English
Related papers

Related papers: Smoothing Policy Iteration for Zero-sum Markov Gam…

200 papers

We study policies aiming to minimize the weighted sum of completion times of jobs in the context of coordination mechanisms for selfish scheduling problems. Our goal is to design local policies that achieve a good price of anarchy in the…

Computer Science and Game Theory · Computer Science 2010-12-23 Richard Cole , José R. Correa , Vasilis Gkatzelis , Vahab Mirrokni , Neil Olver

In this paper, we propose a novel reinforcement- learning algorithm consisting in a stochastic variance-reduced version of policy gradient for solving Markov Decision Processes (MDPs). Stochastic variance-reduced gradient (SVRG) methods…

Machine Learning · Computer Science 2018-06-15 Matteo Papini , Damiano Binaghi , Giuseppe Canonaco , Matteo Pirotta , Marcello Restelli

We propose SmoothCruiser, a new planning algorithm for estimating the value function in entropy-regularized Markov decision processes and two-player games, given a generative model of the environment. SmoothCruiser makes use of the…

Machine Learning · Computer Science 2026-04-22 Jean-Bastien Grill , Omar Darwiche Domingues , Pierre Ménard , Rémi Munos , Michal Valko

We study multi-player general-sum Markov games with one of the players designated as the leader and the other players regarded as followers. In particular, we focus on the class of games where the followers are myopic, i.e., they aim to…

Machine Learning · Computer Science 2021-12-28 Han Zhong , Zhuoran Yang , Zhaoran Wang , Michael I. Jordan

This paper addresses the problem of model-free reinforcement learning for Robust Markov Decision Process (RMDP) with large state spaces. The goal of the RMDP framework is to find a policy that is robust against the parameter uncertainties…

Machine Learning · Computer Science 2021-02-15 Kishan Panaganti , Dileep Kalathil

Exploration is critical to a reinforcement learning agent's performance in its given environment. Prior exploration methods are often based on using heuristic auxiliary predictions to guide policy behavior, lacking a mathematically-grounded…

Machine Learning · Computer Science 2020-03-02 Lisa Lee , Benjamin Eysenbach , Emilio Parisotto , Eric Xing , Sergey Levine , Ruslan Salakhutdinov

In this paper, we study a class of non-smooth non-convex problems in the form of $\min_{x}[\max_{y\in Y}\phi(x, y) - \max_{z\in Z}\psi(x, z)]$, where both $\Phi(x) = \max_{y\in Y}\phi(x, y)$ and $\Psi(x)=\max_{z\in Z}\psi(x, z)$ are weakly…

Optimization and Control · Mathematics 2024-11-18 Quanqi Hu , Qi Qi , Zhaosong Lu , Tianbao Yang

While single-agent policy optimization in a fixed environment has attracted a lot of research attention recently in the reinforcement learning community, much less is known theoretically when there are multiple agents playing in a…

Machine Learning · Computer Science 2022-07-27 Shuang Qiu , Xiaohan Wei , Jieping Ye , Zhaoran Wang , Zhuoran Yang

Policy optimization methods with function approximation are widely used in multi-agent reinforcement learning. However, it remains elusive how to design such algorithms with statistical guarantees. Leveraging a multi-agent performance…

Machine Learning · Computer Science 2023-05-09 Yulai Zhao , Zhuoran Yang , Zhaoran Wang , Jason D. Lee

The study of convex optimization has historically been concerned with worst-case convergence rates. The development of the Optimized Gradient Method (OGM), due to \citet{drori2012PerformanceOF,Kim2016optimal}, marked a major milestone in…

Optimization and Control · Mathematics 2026-04-21 Benjamin Grimmer , Kevin Shu , Alex L. Wang

Motivated by penalized likelihood maximization in complex models, we study optimization problems where neither the function to optimize nor its gradient have an explicit expression, but its gradient can be approximated by a Monte Carlo…

Computation · Statistics 2017-09-28 Gersende Fort , Edouard Ollier , Adeline Samson

Algorithmic analysis of Markov decision processes (MDP) and stochastic games (SG) in practice relies on value-iteration (VI) algorithms. Since the basic version of VI does not provide guarantees on the precision of the result, variants of…

Computer Science and Game Theory · Computer Science 2026-03-31 Muqsit Azeem , Jan Kretinsky , Maximilian Weininger

In this paper, we consider constrained optimization problems with convex, smooth objective and constraints. We propose a new stochastic gradient algorithm, called the Stochastic Moving Ball Approximation (SMBA) method, to solve this class…

Optimization and Control · Mathematics 2024-12-03 Nitesh Kumar Singh , Ion Necoara

This paper considers nonsmooth convex optimization with either a subgradient or proximal operator oracle. In both settings, we identify algorithms that achieve the recently introduced game-theoretic optimality notion for algorithms known as…

Optimization and Control · Mathematics 2025-11-18 Benjamin Grimmer , Alex L. Wang

Two of the most prominent algorithms for solving unconstrained smooth games are the classical stochastic gradient descent-ascent (SGDA) and the recently introduced stochastic consensus optimization (SCO) [Mescheder et al., 2017]. SGDA is…

Machine Learning · Computer Science 2021-11-05 Nicolas Loizou , Hugo Berard , Gauthier Gidel , Ioannis Mitliagkas , Simon Lacoste-Julien

Algorithmic analysis of Markov decision processes (MDP) and stochastic games (SG) in practice relies on value-iteration (VI) algorithms. Since basic VI does not provide guarantees on the precision of the result, variants of VI have been…

Computer Science and Game Theory · Computer Science 2025-09-18 Muqsit Azeem , Jan Kretinsky , Maximilian Weininger

We present Self-Play Preference Optimization (SPO), an algorithm for reinforcement learning from human feedback. Our approach is minimalist in that it does not require training a reward model nor unstable adversarial training and is…

Machine Learning · Computer Science 2024-06-14 Gokul Swamy , Christoph Dann , Rahul Kidambi , Zhiwei Steven Wu , Alekh Agarwal

One practical requirement in solving dynamic games is to ensure that the players play well from any decision point onward. To satisfy this requirement, existing efforts focus on equilibrium refinement, but the scalability and applicability…

Multiagent Systems · Computer Science 2021-08-24 Weizhe Chen , Zihan Zhou , Yi Wu , Fei Fang

In multi-agent tasks, the central challenge lies in the dynamic adaptation of strategies. However, directly conditioning on opponents' strategies is intractable in the prevalent deep reinforcement learning paradigm due to a fundamental…

Computer Science and Game Theory · Computer Science 2025-12-25 Yue Lin , Shuhui Zhu , Wenhao Li , Ang Li , Dan Qiao , Pascal Poupart , Hongyuan Zha , Baoxiang Wang

The goal of agents in multi-agent environments is to maximize total reward against the opposing agents that are encountered. Following a game-theoretic solution concept, such as Nash equilibrium, may obtain a strong performance in some…

Computer Science and Game Theory · Computer Science 2026-01-05 Sam Ganzfried
‹ Prev 1 4 5 6 7 8 10 Next ›