English
Related papers

Related papers: Alleviating Matthew Effect of Offline Reinforcemen…

200 papers

Offline reinforcement learning (RL) aims to find a near-optimal policy using pre-collected datasets. In real-world scenarios, data collection could be costly and risky; therefore, offline RL becomes particularly challenging when the…

Machine Learning · Computer Science 2024-12-18 Ruizhe Shi , Yuyao Liu , Yanjie Ze , Simon S. Du , Huazhe Xu

We study offline-online reinforcement learning in linear mixture Markov decision processes (MDPs) under environment shift. In the offline phase, data are collected by an unknown behavior policy and may come from a mismatched environment,…

Machine Learning · Computer Science 2026-04-15 Zhongjun Zhang , Sean R. Sinclair

Two central paradigms have emerged in the reinforcement learning (RL) community: online RL and offline RL. In the online RL setting, the agent has no prior knowledge of the environment, and must interact with it in order to find an…

Machine Learning · Computer Science 2023-07-21 Andrew Wagenmaker , Aldo Pacchiano

How can we train a dialog model to produce better conversations by learning from human feedback, without the risk of humans teaching it harmful chat behaviors? We start by hosting models online, and gather human feedback from real-time,…

Online matching problems arise in many complex systems, from cloud services and online marketplaces to organ exchange networks, where timely, principled decisions are critical for maintaining high system performance. Traditional heuristics…

Machine Learning · Statistics 2025-10-09 Chiara Mignacco , Matthieu Jonckheere , Gilles Stoltz

Many advances that have improved the robustness and efficiency of deep reinforcement learning (RL) algorithms can, in one way or another, be understood as introducing additional objectives or constraints in the policy optimization step.…

Many modern approaches to offline Reinforcement Learning (RL) utilize behavior regularization, typically augmenting a model-free actor critic algorithm with a penalty measuring divergence of the policy from the offline data. In this work,…

Machine Learning · Computer Science 2021-03-16 Ilya Kostrikov , Jonathan Tompson , Rob Fergus , Ofir Nachum

Model-based offline reinforcement learning methods (RL) have achieved state-of-the-art performance in many decision-making problems thanks to their sample efficiency and generalizability. Despite these advancements, existing model-based…

Machine Learning · Computer Science 2024-01-23 Mao Hong , Zhiyue Zhang , Yue Wu , Yanxun Xu

In this study, we aim to enhance the arithmetic reasoning ability of Large Language Models (LLMs) through zero-shot prompt optimization. We identify a previously overlooked objective of query dependency in such optimization and elucidate…

Computation and Language · Computer Science 2024-03-08 Hao Sun , Alihan Hüyük , Mihaela van der Schaar

Offline-to-online (O2O) reinforcement learning (RL) pre-trains models on offline data and refines policies through online fine-tuning. However, existing O2O RL algorithms typically require maintaining the tedious offline datasets to…

Machine Learning · Computer Science 2025-02-24 Liyu Zhang , Haochi Wu , Xu Wan , Quan Kong , Ruilong Deng , Mingyang Sun

Offline-to-online deployment of reinforcement-learning (RL) agents must bridge two gaps: (1) the sim-to-real gap, where real systems add latency and other imperfections not present in simulation, and (2) the interaction gap, where policies…

Machine Learning · Computer Science 2026-02-12 Simon Sinong Zhan , Qingyuan Wu , Philip Wang , Frank Yang , Xiangyu Shi , Chao Huang , Qi Zhu

Model-based offline reinforcement learning (RL) is a compelling approach that addresses the challenge of learning from limited, static data by generating imaginary trajectories using learned models. However, these approaches often struggle…

Machine Learning · Computer Science 2024-12-04 Kwanyoung Park , Youngwoon Lee

The offline reinforcement learning (RL) problem aims to learn an optimal policy from historical data collected by one or more behavioural policies (experts) by interacting with an environment. However, the individual experts may be…

Cryptography and Security · Computer Science 2025-11-25 Navodita Sharma , Vishnu Vinod , Abhradeep Thakurta , Alekh Agarwal , Borja Balle , Christoph Dann , Aravindan Raghuveer

A compelling use case of offline reinforcement learning (RL) is to obtain a policy initialization from existing datasets followed by fast online fine-tuning with limited interaction. However, existing offline RL methods tend to behave…

Machine Learning · Computer Science 2024-01-23 Mitsuhiko Nakamoto , Yuexiang Zhai , Anikait Singh , Max Sobol Mark , Yi Ma , Chelsea Finn , Aviral Kumar , Sergey Levine

Offline reinforcement learning (RL) tasks require the agent to learn from a pre-collected dataset with no further interactions with the environment. Despite the potential to surpass the behavioral policies, RL-based methods are generally…

Machine Learning · Computer Science 2022-01-13 Minghuan Liu , Hanye Zhao , Zhengyu Yang , Jian Shen , Weinan Zhang , Li Zhao , Tie-Yan Liu

Reinforcement learning (RL) provides an appealing formalism for learning control policies from experience. However, the classic active formulation of RL necessitates a lengthy active exploration process for each behavior, making it…

Machine Learning · Computer Science 2021-04-27 Ashvin Nair , Abhishek Gupta , Murtaza Dalal , Sergey Levine

Offline reinforcement learning (RL) can in principle synthesize more optimal behavior from a dataset consisting only of suboptimal trials. One way that this can happen is by "stitching" together the best parts of otherwise suboptimal…

Machine Learning · Computer Science 2023-11-01 Joey Hong , Anca Dragan , Sergey Levine

Off-dynamics reinforcement learning (RL), where training and deployment transition dynamics are different, can be formulated as learning in a robust Markov decision process (RMDP) where uncertainties in transition dynamics are imposed.…

Machine Learning · Computer Science 2025-11-10 Yiting He , Zhishuai Liu , Weixin Wang , Pan Xu

Recommender Systems are becoming ubiquitous in many settings and take many forms, from product recommendation in e-commerce stores, to query suggestions in search engines, to friend recommendation in social networks. Current research…

Information Retrieval · Computer Science 2018-09-17 David Rohde , Stephen Bonner , Travis Dunlop , Flavian Vasile , Alexandros Karatzoglou

Offline reinforcement learning (offline RL) considers problems where learning is performed using only previously collected samples and is helpful for the settings in which collecting new data is costly or risky. In model-based offline RL,…

Machine Learning · Computer Science 2023-03-09 Mustafa O. Karabag , Ufuk Topcu