English
Related papers

Related papers: Unregularized Linear Convergence in Zero-Sum Game …

200 papers

We investigate Reinforcement Learning from Human Feedback (RLHF) in the context of a general preference oracle. In particular, we do not assume the existence of a reward function and an oracle preference signal drawn from the Bradley-Terry…

Machine Learning · Computer Science 2024-11-13 Chenlu Ye , Wei Xiong , Yuheng Zhang , Hanze Dong , Nan Jiang , Tong Zhang

We study reinforcement learning for two-player zero-sum Markov games with simultaneous moves in the finite-horizon setting, where the transition kernel of the underlying Markov games can be parameterized by a linear function over the…

Machine Learning · Computer Science 2022-04-21 Zixiang Chen , Dongruo Zhou , Quanquan Gu

In this work, we introduce the concept of non-negative weighted regret, an extension of non-negative regret \cite{anagnostides2022last} in games. Investigating games with non-negative weighted regret helps us to understand games with…

Computer Science and Game Theory · Computer Science 2025-05-22 Nanxiang Zhou , Jing Dong , Baoxiang Wang

Motivated by Generative Adversarial Networks, we study the computation of Nash equilibrium in concave network zero-sum games (NZSGs), a multiplayer generalization of two-player zero-sum games first proposed with linear payoffs. Extending…

Machine Learning · Computer Science 2020-07-13 Amit Kadan , Hu Fu

Reinforcement Learning from Human Feedback (RLHF) assumes annotator preferences reflect stable internal states. We challenge this through three experiments spanning the preference pipeline. In a human choice blindness study, 91% of…

Computation and Language · Computer Science 2026-03-10 Wenbin Wu

Our work focuses on extra gradient learning algorithms for finding Nash equilibria in bilinear zero-sum games. The proposed method, which can be formally considered as a variant of Optimistic Mirror Descent…

Computer Science and Game Theory · Computer Science 2022-03-09 Michail Fasoulakis , Evangelos Markakis , Yannis Pantazis , Constantinos Varsos

This paper studies post-training large language models (LLMs) using preference feedback from a powerful oracle to help a model iteratively improve over itself. The typical approach for post-training LLMs involves Reinforcement Learning from…

Machine Learning · Computer Science 2024-04-08 Corby Rosset , Ching-An Cheng , Arindam Mitra , Michael Santacroce , Ahmed Awadallah , Tengyang Xie

Reinforcement Learning from Human Feedback (RLHF) plays a significant role in aligning Large Language Models (LLMs) with human preferences. While RLHF with expected reward constraints can be formulated as a primal-dual optimization problem,…

Machine Learning · Computer Science 2026-02-26 Yining Li , Peizhong Ju , Ness Shroff

In this work, we study the sample complexity of obtaining a Nash equilibrium (NE) estimate in two-player zero-sum matrix games with noisy feedback. Specifically, we propose a novel algorithm that repeatedly solves linear programs (LPs) to…

Optimization and Control · Mathematics 2026-02-16 Jiashuo Jiang , Mengxiao Zhang

Accurately aligning large language models (LLMs) with human preferences is crucial for informing fair, economically sound, and statistically efficient decision-making processes. However, we argue that the predominant approach for aligning…

Machine Learning · Statistics 2025-08-26 Jiancong Xiao , Ziniu Li , Xingyu Xie , Emily Getzen , Cong Fang , Qi Long , Weijie J. Su

This paper studies the convergence of the Optimistic Multiplicative Weights Update algorithm (OMWU) in two player zero-sum games. Recent works have identified instances on which the last-iterate of OMWU can converge arbitrarily slowly, but…

Computer Science and Game Theory · Computer Science 2026-05-14 John Lazarsfeld , Anas Barakat , Georgios Piliouras , Antonios Varvitsiotis , Andre Wibisono

Zero-sum games are a fundamental setting for adversarial training and decision-making in multi-agent learning (MAL). Existing methods often ensure convergence to (approximate) Nash equilibria by introducing a form of regularization. Yet,…

Multiagent Systems · Computer Science 2026-02-10 Tuo Zhang , Leonardo Stella

Alignment via reinforcement learning from human feedback (RLHF) has become the dominant paradigm for controlling the quality of outputs from large language models (LLMs). However, existing theories do not provide strong justification for…

Machine Learning · Computer Science 2026-05-19 Jihun Yun , Juno Kim , Jongho Park , Junhyuck Kim , Jongha Jon Ryu , Jaewoong Cho , Kwang-Sung Jun

We study the global convergence of policy optimization for finding the Nash equilibria (NE) in zero-sum linear quadratic (LQ) games. To this end, we first investigate the landscape of LQ games, viewing it as a nonconvex-nonconcave…

Machine Learning · Computer Science 2021-02-12 Kaiqing Zhang , Zhuoran Yang , Tamer Başar

Consider a strongly monotone game where the players' utility functions include a reward function and a linear term for each dimension, with coefficients that are controlled by the manager. Gradient play converges to a unique Nash…

Multiagent Systems · Computer Science 2026-02-25 Siddharth Chandak , Ilai Bistritz , Nicholas Bambos

Reinforcement Learning from Human Feedback (RLHF) has greatly improved the performance of modern Large Language Models (LLMs). The RLHF process is resource-intensive and technically challenging, generally requiring a large collection of…

Reinforcement Learning from Human Feedback (RLHF) aligns language models to human preferences by employing a singular reward model derived from preference data. However, such an approach overlooks the rich diversity of human preferences…

Computation and Language · Computer Science 2024-12-30 Souradip Chakraborty , Jiahao Qiu , Hui Yuan , Alec Koppel , Furong Huang , Dinesh Manocha , Amrit Singh Bedi , Mengdi Wang

Reinforcement Learning from Human Feedback (RLHF) allows us to train models, such as language models (LMs), to follow complex human preferences. In RLHF for LMs, we first train an LM using supervised fine-tuning, sample pairs of responses,…

Machine Learning · Computer Science 2025-07-22 Johannes Ackermann , Takashi Ishida , Masashi Sugiyama

Constructing effective algorithms to converge to Nash Equilibrium (NE) is an important problem in algorithmic game theory. Prior research generally posits that the upper bound on the convergence rate for games is $O\left(T^{-1/2}\right)$.…

Computer Science and Game Theory · Computer Science 2024-09-06 Qi Ju , Falin Hei , Yuxuan Liu , Zhemei Fang , Yunfeng Luo

We study estimation and statistical inference for reward models used in aligning large language models (LLMs). A key component of LLM alignment is reinforcement learning from human feedback (RLHF), where humans compare pairs of…

Machine Learning · Statistics 2025-12-04 Pangpang Liu , Junwei Lu , Will Wei Sun