English
Related papers

Related papers: Beyond Pessimism: Offline Learning in KL-regulariz…

200 papers

An ideal strategy in zero-sum games should not only grant the player an average reward no less than the value of Nash equilibrium, but also exploit the (adaptive) opponents when they are suboptimal. While most existing works in Markov games…

Machine Learning · Computer Science 2022-06-15 Qinghua Liu , Yuanhao Wang , Chi Jin

Multi-Agent Reinforcement Learning (MARL) -- where multiple agents learn to interact in a shared dynamic environment -- permeates across a wide range of critical applications. While there has been substantial progress on understanding the…

Computer Science and Game Theory · Computer Science 2022-10-05 Shicong Cen , Yuejie Chi , Simon S. Du , Lin Xiao

Many offline reinforcement learning algorithms are underpinned by $f$-divergence regularization, but their sample complexity *defined with respect to regularized objectives* still lacks tight analyses, especially in terms of concrete data…

Machine Learning · Computer Science 2026-02-27 Qingyue Zhao , Kaixuan Ji , Heyang Zhao , Tong Zhang , Quanquan Gu

Motivated by the scarcity of accurate payoff feedback in practical applications of game theory, we examine a class of learning dynamics where players adjust their choices based on past payoff observations that are subject to noise and…

Optimization and Control · Mathematics 2016-06-03 Mario Bravo , Panayotis Mertikopoulos

We propose a reinforcement learning algorithm for stationary mean-field games, where the goal is to learn a pair of mean-field state and stationary policy that constitutes the Nash equilibrium. When viewing the mean-field state and the…

Machine Learning · Computer Science 2020-10-12 Qiaomin Xie , Zhuoran Yang , Zhaoran Wang , Andreea Minca

We propose projection-free sequential algorithms for linear-quadratic dynamics games. These policy gradient based algorithms are akin to Stackelberg leadership model and can be extended to model-free settings. We show that if the leader…

Systems and Control · Electrical Eng. & Systems 2019-11-13 Jingjing Bu , Lillian J. Ratliff , Mehran Mesbahi

While ERM suffices to attain near-optimal generalization error in the stochastic learning setting, this is not known to be the case in the online learning setting, where algorithms for general concept classes rely on computationally…

Machine Learning · Computer Science 2023-07-11 Angelos Assos , Idan Attias , Yuval Dagan , Constantinos Daskalakis , Maxwell Fishelson

Model-based offline reinforcement learning (RL) has made remarkable progress, offering a promising avenue for improving generalization with synthetic model rollouts. Existing works primarily focus on incorporating pessimism for policy…

Machine Learning · Computer Science 2024-01-12 Yuanzhao Zhai , Yiying Li , Zijian Gao , Xudong Gong , Kele Xu , Dawei Feng , Ding Bo , Huaimin Wang

While policy optimization algorithms have played an important role in recent empirical success of Reinforcement Learning (RL), the existing theoretical understanding of policy optimization remains rather limited -- they are either…

Machine Learning · Computer Science 2023-12-05 Qinghua Liu , Gellért Weisz , András György , Chi Jin , Csaba Szepesvári

We revisit the problem of solving two-player zero-sum games in the decentralized setting. We propose a simple algorithmic framework that simultaneously achieves the best rates for honest regret as well as adversarial regret, and in addition…

Computer Science and Game Theory · Computer Science 2018-06-07 Ehsan Asadi Kangarshahi , Ya-Ping Hsieh , Mehmet Fatih Sahin , Volkan Cevher

In this work, we present a new model-free and off-policy reinforcement learning (RL) algorithm, that is capable of finding a near-optimal policy with state-action observations from arbitrary behavior policies. Our algorithm, called the…

Optimization and Control · Mathematics 2025-07-21 Narim Jeong , Donghwan Lee , Niao He

Dynamic treatment regimes (DTRs) provide a principled framework for optimizing sequential decision-making in domains where decisions must adapt over time in response to individual trajectories, such as healthcare, education, and digital…

Machine Learning · Statistics 2026-01-30 Ruijia Zhang , Xiangyu Zhang , Zhengling Qi , Yue Wu , Yanxun Xu

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

Game theory is playing more and more important roles in understanding complex systems and in investigating intelligent machines with various uncertainties. As a starting point, we consider the classical two-player zero-sum linear-quadratic…

Optimization and Control · Mathematics 2022-04-20 Nian Liu , Lei Guo

In two-player zero-sum stochastic games, where two competing players make decisions under uncertainty, a pair of optimal strategies is traditionally described by Nash equilibrium and computed under the assumption that the players have…

Optimization and Control · Mathematics 2019-07-30 Yagiz Savas , Mohamadreza Ahmadi , Takashi Tanaka , Ufuk Topcu

Two-player complete-information game trees are perhaps the simplest possible setting for studying general-sum games and the computational problem of finding equilibria. These games admit a simple bottom-up algorithm for finding subgame…

Computer Science and Game Theory · Computer Science 2012-07-02 Michael L. Littman , Nishkam Ravi , Arjun Talwar , Martin Zinkevich

We analyze independent policy-gradient (PG) learning in $N$-player linear-quadratic (LQ) stochastic differential games. Each player employs a distributed policy that depends only on its own state and updates the policy independently using…

Optimization and Control · Mathematics 2026-02-19 Philipp Plank , Yufei Zhang

We present a novel observation about the behavior of offline reinforcement learning (RL) algorithms: on many benchmark datasets, offline RL can produce well-performing and safe policies even when trained with "wrong" reward labels, such as…

Machine Learning · Computer Science 2023-11-09 Anqi Li , Dipendra Misra , Andrey Kolobov , Ching-An Cheng

Offline Reinforcement Learning (RL) aims to learn policies from previously collected datasets without exploring the environment. Directly applying off-policy algorithms to offline RL usually fails due to the extrapolation error caused by…

Machine Learning · Computer Science 2022-02-24 Chenjia Bai , Lingxiao Wang , Zhuoran Yang , Zhihong Deng , Animesh Garg , Peng Liu , Zhaoran Wang

Reinforcement-based learning has attracted considerable attention both in modeling human behavior as well as in engineering, for designing measurement- or payoff-based optimization schemes. Such learning schemes exhibit several advantages,…

Machine Learning · Computer Science 2025-11-26 Georgios C. Chasparis