English
Related papers

Related papers: Anytime PSRO for Two-Player Zero-Sum Games

200 papers

Group distributionally robust optimization (GDRO) aims to develop models that perform well across $m$ distributions simultaneously. Existing GDRO algorithms can only process a fixed number of samples per iteration, either 1 or $m$, and…

Machine Learning · Computer Science 2025-05-22 Haomin Bai , Dingzhi Yu , Shuai Li , Haipeng Luo , Lijun Zhang

Unlike Poker where the action space $\mathcal{A}$ is discrete, differential games in the physical world often have continuous action spaces not amenable to discrete abstraction, rendering no-regret algorithms with…

Computer Science and Game Theory · Computer Science 2025-02-17 Mukesh Ghimire , Zhe Xu , Yi Ren

Standard reinforcement learning from human feedback (RLHF) approaches relying on parametric models like the Bradley-Terry model fall short in capturing the intransitivity and irrationality in human preferences. Recent advancements suggest…

Machine Learning · Computer Science 2024-10-08 Yue Wu , Zhiqing Sun , Huizhuo Yuan , Kaixuan Ji , Yiming Yang , Quanquan Gu

Cooperative games are those in which both agents share the same payoff structure. Value-based reinforcement-learning algorithms, such as variants of Q-learning, have been applied to learning cooperative games, but they only apply when the…

Machine Learning · Computer Science 2017-05-25 Leonid Peshkin , Kee-Eung Kim , Nicolas Meuleau , Leslie Pack Kaelbling

Cooperative games are those in which both agents share the same payoff structure. Value-based reinforcement-learning algorithms, such as variants of Q-learning, have been applied to learning cooperative games, but they only apply when the…

Artificial Intelligence · Computer Science 2014-08-08 Leonid Peshkin , Kee-Eung Kim , Nicolas Meuleau , Leslie Pack Kaelbling

This paper considers the design of fully distributed Nash equilibrium seeking strategies for multi-agent games. To develop fully distributed seeking strategies, two adaptive control laws, including a node-based control law and an edge-based…

Optimization and Control · Mathematics 2019-12-03 Maojiao Ye , Guoqiang Hu

Reinforcement learning (RL) policies often fail under dynamics that differ from training, a gap not fully addressed by domain randomization or existing adversarial RL methods. Distributionally robust RL provides a formal remedy but still…

Machine Learning · Computer Science 2026-04-16 Mintae Kim , Koushil Sreenath

We study the problem of computing an $\epsilon$-approximate Nash equilibrium of a two-player, bilinear game with a bounded payoff matrix $A \in \mathbb{R}^{m \times n}$, when the players' strategies are constrained to lie in simple sets. We…

Optimization and Control · Mathematics 2026-01-08 Ishani Karmarkar , Liam O'Carroll , Aaron Sidford

Much of recent success in multiagent reinforcement learning has been in two-player zero-sum games. In these games, algorithms such as fictitious self-play and minimax tree search can converge to an approximate Nash equilibrium. While…

Multiagent Systems · Computer Science 2019-12-11 Alexander Shmakov , John Lanier , Stephen McAleer , Rohan Achar , Cristina Lopes , Pierre Baldi

In this paper, we propose several new stochastic second-order algorithms for policy optimization that only require gradient and Hessian-vector product in each iteration, making them computationally efficient and comparable to policy…

Optimization and Control · Mathematics 2023-01-31 Jinsong Liu , Chenghan Xie , Qi Deng , Dongdong Ge , Yinyu Ye

Much of the advancement in Multi-Agent Reinforcement Learning (MARL) for imperfect-information games has historically depended on the manual, iterative refinement of algorithmic baselines. Recently, evolutionary coding agents powered by…

Computer Science and Game Theory · Computer Science 2026-05-11 Zun Li , John Schultz , Daniel Hennes , Marc Lanctot

The Colonel Blotto game, formulated by Emile Borel, involves players allocating limited resources to multiple battlefields simultaneously, with the winner being the one who allocates more resources to each battlefield. Computation of the…

Computer Science and Game Theory · Computer Science 2025-07-31 Debtoru Chatterjee , Girish Tiwari , Niladri Chatterjee

Trust Region Policy Optimization (TRPO) and Proximal Policy Optimization (PPO) are among the most successful policy gradient approaches in deep reinforcement learning (RL). While these methods achieve state-of-the-art performance across a…

Machine Learning · Computer Science 2020-06-22 Ahmed Touati , Amy Zhang , Joelle Pineau , Pascal Vincent

Reinforcement-based learning dynamics may exhibit several limitations when applied in a distributed setup. In (repeatedly-played) multi-player/action strategic-form games, and when each player applies an independent copy of the learning…

Computer Science and Game Theory · Computer Science 2025-11-25 Georgios C. Chasparis

We study a two-player zero-sum game in which the row player aims to maximize their payoff against a competing column player, under an unknown payoff matrix estimated through bandit feedback. We propose three algorithms based on the…

Machine Learning · Computer Science 2026-02-20 Elif Yılmaz , Christos Dimitrakakis

Model-free reinforcement learning methods such as the Proximal Policy Optimization algorithm (PPO) have successfully applied in complex decision-making problems such as Atari games. However, these methods suffer from high variances and high…

Machine Learning · Computer Science 2018-11-20 Feiyang Pan , Qingpeng Cai , An-Xiang Zeng , Chun-Xiang Pan , Qing Da , Hualin He , Qing He , Pingzhong Tang

Provably efficient Model-Based Reinforcement Learning (MBRL) based on optimism or posterior sampling (PSRL) is ensured to attain the global optimality asymptotically by introducing the complexity measure of the model. However, the…

Machine Learning · Computer Science 2022-09-19 Shenao Zhang

Reinforcement learning algorithms are fundamental to align large language models with human preferences and to enhance their reasoning capabilities. However, current reinforcement learning algorithms often suffer from training instability…

Machine Learning · Computer Science 2025-06-05 Yaru Hao , Li Dong , Xun Wu , Shaohan Huang , Zewen Chi , Furu Wei

In this paper, we present exploitability descent, a new algorithm to compute approximate equilibria in two-player zero-sum extensive-form games with imperfect information, by direct policy optimization against worst-case opponents. We prove…

Artificial Intelligence · Computer Science 2020-06-15 Edward Lockhart , Marc Lanctot , Julien Pérolat , Jean-Baptiste Lespiau , Dustin Morrill , Finbarr Timbers , Karl Tuyls

If a game has a Nash equilibrium with probability values that are either zero or Omega(1) then this equilibrium can be found exhaustively in polynomial time. Somewhat surprisingly, we show that there is a PTAS for the games whose equilibria…

Computer Science and Game Theory · Computer Science 2011-02-14 Constantinos Daskalakis , Christos H. Papadimitriou