English
Related papers

Related papers: Adaptive prediction theory combining offline and o…

200 papers

One of the main challenges in reinforcement learning (RL) is that the agent has to make decisions that would influence the future performance without having complete knowledge of the environment. Dynamically adjusting the level of epistemic…

Machine Learning · Computer Science 2026-03-02 Yupeng Wu , Wenyun Li , Wenjie Huang , Chin Pang Ho

In this paper, we study the problem of efficient online reinforcement learning in the infinite horizon setting when there is an offline dataset to start with. We assume that the offline dataset is generated by an expert but with unknown…

Machine Learning · Computer Science 2024-02-05 Dengwang Tang , Rahul Jain , Botao Hao , Zheng Wen

Given the rapid rise in energy demand by data centers and computing systems in general, it is fundamental to incorporate energy considerations when designing (scheduling) algorithms. Machine learning can be a useful approach in practice by…

Data Structures and Algorithms · Computer Science 2021-12-07 Antonios Antoniadis , Peyman Jabbarzade Ganje , Golnoosh Shahkarami

Incorporating pre-collected offline data can substantially improve the sample efficiency of reinforcement learning (RL), but its benefits can break down when the transition dynamics in the offline dataset differ from those encountered…

Machine Learning · Computer Science 2026-01-22 Lingkai Kong , Haichuan Wang , Tonghan Wang , Guojun Xiong , Milind Tambe

We study the problem of uncertainty quantification via prediction sets, in an online setting where the data distribution may vary arbitrarily over time. Recent work develops online conformal prediction techniques that leverage regret…

Machine Learning · Computer Science 2023-02-16 Aadyot Bhatnagar , Huan Wang , Caiming Xiong , Yu Bai

Recent years have witnessed growing interest in the application of deep neural networks (DNNs) for receiver design, which can potentially be applied in complex environments without relying on knowledge of the channel model. However, the…

Information Theory · Computer Science 2023-02-14 Tomer Raviv , Sangwoo Park , Osvaldo Simeone , Yonina C. Eldar , Nir Shlezinger

Conformal prediction has emerged as a powerful framework for constructing distribution-free prediction sets with guaranteed coverage assuming only the exchangeability assumption. However, this assumption is often violated in online…

Machine Learning · Statistics 2025-11-07 Jungbin Jun , Ilsang Ohn

The stable combination of optimal feedback policies with online learning is studied in a new control-theoretic framework for uncertain nonlinear systems. The framework can be systematically used in transfer learning and sim-to-real…

Systems and Control · Electrical Eng. & Systems 2022-04-13 Brett T. Lopez , Jean-Jacques E. Slotine

We introduce an online mathematical framework for survival analysis, allowing real time adaptation to dynamic environments and censored data. This framework enables the estimation of event time distributions through an optimal second order…

Machine Learning · Computer Science 2024-02-09 Camila Fernandez , Pierre Gaillard , Joseph de Vilmarest , Olivier Wintenberger

To integrate strategic, tactical and operational decisions, the two-stage optimization has been widely used to guide dynamic decision making. In this paper, we study the two-stage stochastic programming for complex systems with unknown…

Optimization and Control · Mathematics 2019-10-15 Wei Xie , Yuan Yi , Hua Zheng

This paper studies the operation of multi-agent networks engaged in multi-task decision problems under the paradigm of simultaneous learning and adaptation. Two scenarios are considered: one in which a decision must be taken among multiple…

Signal Processing · Electrical Eng. & Systems 2019-12-13 Stefano Marano , Ali H. Sayed

End-to-end learning robotic manipulation with high data efficiency is one of the key challenges in robotics. The latest methods that utilize human demonstration data and unsupervised representation learning has proven to be a promising…

Robotics · Computer Science 2021-10-22 Jin Li , Xianyuan Zhan , Zixu Xiao , Guyue Zhou

Machine learning assumes a pivotal role in our data-driven world. The increasing scale of models and datasets necessitates quick and reliable algorithms for model training. This dissertation investigates adaptivity in machine learning…

Machine Learning · Computer Science 2023-11-20 Slavomír Hanzely

Reinforcement learning (RL) policies trained in simulation often suffer from severe performance degradation when deployed in real-world environments due to non-stationary dynamics. While Domain Randomization (DR) and meta-RL have been…

Machine Learning · Computer Science 2026-02-09 Aoi Yoshimura , Gouhei Tanaka

Offline-to-online reinforcement learning (RL) has emerged as a practical paradigm that leverages offline datasets for pretraining and online interactions for fine-tuning. However, its empirical behavior is highly inconsistent: design…

Machine Learning · Computer Science 2026-02-03 Lu Li , Tianwei Ni , Yihao Sun , Pierre-Luc Bacon

Diffusion models have recently shown promise in offline RL. However, these methods often suffer from high training costs and slow convergence, particularly when using transformer-based denoising backbones. While several optimization…

Machine Learning · Computer Science 2025-06-23 Zhiying Qiu , Tao Lin

In this work and the supporting Parts II [2] and III [3], we provide a rather detailed analysis of the stability and performance of asynchronous strategies for solving distributed optimization and adaptation problems over networks. We…

Systems and Control · Computer Science 2014-12-17 Xiaochuan Zhao , Ali H. Sayed

Being able to quickly adapt to changes in dynamics is paramount in model-based control for object manipulation tasks. In order to influence fast adaptation of the inverse dynamics model's parameters, data efficiency is crucial. Given…

Robotics · Computer Science 2022-11-28 Kristen Morse , Neha Das , Yixin Lin , Austin S. Wang , Akshara Rai , Franziska Meier

In this paper, we investigate the power of online learning in stochastic network optimization with unknown system statistics {\it a priori}. We are interested in understanding how information and learning can be efficiently incorporated…

Optimization and Control · Mathematics 2014-07-30 Longbo Huang , Xin Liu , Xiaohong Hao

Recent literature on online learning has focused on developing adaptive algorithms that take advantage of a regularity of the sequence of observations, yet retain worst-case performance guarantees. A complementary direction is to develop…

Machine Learning · Computer Science 2015-01-27 Ali Jadbabaie , Alexander Rakhlin , Shahin Shahrampour , Karthik Sridharan