English
Related papers

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

200 papers

The study of learning in games typically assumes that each player always has access to all of their actions. However, in many practical scenarios, players' available actions might be restricted due to exogenous stochasticity. To model this…

Computer Science and Game Theory · Computer Science 2026-05-12 Thomas Schwarz , Ryann Sim , Chun Kai Ling

This work considers stochastic optimization problems in which the objective function values can only be computed by a blackbox corrupted by some random noise following an unknown distribution. The proposed method is based on sequential…

Optimization and Control · Mathematics 2023-08-15 Charles Audet , Jean Bigeon , Romain Couderc , Michael Kokkolaras

We explore the use of policy approximations to reduce the computational cost of learning Nash equilibria in zero-sum stochastic games. We propose a new Q-learning type algorithm that uses a sequence of entropy-regularized soft policies to…

Machine Learning · Computer Science 2021-06-29 Yue Guan , Qifan Zhang , Panagiotis Tsiotras

We present a fast numerical algorithm for large scale zero-sum stochastic games with perfect information, which combines policy iteration and algebraic multigrid methods. This algorithm can be applied either to a true finite state space…

Optimization and Control · Mathematics 2015-03-19 Marianne Akian , Sylvie Detournay

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…

Machine Learning · Computer Science 2025-06-17 Liad Erez , Tal Lancewicki , Uri Sherman , Tomer Koren , Yishay Mansour

This paper considers offline multi-agent reinforcement learning. We propose the strategy-wise concentration principle which directly builds a confidence interval for the joint strategy, in contrast to the point-wise concentration principle…

Machine Learning · Computer Science 2022-10-17 Qiwen Cui , Simon S. Du

We propose policy gradient algorithms for robust infinite-horizon Markov decision processes (MDPs) with non-rectangular uncertainty sets, thereby addressing an open challenge in the robust MDP literature. Indeed, uncertainty sets that…

Optimization and Control · Mathematics 2025-09-30 Mengmeng Li , Daniel Kuhn , Tobias Sutter

Various methods for Multi-Agent Reinforcement Learning (MARL) have been developed with the assumption that agents' policies are based on accurate state information. However, policies learned through Deep Reinforcement Learning (DRL) are…

Artificial Intelligence · Computer Science 2024-04-15 Songyang Han , Sanbao Su , Sihong He , Shuo Han , Haizhao Yang , Shaofeng Zou , Fei Miao

We consider non-smooth saddle point optimization problems. To solve these problems, we propose a zeroth-order method under bounded or Lipschitz continuous noise, possible adversarial. In contrast to the state-of-the-art algorithms, our…

Optimization and Control · Mathematics 2023-03-28 Darina Dvinskikh , Vladislav Tominin , Yaroslav Tominin , Alexander Gasnikov

We consider reinforcement learning in changing Markov Decision Processes where both the state-transition probabilities and the reward functions may vary over time. For this problem setting, we propose an algorithm using a sliding window…

Machine Learning · Computer Science 2018-05-28 Pratik Gajane , Ronald Ortner , Peter Auer

We propose a new sample-efficient methodology, called Supervised Policy Update (SPU), for deep reinforcement learning. Starting with data generated by the current policy, SPU formulates and solves a constrained optimization problem in the…

Machine Learning · Computer Science 2018-12-27 Quan Vuong , Yiming Zhang , Keith W. Ross

This study investigates computationally efficient algorithms for solving discrete-time infinite-horizon single-agent/multi-agent dynamic models with continuous actions. It shows that we can easily reduce the computational costs by slightly…

General Economics · Economics 2025-02-21 Takeshi Fukasawa

Reinforcement learning is a widely used approach to autonomous navigation, showing potential in various tasks and robotic setups. Still, it often struggles to reach distant goals when safety constraints are imposed (e.g., the wheeled robot…

Robotics · Computer Science 2024-08-27 Brian Angulo , Gregory Gorbov , Aleksandr Panov , Konstantin Yakovlev

Multi-agent reinforcement learning, despite its popularity and empirical success, faces significant scalability challenges in large-population dynamic games. Graphon mean field games (GMFGs) offer a principled framework for approximating…

Optimization and Control · Mathematics 2025-06-09 Philipp Plank , Yufei Zhang

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

We consider the problem of computing optimal policies in average-reward Markov decision processes. This classical problem can be formulated as a linear program directly amenable to saddle-point optimization methods, albeit with a number of…

Optimization and Control · Mathematics 2020-01-13 Joan Bas-Serrano , Gergely Neu

This work designs and analyzes a novel set of algorithms for multi-agent reinforcement learning (MARL) based on the principle of information-directed sampling (IDS). These algorithms draw inspiration from foundational concepts in…

Information Theory · Computer Science 2024-05-01 Qiaosheng Zhang , Chenjia Bai , Shuyue Hu , Zhen Wang , Xuelong Li

This paper proposes a novel technique called "successive stochastic smoothing" that optimizes nonsmooth and discontinuous functions while considering various constraints. Our methodology enables local and global optimization, making it a…

Optimization and Control · Mathematics 2023-08-17 Vladimir Norkin , Alois Pichler , Anton Kozyriev

We address the problem of finding an optimal policy in a Markov decision process under a restricted policy class defined by the convex hull of a set of base policies. This problem is of great interest in applications in which a number of…

Machine Learning · Computer Science 2018-02-28 Ershad Banijamali , Yasin Abbasi-Yadkori , Mohammad Ghavamzadeh , Nikos Vlassis

We study the problem of zero-order optimization of a strongly convex function. The goal is to find the minimizer of the function by a sequential exploration of its values, under measurement noise. We study the impact of higher order…

Machine Learning · Computer Science 2022-11-28 Arya Akhavan , Massimiliano Pontil , Alexandre B. Tsybakov