English
Related papers

Related papers: COMAL: A Convergent Meta-Algorithm for Aligning LL…

200 papers

Reinforcement Learning from Human Feedback (RLHF) has become a cornerstone for aligning large language models (LLMs) with human values. However, existing approaches struggle to capture the multi-dimensional, distributional nuances of human…

Computation and Language · Computer Science 2025-05-20 Zelei Cheng , Xin-Qiang Cai , Yuting Tang , Pushi Zhang , Boming Yang , Masashi Sugiyama , Xinyu Xing

Computing Nash equilibrium policies is a central problem in multi-agent reinforcement learning that has received extensive attention both in theory and in practice. However, provable guarantees have been thus far either limited to fully…

Reverse Kullback-Leibler (KL) divergence-based regularization with respect to a fixed reference policy is widely used in modern reinforcement learning to preserve the desired traits of the reference policy and sometimes to promote…

Machine Learning · Computer Science 2026-02-05 Anupam Nayak , Tong Yang , Osman Yagan , Gauri Joshi , Yuejie Chi

We consider learning Nash equilibria in two-player zero-sum Markov Games with nonlinear function approximation, where the action-value function is approximated by a function in a Reproducing Kernel Hilbert Space (RKHS). The key challenge is…

Machine Learning · Computer Science 2022-08-11 Chris Junchi Li , Dongruo Zhou , Quanquan Gu , Michael I. Jordan

Existing alignment methods share a common topology of information flow, where reward information is collected from humans, modeled with preference learning, and used to tune language models. However, this shared topology has not been…

Machine Learning · Computer Science 2025-05-29 Tianyi Qiu , Fanzhi Zeng , Jiaming Ji , Dong Yan , Kaile Wang , Jiayi Zhou , Yang Han , Josef Dai , Xuehai Pan , Yaodong Yang

Traditional reinforcement learning from human feedback (RLHF) for large language models (LLMs) relies on expensive human-annotated datasets, while Reinforcement Learning from AI Feedback (RLAIF) also incurs significant costs, requiring the…

Computation and Language · Computer Science 2025-10-09 Shangjian Yin , Zhepei Wei , Xinyu Zhu , Wei-Lin Chen , Yu Meng

Reinforcement learning has been shown to be an effective strategy for automatically training policies for challenging control problems. Focusing on non-cooperative multi-agent systems, we propose a novel reinforcement learning framework for…

Computer Science and Game Theory · Computer Science 2022-06-08 Kishor Jothimurugan , Suguman Bansal , Osbert Bastani , Rajeev Alur

We study the repeated congestion game, in which multiple populations of players share resources, and make, at each iteration, a decentralized decision on which resources to utilize. We investigate the following question: given a model of…

Machine Learning · Computer Science 2014-08-04 Walid Krichene , Benjamin Drighès , Alexandre M. Bayen

Reinforcement Learning from Human Feedback (RLHF) has emerged as a important paradigm for aligning large language models (LLMs) with human preferences during post-training. This framework typically involves two stages: first, training a…

Machine Learning · Computer Science 2025-04-08 Wenyuan Xu , Xiaochen Zuo , Chao Xin , Yu Yue , Lin Yan , Yonghui Wu

We develop provably efficient reinforcement learning algorithms for two-player zero-sum finite-horizon Markov games with simultaneous moves. To incorporate function approximation, we consider a family of Markov games where the reward…

Machine Learning · Computer Science 2020-06-25 Qiaomin Xie , Yudong Chen , Zhaoran Wang , Zhuoran Yang

Reinforcement Learning from Human Feedback (RLHF) has emerged as a key technique for post-training large language models. Despite its empirical success, the theoretical understanding of RLHF is still limited, as learning the KL-regularized…

Machine Learning · Computer Science 2025-10-29 Di Wu , Chengshuai Shi , Jing Yang , Cong Shen

In general, two-agent decision-making problems can be modeled as a two-player game, and a typical solution is to find a Nash equilibrium in such game. Counterfactual regret minimization (CFR) is a well-known method to find a Nash…

Computer Science and Game Theory · Computer Science 2020-12-07 Huale Li , Xuan Wang , Shuhan Qi , Jiajia Zhang , Yang Liu , Yulin Wu , Fengwei Jia

Computational tractability and social welfare (aka. efficiency) of equilibria are two fundamental but in general orthogonal considerations in algorithmic game theory. Nevertheless, we show that when (approximate) full efficiency can be…

Computer Science and Game Theory · Computer Science 2025-01-10 Ioannis Anagnostides , Tuomas Sandholm

As Large Language Models (LLMs) integrate into our social and economic interactions, we need to deepen our understanding of how humans respond to LLMs opponents in strategic settings. We present the results of the first controlled…

General Economics · Economics 2025-05-19 Darija Barak , Miguel Costa-Gomes

Reinforcement Learning from Human Feedback (RLHF) is an effective approach for aligning language models to human preferences. Central to RLHF is learning a reward function for scoring human preferences. Two main approaches for learning a…

Aligning large language models (LLMs) with human preferences has become essential for safe and beneficial AI deployment. While Reinforcement Learning from Human Feedback (RLHF) established the dominant paradigm, a proliferation of…

Artificial Intelligence · Computer Science 2026-01-13 Tarun Raheja , Nilay Pochhi

This paper investigates posterior sampling algorithms for competitive reinforcement learning (RL) in the context of general function approximations. Focusing on zero-sum Markov games (MGs) under two critical settings, namely self-play and…

Machine Learning · Computer Science 2023-11-01 Shuang Qiu , Ziyu Dai , Han Zhong , Zhaoran Wang , Zhuoran Yang , Tong Zhang

Reinforcement Learning from Human Feedback (RLHF) is crucial for aligning Large Language Models (LLMs) with human values. However, RLHF has been continuously challenged by its high complexity in implementation and computation consumption,…

Machine Learning · Computer Science 2026-03-24 Yuhao Du , Zhuo Li , Pengyu Cheng , Zhihong Chen , Yuejiao Xie , Xiang Wan , Anningzhe Gao

In this paper, we investigate the impact of introducing relative entropy regularization on the Nash Equilibria (NE) of General-Sum $N$-agent games, revealing the fact that the NE of such games conform to linear Gaussian policies. Moreover,…

Computer Science and Game Theory · Computer Science 2024-09-16 Muhammad Aneeq uz Zaman , Shubham Aggarwal , Melih Bastopcu , Tamer Başar

The thriving field of multi-agent reinforcement learning (MARL) studies how a group of interacting agents make decisions autonomously in a shared dynamic environment. Existing theoretical studies in this area suffer from at least two of the…

Machine Learning · Computer Science 2025-12-02 Na Li , Yuchen Jiao , Hangguan Shan , Shefeng Yan