English
Related papers

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

200 papers

Reinforcement learning from self-play has recently reported many successes. Self-play, where the agents compete with themselves, is often used to generate training data for iterative policy improvement. In previous work, heuristic rules are…

Machine Learning · Computer Science 2020-09-15 Yuanyi Zhong , Yuan Zhou , Jian Peng

Nonsmooth sparsity constrained optimization encompasses a broad spectrum of applications in machine learning. This problem is generally non-convex and NP-hard. Existing solutions to this problem exhibit several notable limitations,…

Optimization and Control · Mathematics 2023-12-18 Ganzhao Yuan

We study model-based and model-free policy optimization in a class of nonzero-sum stochastic dynamic games called linear quadratic (LQ) deep structured games. In such games, players interact with each other through a set of weighted…

Computer Science and Game Theory · Computer Science 2020-12-15 Masoud Roudneshin , Jalal Arabneydi , Amir G. Aghdam

This paper studies how to efficiently update the saddle-point strategy, or security strategy of one player in a matrix game when the other player develops new actions in the game. It is well known that the saddle-point strategy of one…

Computer Science and Game Theory · Computer Science 2017-11-08 Lichun Li , Cedric Langbort

This paper develops a deep policy iteration method for high-dimensional finite-horizon mean-field games (MFG). We reformulate the game as a regenerative problem with deterministic cycles, which allows policy evaluation (PE), policy…

Numerical Analysis · Mathematics 2026-05-18 Shuixin Fang , Shupeng Wang , Zhen Wu , Hui Zhang , Tao Zhou

Safe policy improvement (SPI) is an offline reinforcement learning problem in which a new policy that reliably outperforms the behavior policy with high confidence needs to be computed using only a dataset and the behavior policy. Markov…

Artificial Intelligence · Computer Science 2025-08-20 Kasper Engelen , Guillermo A. Pérez , Marnix Suilen

We study agents competing against each other in a repeated network zero-sum game while applying the multiplicative weights update (MWU) algorithm with fixed learning rates. In our implementation, agents select their strategies…

Computer Science and Game Theory · Computer Science 2021-10-06 James P. Bailey , Sai Ganesh Nagarajan , Georgios Piliouras

We define a class of zero-sum games with combinatorial structure, where the best response problem of one player is to maximize a submodular function. For example, this class includes security games played on networks, as well as the problem…

Computer Science and Game Theory · Computer Science 2017-12-04 Bryan Wilder

We consider approximate dynamic programming for the infinite-horizon stationary $\gamma$-discounted optimal control problem formalized by Markov Decision Processes. While in the exact case it is known that there always exists an optimal…

Optimization and Control · Mathematics 2013-04-23 Boris Lesner , Bruno Scherrer

Softmax policy gradient is a popular algorithm for policy optimization in single-agent reinforcement learning, particularly since projection is not needed for each gradient update. However, in multi-agent systems, the lack of central…

Optimization and Control · Mathematics 2022-11-01 Runyu Zhang , Jincheng Mei , Bo Dai , Dale Schuurmans , Na Li

A core challenge in policy optimization in competitive Markov decision processes is the design of efficient optimization methods with desirable convergence and stability properties. To tackle this, we propose competitive policy optimization…

Machine Learning · Computer Science 2020-06-19 Manish Prajapat , Kamyar Azizzadenesheli , Alexander Liniger , Yisong Yue , Anima Anandkumar

Constrained Markov games offer a formal mathematical framework for modeling multi-agent reinforcement learning problems where the behavior of the agents is subject to constraints. In this work, we focus on the recently introduced class of…

Machine Learning · Computer Science 2024-02-29 Philip Jordan , Anas Barakat , Niao He

Entropy regularized algorithms such as Soft Q-learning and Soft Actor-Critic, recently showed state-of-the-art performance on a number of challenging reinforcement learning (RL) tasks. The regularized formulation modifies the standard RL…

Machine Learning · Statistics 2019-10-15 Elena Smirnova , Elvis Dohmatob

Nonzero-sum stochastic differential games with impulse controls offer a realistic and far-reaching modelling framework for applications within finance, energy markets, and other areas, but the difficulty in solving such problems has…

Numerical Analysis · Mathematics 2020-06-29 Diego Zabaljauregui

In recent years, solving optimization problems involving black-box simulators has become a point of focus for the machine learning community due to their ubiquity in science and engineering. The simulators describe a forward process…

Machine Learning · Computer Science 2024-06-07 Fabio Valerio Massoli , Tim Bakker , Thomas Hehn , Tribhuvanesh Orekondy , Arash Behboodi

In this paper, we consider a differential stochastic zero-sum game in which two players intervene by adopting impulse controls in a finite time horizon. We provide a numerical solution as an approximation of the value function, which turns…

Optimization and Control · Mathematics 2024-10-14 Antoine Zolome , Brahim El Asri

We study the problem of computing an approximate Nash equilibrium of continuous-action game without access to gradients. Such game access is common in reinforcement learning settings, where the environment is typically treated as a black…

Computer Science and Game Theory · Computer Science 2023-08-30 Carlos Martin , Tuomas Sandholm

In this paper, we propose a single-loop stochastic gradient algorithm for solving stochastic nonconvex-concave minimax optimization with nonlinear convex coupled constraints (MCC). The proposed method, SPACO (Stochastic Penalty-based…

Optimization and Control · Mathematics 2026-05-05 Qichao Cao , Shangzhi Zeng , Jin Zhang , Yuxuan Zhou

We study the game modification problem, where a benevolent game designer or a malevolent adversary modifies the reward function of a zero-sum Markov game so that a target deterministic or stochastic policy profile becomes the unique Markov…

Computer Science and Game Theory · Computer Science 2024-08-27 Young Wu , Jeremy McMahan , Yiding Chen , Yudong Chen , Xiaojin Zhu , Qiaomin Xie

Policy gradient (PG) methods have played an essential role in the empirical successes of reinforcement learning. In order to handle large state-action spaces, PG methods are typically used with function approximation. In this setting, the…