English
Related papers

Related papers: Offline Supervised Learning V.S. Online Direct Pol…

200 papers

Learning control policies offline from pre-recorded datasets is a promising avenue for solving challenging real-world problems. However, available datasets are typically of mixed quality, with a limited number of the trajectories that we…

This paper presents a novel methodology to tackle feedback optimal control problems in scenarios where the exact state of the controlled process is unknown. It integrates data assimilation techniques and optimal control solvers to manage…

Optimization and Control · Mathematics 2024-04-10 Siming Liang , Ruoyu Hu , Feng Bao , Richard Archibald , Guannan Zhang

The off-policy learning paradigm allows for recommender systems and general ranking applications to be framed as decision-making problems, where we aim to learn decision policies that optimize an unbiased offline estimate of an online…

Machine Learning · Computer Science 2024-08-15 Shashank Gupta , Olivier Jeunen , Harrie Oosterhuis , Maarten de Rijke

Offline learning is a key part of making reinforcement learning (RL) useable in real systems. Offline RL looks at scenarios where there is data from a system's operation, but no direct access to the system when learning a policy. Recent…

Machine Learning · Computer Science 2021-03-18 Arthur Argenson , Gabriel Dulac-Arnold

Offline reinforcement learning (RL) aims to learn the optimal policy from a fixed dataset generated by behavior policies without additional environment interactions. One common challenge that arises in this setting is the…

Machine Learning · Computer Science 2026-02-06 Songyuan Zhang , Oswin So , H. M. Sabbir Ahmad , Eric Yang Yu , Matthew Cleaveland , Mitchell Black , Chuchu Fan

This paper proposes an off-policy risk-sensitive reinforcement learning based control framework for stabilization of a continuous-time nonlinear system that subjects to additive disturbances, input saturation, and state constraints. By…

Systems and Control · Electrical Eng. & Systems 2022-04-21 Cong Li , Qingchen Liu , Zhehua Zhou , Martin Buss , Fangzhou Liu

Recent Offline Reinforcement Learning methods have succeeded in learning high-performance policies from fixed datasets of experience. A particularly effective approach learns to first identify and then mimic optimal decision-making…

Machine Learning · Computer Science 2023-12-12 Jake Grigsby , Yanjun Qi

Offline reinforcement learning (RL) offers a powerful paradigm for data-driven control. Compared to model-free approaches, offline model-based RL (MBRL) explicitly learns a world model from a static dataset and uses it as a surrogate…

Machine Learning · Computer Science 2026-02-02 Jiayu Chen , Le Xu , Aravind Venugopal , Jeff Schneider

Policy learning (PL) is a module of a task-oriented dialogue system that trains an agent to make actions in each dialogue turn. Imitating human action is a fundamental problem of PL. However, both supervised learning (SL) and reinforcement…

Computation and Language · Computer Science 2023-05-09 Zhoujian Sun , Chenyang Zhao , Zhengxing Huang , Nai Ding

Offline-to-online reinforcement learning harnesses the stability of offline pretraining and the flexibility of online fine-tuning. A key challenge lies in the non-stationary distribution shift between offline datasets and the evolving…

Machine Learning · Computer Science 2026-05-15 Letian Yang , Xu Liu , Yiqiang Lu , Jian Liu , Weiqiang Wang , Shuai Li

We develop an optimization-based framework for joint real-time trajectory planning and feedback control of feedback-linearizable systems. To achieve this goal, we define a target trajectory as the optimal solution of a time-varying…

Systems and Control · Electrical Eng. & Systems 2020-03-17 Tianqi Zheng , John Simpson-Porco , Enrique Mallada

Reinforcement learning (RL) has shown promise for decision-making tasks in real-world applications. One practical framework involves training parameterized policy models from an offline dataset and subsequently deploying them in an online…

Machine Learning · Computer Science 2023-03-14 Ziniu Li , Ke Xu , Liu Liu , Lanqing Li , Deheng Ye , Peilin Zhao

Model predictive control is a prominent approach to construct a feedback control loop for dynamical systems. Due to real-time constraints, the major challenge in MPC is to solve model-based optimal control problems in a very short amount of…

Optimization and Control · Mathematics 2020-12-15 Sina Ober-Blöbaum , Sebastian Peitz

Offline model-based optimization (MBO) seeks to discover high-performing designs using only a fixed dataset of past evaluations. Most existing methods rely on learning a surrogate model via regression and implicitly assume that good…

Machine Learning · Computer Science 2026-03-05 Shen-Huan Lyu , Rong-Xi Tan , Ke Xue , Yi-Xiao He , Yu Huang , Qingfu Zhang , Chao Qian

We study learning control in an online reset-free lifelong learning scenario, where mistakes can compound catastrophically into the future and the underlying dynamics of the environment may change. Traditional model-free policy learning…

Machine Learning · Computer Science 2020-06-30 Kevin Lu , Igor Mordatch , Pieter Abbeel

This paper proposes an Online Control-Informed Learning (OCIL) framework, which employs the well-established optimal control and state estimation techniques in the field of control to solve a broad class of learning tasks in an online…

Optimization and Control · Mathematics 2025-03-12 Zihao Liang , Tianyu Zhou , Zehui Lu , Shaoshuai Mou

This paper examines the problem of real-time optimization of networked systems and develops online algorithms that steer the system towards the optimal trajectory without explicit knowledge of the system model. The problem is modeled as a…

Optimization and Control · Mathematics 2019-10-01 Yue Chen , Andrey Bernstein , Adithya Devraj , Sean Meyn

The goal of this tutorial is to introduce key models, algorithms, and open questions related to the use of optimization methods for solving problems arising in machine learning. It is written with an INFORMS audience in mind, specifically…

Machine Learning · Statistics 2017-07-03 Frank E. Curtis , Katya Scheinberg

We study data poisoning attacks in the online setting where training items arrive sequentially, and the attacker may perturb the current item to manipulate online learning. Importantly, the attacker has no knowledge of future training items…

Machine Learning · Computer Science 2019-06-03 Xuezhou Zhang , Xiaojin Zhu , Laurent Lessard

Offline reinforcement learning allows training reinforcement learning models on data from live deployments. However, it is limited to choosing the best combination of behaviors present in the training data. In contrast, simulation…

Machine Learning · Computer Science 2024-09-24 Eshagh Kargar , Ville Kyrki