop a game-theoretic framework for predicting and steering the behavior of populations of large language models (LLMs) through Nash equilibrium (NE) analysis. To avoid the intractability of equilibrium computation in open-ended text…

Artificial Intelligence · Computer Science 2026-02-09 Tonghan Wang , Yuqi Pan , Xinyi Yang , Yanchen Jiang , Milind Tambe , David C. Parkes

Reinforcement learning has been successful both empirically and theoretically in single-agent settings, but extending these results to multi-agent reinforcement learning in general-sum Markov games remains challenging. This paper studies…

Machine Learning · Computer Science 2026-04-07 Narim Jeong , Donghwan Lee

Provably sample-efficient Reinforcement Learning (RL) with rich observations and function approximation has witnessed tremendous recent progress, particularly when the underlying function approximators are linear. In this linear regime,…

Machine Learning · Computer Science 2024-08-09 Alekh Agarwal , Tong Zhang

Q-learning is a popular Reinforcement Learning (RL) algorithm which is widely used in practice with function approximation (Mnih et al., 2015). In contrast, existing theoretical results are pessimistic about Q-learning. For example, (Baird,…

Machine Learning · Computer Science 2021-10-20 Naman Agarwal , Syomantak Chaudhuri , Prateek Jain , Dheeraj Nagaraj , Praneeth Netrapalli

We introduce Mean-Field Trust Region Policy Optimization (MF-TRPO), a novel algorithm designed to compute approximate Nash equilibria for ergodic Mean-Field Games (MFG) in finite state-action spaces. Building on the well-established…

Machine Learning · Statistics 2025-05-30 Antonio Ocello , Daniil Tiapkin , Lorenzo Mancini , Mathieu Laurière , Eric Moulines

In this paper, we consider the problem of learning a generalized Nash equilibrium (GNE) in strongly monotone games. First, we propose a novel continuous-time solution algorithm that uses regular projections and first-order information. As…

Systems and Control · Electrical Eng. & Systems 2020-07-23 Suad Krilašević , Sergio Grammatico

The works of (Daskalakis et al., 2009, 2022; Jin et al., 2022; Deng et al., 2023) indicate that computing Nash equilibria in multi-player Markov games is a computationally hard task. This fact raises the question of whether or not…

Computer Science and Game Theory · Computer Science 2023-05-30 Fivos Kalogiannis , Ioannis Panageas

Robust Reinforcement Learning (RRL) is a promising Reinforcement Learning (RL) paradigm aimed at training robust to uncertainty or disturbances models, making them more efficient for real-world applications. Following this paradigm,…

Machine Learning · Computer Science 2024-05-06 Anton Plaksin , Vitaly Kalev

This paper establishes a novel role for Gaussian-mixture models (GMMs) as functional approximators of Q-function losses in reinforcement learning (RL). Unlike the existing RL literature, where GMMs play their typical role as estimates of…

Machine Learning · Computer Science 2024-09-11 Minh Vu , Konstantinos Slavakis

In this paper, we study the problem of learning the set of pure strategy Nash equilibria and the exact structure of a continuous-action graphical game with quadratic payoffs by observing a small set of perturbed equilibria. A…

Computer Science and Game Theory · Computer Science 2019-11-12 Adarsh Barik , Jean Honorio

We address payoff-based decentralized learning in infinite-horizon zero-sum Markov games. In this setting, each player makes decisions based solely on received rewards, without observing the opponent's strategy or actions nor sharing…

Computer Science and Game Theory · Computer Science 2025-02-11 Reda Ouhamma , Maryam Kamgarpour

Greedy-GQ is an off-policy two timescale algorithm for optimal control in reinforcement learning. This paper develops the first finite-sample analysis for the Greedy-GQ algorithm with linear function approximation under Markovian noise. Our…

Machine Learning · Computer Science 2020-05-21 Yue Wang , Shaofeng Zou

When the data used for reinforcement learning (RL) are collected by multiple agents in a distributed manner, federated versions of RL algorithms allow collaborative learning without the need for agents to share their local data. In this…

Machine Learning · Computer Science 2023-12-14 Jiin Woo , Gauri Joshi , Yuejie Chi
‹ Prev 1 8 9 10 Next ›