English
Related papers

Related papers: Understanding the performance gap between online a…

200 papers

Recently, Offline Reinforcement Learning (RL) has achieved remarkable progress with the emergence of various algorithms and datasets. However, these methods usually focus on algorithmic advancements, ignoring that many low-level…

Machine Learning · Computer Science 2023-06-02 Bingyi Kang , Xiao Ma , Yirui Wang , Yang Yue , Shuicheng Yan

We present a novel unified bilevel optimization-based framework, \textsf{PARL}, formulated to address the recently highlighted critical issue of policy alignment in reinforcement learning using utility or preference-based feedback. We…

Machine Learning · Computer Science 2024-05-02 Souradip Chakraborty , Amrit Singh Bedi , Alec Koppel , Dinesh Manocha , Huazheng Wang , Mengdi Wang , Furong Huang

Reinforcement learning from human or AI feedback (RLHF / RLAIF) has become the standard paradigm for aligning large language models (LLMs). However, most pipelines rely on a single reward model (RM), limiting alignment quality and risking…

Artificial Intelligence · Computer Science 2025-10-06 Xinle Wu , Yao Lu

Offline reinforcement learning (RL) refers to the problem of learning policies entirely from a large batch of previously collected data. This problem setting offers the promise of utilizing such datasets to acquire policies without any…

Machine Learning · Computer Science 2020-11-24 Tianhe Yu , Garrett Thomas , Lantao Yu , Stefano Ermon , James Zou , Sergey Levine , Chelsea Finn , Tengyu Ma

Reinforcement learning serves as a potent tool for modeling dynamic user interests within recommender systems, garnering increasing research attention of late. However, a significant drawback persists: its poor data efficiency, stemming…

Information Retrieval · Computer Science 2023-08-23 Xiaocong Chen , Siyu Wang , Julian McAuley , Dietmar Jannach , Lina Yao

Language model alignment methods such as reinforcement learning from human feedback (RLHF) have led to impressive advances in language model capabilities, but are limited by a widely observed phenomenon known as overoptimization, where the…

Artificial Intelligence · Computer Science 2025-02-19 Audrey Huang , Wenhao Zhan , Tengyang Xie , Jason D. Lee , Wen Sun , Akshay Krishnamurthy , Dylan J. Foster

We study offline meta-reinforcement learning, a practical reinforcement learning paradigm that learns from offline data to adapt to new tasks. The distribution of offline data is determined jointly by the behavior policy and the task.…

Machine Learning · Computer Science 2022-06-22 Haoqi Yuan , Zongqing Lu

Offline reinforcement learning enables sample-efficient policy acquisition without risky online interaction, yet policies trained on static datasets remain brittle under action-space perturbations such as actuator faults. This study…

Robotics · Computer Science 2026-03-02 Shingo Ayabe , Hiroshi Kera , Kazuhiko Kawamoto

Learning policies from previously recorded data is a promising direction for real-world robotics tasks, as online learning is often infeasible. Dexterous manipulation in particular remains an open problem in its general form. The…

The recent development of reinforcement learning (RL) has boosted the adoption of online RL for wireless radio resource management (RRM). However, online RL algorithms require direct interactions with the environment, which may be…

Information Theory · Computer Science 2023-11-21 Kun Yang , Cong Shen , Jing Yang , Shu-ping Yeh , Jerry Sydir

Flow Matching (FM) has shown remarkable ability in modeling complex distributions and achieves strong performance in offline imitation learning for cloning expert behaviors. However, despite its behavioral cloning expressiveness, FM-based…

Machine Learning · Computer Science 2025-10-14 Zhenglin Wan , Jingxuan Wu , Xingrui Yu , Chubin Zhang , Mingcong Lei , Bo An , Ivor Tsang

In offline reinforcement learning (RL), we seek to utilize offline data to evaluate (or learn) policies in scenarios where the data are collected from a distribution that substantially differs from that of the target policy to be evaluated.…

Machine Learning · Computer Science 2021-03-09 Ruosong Wang , Yifan Wu , Ruslan Salakhutdinov , Sham M. Kakade

Standard reinforcement learning from human feedback (RLHF) trains a reward model on pairwise preference data and then uses it for policy optimization. However, while reward models are optimized to capture relative preferences, existing…

Machine Learning · Computer Science 2026-02-05 Kyuseong Choi , Dwaipayan Saha , Woojeong Kim , Anish Agarwal , Raaz Dwivedi

Reinforcement Learning (RL) is notoriously data-inefficient, which makes training on a real robot difficult. While model-based RL algorithms (world models) improve data-efficiency to some extent, they still require hours or days of…

Machine Learning · Computer Science 2023-10-25 Yunhai Feng , Nicklas Hansen , Ziyan Xiong , Chandramouli Rajagopalan , Xiaolong Wang

Reinforcement Learning with Human Feedback (RLHF) has emerged as an influential technique, enabling the alignment of large language models (LLMs) with human preferences. Despite the promising potential of RLHF, how to protect user…

Machine Learning · Computer Science 2025-02-26 Jiaming Zhang , Mingxi Lei , Meng Ding , Mengdi Li , Zihang Xiang , Difei Xu , Jinhui Xu , Di Wang

Inverse Reinforcement Learning (IRL) -- the problem of learning reward functions from demonstrations of an \emph{expert policy} -- plays a critical role in developing intelligent systems. While widely used in applications, theoretical…

Machine Learning · Statistics 2024-02-13 Lei Zhao , Mengdi Wang , Yu Bai

Reinforcement learning from human feedback (RLHF) is a widely used method for aligning large language models with human preferences. However, RLHF often suffers from reward model overoptimisation, in which models overfit to the reward…

Machine Learning · Computer Science 2025-09-30 Lorenz Wolf , Robert Kirk , Mirco Musolesi

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…

Computation and Language · Computer Science 2024-06-18 Rui Zheng , Hongyi Guo , Zhihan Liu , Xiaoying Zhang , Yuanshun Yao , Xiaojun Xu , Zhaoran Wang , Zhiheng Xi , Tao Gui , Qi Zhang , Xuanjing Huang , Hang Li , Yang Liu

Learning from human feedback (LHF) -- and in particular learning from pairwise preferences -- has recently become a crucial ingredient in training large language models (LLMs), and has been the subject of much research. Most recent works…

Machine Learning · Computer Science 2024-01-11 Vincent Dumoulin , Daniel D. Johnson , Pablo Samuel Castro , Hugo Larochelle , Yann Dauphin

Online reinforcement learning from human feedback (RLHF) has emerged as a promising paradigm for aligning large language models (LLMs) by continuously collecting new preference feedback during training. A foundational challenge in this…

Machine Learning · Computer Science 2026-05-07 Zhen-Yu Zhang , Yuting Tang , Jiandong Zhang , Lanjihong Ma , Masashi Sugiyama