English
Related papers

Related papers: Improving Sample Efficiency of Model-Free Algorith…

200 papers

We study a new model-free algorithm to compute $\varepsilon$-optimal policies for average reward Markov decision processes, in the weakly communicating case. Given a generative model, our procedure combines a recursive sampling technique…

Optimization and Control · Mathematics 2025-06-16 Jongmin Lee , Mario Bravo , Roberto Cominetti

This paper provides the first expert sample complexity characterization for learning a Nash equilibrium from expert data in Markov Games. We show that a new quantity named the single policy deviation concentrability coefficient is…

Machine Learning · Computer Science 2025-10-10 Till Freihaut , Luca Viano , Volkan Cevher , Matthieu Geist , Giorgia Ramponi

We study the open question of how players learn to play a social optimum pure-strategy Nash equilibrium (PSNE) through repeated interactions in general-sum coordination games. A social optimum of a game is the stable Pareto-optimal state…

Computer Science and Game Theory · Computer Science 2023-07-26 Duong Nguyen , Langford White , Hung Nguyen

We consider a class of two-player zero-sum stochastic games with finite state and compact control spaces, which we call stochastic shortest path (SSP) games. They are undiscounted total cost stochastic dynamic games that have a cost-free…

Optimization and Control · Mathematics 2014-12-31 Huizhen Yu

Optimal policies in standard MDPs can be obtained using either value iteration or policy iteration. However, in the case of zero-sum Markov games, there is no efficient policy iteration algorithm; e.g., it has been shown that one has to…

Machine Learning · Computer Science 2023-10-31 Anna Winnicki , R. Srikant

Model-based reinforcement learning uses models to plan, where the predictions and policies of an agent can be improved by using more computation without additional data from the environment, thereby improving sample efficiency. However,…

Machine Learning · Computer Science 2023-02-22 Animesh Kumar Paul , Videh Raj Nema

Computing approximate Nash equilibria in multi-player general-sum Markov games is a computationally intractable task. However, multi-player Markov games with certain cooperative or competitive structures might circumvent this…

Computer Science and Game Theory · Computer Science 2023-08-17 Zailin Ma , Jiansheng Yang , Zhihua Zhang

We study the problem of learning Nash equilibria in offline two-player zero-sum Markov games. While existing approaches often rely on explicit pessimism to address distribution shift, we show that KL regularization alone suffices to…

Machine Learning · Computer Science 2026-05-14 Claire Chen , Yuheng Zhang , Xinyu Liu , Zixuan Xie , Shuze Daniel Liu , Nan Jiang

We study Markov potential games under the infinite horizon average reward criterion. Most previous studies have been for discounted rewards. We prove that both algorithms based on independent policy gradient and independent natural policy…

Machine Learning · Computer Science 2024-03-12 Min Cheng , Ruida Zhou , P. R. Kumar , Chao Tian

We study episodic two-player zero-sum Markov games (MGs) in the offline setting, where the goal is to find an approximate Nash equilibrium (NE) policy pair based on a dataset collected a priori. When the dataset does not have uniform…

Machine Learning · Computer Science 2023-01-02 Han Zhong , Wei Xiong , Jiyuan Tan , Liwei Wang , Tong Zhang , Zhaoran Wang , Zhuoran Yang

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

Distributionally Robust Reinforcement Learning (DR-RL) aims to derive a policy optimizing the worst-case performance within a predefined uncertainty set. Despite extensive research, previous DR-RL algorithms have predominantly favored…

Machine Learning · Computer Science 2024-06-26 Yudan Wang , Shaofeng Zou , Yue Wang

Sample efficiency is one of the most critical issues for online reinforcement learning (RL). Existing methods achieve higher sample efficiency by adopting model-based methods, Q-ensemble, or better exploration mechanisms. We, instead,…

Machine Learning · Computer Science 2023-05-31 Jiafei Lyu , Le Wan , Zongqing Lu , Xiu Li

Consider a Markov decision process (MDP) that admits a set of state-action features, which can linearly express the process's probabilistic transition model. We propose a parametric Q-learning algorithm that finds an approximate-optimal…

Machine Learning · Computer Science 2019-06-07 Lin F. Yang , Mengdi Wang

It is believed that a model-based approach for reinforcement learning (RL) is the key to reduce sample complexity. However, the understanding of the sample optimality of model-based RL is still largely missing, even for the linear case.…

Machine Learning · Computer Science 2020-10-20 Qiwen Cui , Lin F. Yang

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

Recent techniques for approximating Nash equilibria in very large games leverage neural networks to learn approximately optimal policies (strategies). One promising line of research uses neural networks to approximate counterfactual regret…

Computer Science and Game Theory · Computer Science 2022-10-12 Stephen McAleer , Gabriele Farina , Marc Lanctot , Tuomas Sandholm

We study the problem of learning in zero-sum matrix games with repeated play and bandit feedback. Specifically, we focus on developing uncoupled algorithms that guarantee, without communication between players, the convergence of the…

Machine Learning · Computer Science 2026-04-20 Côme Fiegel , Pierre Ménard , Tadashi Kozuno , Michal Valko , Vianney Perchet

In practical multi-agent systems, agents often have diverse objectives, which makes the system more complex, as each agent's performance across multiple criteria depends on the joint actions of all agents, creating intricate strategic…

Multiagent Systems · Computer Science 2025-09-30 Yue Wang

Markov Potential Games (MPGs) form an important sub-class of Markov games, which are a common framework to model multi-agent reinforcement learning problems. In particular, MPGs include as a special case the identical-interest setting where…

Machine Learning · Computer Science 2024-08-16 Pragnya Alatur , Anas Barakat , Niao He