中文
相关论文

相关论文: Structure from Strategic Interaction & Uncertainty…

200 篇论文

Recent advances in aligning Large Language Models with human preferences have benefited from larger reward models and better preference data. However, most of these methodologies rely on the accuracy of the reward model. The reward models…

人工智能 · 计算机科学 2024-11-01 Debangshu Banerjee , Aditya Gopalan

Nash Learning from Human Feedback is a game-theoretic framework for aligning large language models (LLMs) with human preferences by modeling learning as a two-player zero-sum game. However, using raw preference as the payoff in the game…

计算机科学与博弈论 · 计算机科学 2025-05-28 Zhekun Shi , Kaizhao Liu , Qi Long , Weijie J. Su , Jiancong Xiao

Model-based algorithms -- algorithms that explore the environment through building and utilizing an estimated model -- are widely used in reinforcement learning practice and theoretically shown to achieve optimal sample efficiency for…

机器学习 · 计算机科学 2021-02-09 Qinghua Liu , Tiancheng Yu , Yu Bai , Chi Jin

Ensuring that AI systems make strategic decisions aligned with the specified preferences in adversarial sequential interactions is a critical challenge for developing trustworthy AI systems, especially when the environment is stochastic and…

计算机科学与博弈论 · 计算机科学 2025-01-28 Abhishek Ninad Kulkarni , Jie Fu , Ufuk Topcu

Reinforcement Learning from Human Feedback (RLHF), the standard for aligning Large Language Models (LLMs) with human values, is known to fail to satisfy properties that are intuitively desirable, such as respecting the preferences of the…

人工智能 · 计算机科学 2025-02-03 Roberto-Rafael Maura-Rivero , Marc Lanctot , Francesco Visin , Kate Larson

The standard Reinforcement Learning from Human Feedback (RLHF) framework primarily focuses on optimizing the performance of large language models using pre-collected prompts. However, collecting prompts that provide comprehensive coverage…

Reinforcement learning from human feedback (RLHF) has emerged as a central framework for aligning large language models (LLMs) with human preferences. Despite its practical success, RLHF raises fundamental statistical questions because it…

机器学习 · 统计学 2026-04-06 Pangpang Liu , Chengchun Shi , Will Wei Sun

Artificial intelligence (AI) has surpassed top human players in a variety of games. In imperfect information games, these achievements have primarily been driven by Counterfactual Regret Minimization (CFR) and its variants for computing…

计算机科学与博弈论 · 计算机科学 2025-05-29 Qi Ju , Thomas Tellier , Meng Sun , Zhemei Fang , Yunfeng Luo

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…

最优化与控制 · 数学 2016-06-03 Mario Bravo , Panayotis Mertikopoulos

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…

机器学习 · 计算机科学 2021-02-12 Kaiqing Zhang , Zhuoran Yang , Tamer Başar

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…

机器学习 · 计算机科学 2024-10-08 Yue Wu , Zhiqing Sun , Huizhuo Yuan , Kaixuan Ji , Yiming Yang , Quanquan Gu

The game-theoretic risk management framework put forth in the precursor work "Towards a Theory of Games with Payoffs that are Probability-Distributions" (arXiv:1506.07368 [q-fin.EC]) is herein extended by algorithmic details on how to…

综合经济学 · 经济学 2020-04-10 Stefan Rass

Game theory is a very profound study on distributed decision-making behavior and has been extensively developed by many scholars. However, many existing works rely on certain strict assumptions such as knowing the opponent's private…

计算机科学与博弈论 · 计算机科学 2020-04-21 Kuo Chun Tsai , Zhu Han

We study a finite-horizon two-person zero-sum risk-sensitive stochastic game for continuous-time Markov chains and Borel state and action spaces, in which payoff rates, transition rates and terminal reward functions are allowed to be…

最优化与控制 · 数学 2021-03-09 Junyu Zhang , Xianping Guo , Li Xia

We develop a flexible stochastic approximation framework for analyzing the long-run behavior of learning in games (both continuous and finite). The proposed analysis template incorporates a wide array of popular learning algorithms,…

计算机科学与博弈论 · 计算机科学 2023-07-04 Panayotis Mertikopoulos , Ya-Ping Hsieh , Volkan Cevher

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…

机器学习 · 计算机科学 2020-09-15 Yuanyi Zhong , Yuan Zhou , Jian Peng

In this paper, we propose a passivity-based methodology for analysis and design of reinforcement learning in multi-agent finite games. Starting from a known exponentially-discounted reinforcement learning scheme, we show that convergence to…

最优化与控制 · 数学 2024-10-30 Bolin Gao , Lacra Pavel

Reinforcement learning from human feedback (RLHF) has emerged as an effective approach to aligning large language models (LLMs) to human preferences. RLHF contains three steps, i.e., human preference collecting, reward learning, and policy…

计算与语言 · 计算机科学 2024-03-29 Hao Lang , Fei Huang , Yongbin Li

A large body of research is currently investigating on the connection between machine learning and game theory. In this work, game theory notions are injected into a preference learning framework. Specifically, a preference learning problem…

机器学习 · 计算机科学 2018-12-20 Mirko Polato , Fabio Aiolli

This article is related to risk-sensitive nonzero-sum stochastic differential games in the Markovian framework. This game takes into account the attitudes of the players toward risk and the utility is of exponential form. We show the…

最优化与控制 · 数学 2014-12-04 Said Hamadène , Rui Mu