中文
相关论文

相关论文: Offline Reinforcement Learning for Safer Blood Glu…

200 篇论文

Calculating mealtime insulin doses poses a significant challenge for individuals with Type 1 Diabetes (T1D). Doses should perfectly compensate for expected post-meal glucose excursions, requiring a profound understanding of the individual's…

定量方法 · 定量生物学 2024-06-24 Anas El Fathi , Elliott Pryor , Marc D. Breton

Offline reinforcement learning (RL) enables learning control policies by utilizing only prior experience, without any online interaction. This can allow robots to acquire generalizable skills from large and diverse datasets, without any…

机器学习 · 计算机科学 2021-09-24 Aviral Kumar , Anikait Singh , Stephen Tian , Chelsea Finn , Sergey Levine

Offline reinforcement learning (offline RL) offers a promising framework for developing control strategies in chemical process systems using historical data, without the risks or costs of online experimentation. This work investigates the…

系统与控制 · 电气工程与系统科学 2025-07-31 Alex Durkin , Jasper Stolte , Matthew Jones , Raghuraman Pitchumani , Bei Li , Christian Michler , Mehmet Mercangöz

Energy efficiency has become an integral aspect of modern computing infrastructure design, impacting the performance, cost, scalability, and durability of production systems. The incorporation of power actuation and sensing capabilities in…

机器学习 · 计算机科学 2026-01-19 Akhilesh Raj , Swann Perarnau , Aniruddha Gokhale , Solomon Bekele Abera

Deep brain stimulation (DBS) has shown great promise toward treating motor symptoms caused by Parkinson's disease (PD), by delivering electrical pulses to the Basal Ganglia (BG) region of the brain. However, DBS devices approved by the U.S.…

Blood glucose simulation allows the effectiveness of type 1 diabetes (T1D) management strategies to be evaluated without patient harm. Deep learning algorithms provide a promising avenue for extending simulator capabilities; however, these…

机器学习 · 计算机科学 2023-10-24 Harry Emerson , Ryan McConville , Matthew Guy

Safe Reinforcement Learning (RL) algorithms are typically evaluated under fixed training conditions. We investigate whether training-time safety guarantees transfer to deployment under distribution shift, using diabetes management as a…

机器学习 · 计算机科学 2026-05-26 Minjae Kwon , Josephine Lamp , Lu Feng

While the Artificial Pancreas is effective in regulating the blood glucose in the safe range of 70-180 mg/dl in type 1 diabetic patients, the high intra-patient variability, as well as exogenous meal disturbances, poses a serious challenge.…

系统与控制 · 电气工程与系统科学 2022-06-30 Bhabani Shankar Dey , Anirudh Nath , Abhilash Patel , Indra Narayan Kar

Patients with diabetes who are self-monitoring have to decide right before each meal how much insulin they should take. A standard bolus advisor exists, but has never actually been proven to be optimal in any sense. We challenged this rule…

机器学习 · 统计学 2020-07-24 Frédéric Logé , Erwan Le Pennec , Habiboulaye Amadou-Boubacar

Scheduling laboratory tests for ICU patients presents a significant challenge. Studies show that 20-40% of lab tests ordered in the ICU are redundant and could be eliminated without compromising patient safety. Prior work has leveraged…

机器学习 · 计算机科学 2024-02-13 Zongliang Ji , Anna Goldenberg , Rahul G. Krishnan

Recent advance in deep offline reinforcement learning (RL) has made it possible to train strong robotic agents from offline datasets. However, depending on the quality of the trained agents and the application being considered, it is often…

机器人学 · 计算机科学 2021-11-02 Seunghyun Lee , Younggyo Seo , Kimin Lee , Pieter Abbeel , Jinwoo Shin

Reinforcement learning is commonly associated with training of reward-maximizing (or cost-minimizing) agents, in other words, controllers. It can be applied in model-free or model-based fashion, using a priori or online collected system…

系统与控制 · 电气工程与系统科学 2022-09-01 Lukas Beckenbach , Pavel Osinenko , Stefan Streif

Control of blood glucose is essential for diabetes management. Current digital therapeutic approaches for subjects with Type 1 diabetes mellitus (T1DM) such as the artificial pancreas and insulin bolus calculators leverage machine learning…

计算机视觉与模式识别 · 计算机科学 2019-02-27 Kezhi Li , John Daniels , Chengyuan Liu , Pau Herrero , Pantelis Georgiou

Robust reinforcement learning (RL) aims to learn policies that remain effective despite uncertainties in its environment, which frequently arise in real-world applications due to variations in environment dynamics. The robust RL methods…

机器学习 · 计算机科学 2025-05-30 Linh Le Pham Van , Minh Hoang Nguyen , Hung Le , Hung The Tran , Sunil Gupta

We study the problem of safe offline reinforcement learning (RL), the goal is to learn a policy that maximizes long-term reward while satisfying safety constraints given only offline data, without further interaction with the environment.…

机器学习 · 计算机科学 2022-04-11 Haoran Xu , Xianyuan Zhan , Xiangyu Zhu

Self-monitoring of blood glucose (SMBG) and continuous glucose monitoring (CGM) are commonly used by type 1 diabetes (T1D) patients to measure glucose concentrations. The proposed adaptive basal-bolus algorithm (ABBA) supports inputs from…

系统与控制 · 电气工程与系统科学 2024-12-20 Qingnan Sun , Marko V. Jankovic , João Budzinski , Brett Moore , Peter Diem , Christoph Stettler , Stavroula G. Mougiakakou

Sample efficiency is critical when applying learning-based methods to robotic manipulation due to the high cost of collecting expert demonstrations and the challenges of on-robot policy learning through online Reinforcement Learning (RL).…

机器学习 · 计算机科学 2024-06-21 Arsh Tangri , Ondrej Biza , Dian Wang , David Klee , Owen Howell , Robert Platt

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…

机器学习 · 计算机科学 2023-06-02 Bingyi Kang , Xiao Ma , Yirui Wang , Yang Yue , Shuicheng Yan

Offline-to-online reinforcement learning (RL) improves sample efficiency by leveraging pre-collected datasets prior to online interaction. A key challenge, however, is learning an accurate critic in large state--action spaces with limited…

人工智能 · 计算机科学 2026-05-21 Andrew Choi , Wei Xu

Reinforcement learning (RL) in the real world necessitates the development of procedures that enable agents to explore without causing harm to themselves or others. The most successful solutions to the problem of safe RL leverage offline…

机器学习 · 计算机科学 2025-01-09 Alexander Quessy , Thomas Richardson , Sebastian East