English
Related papers

Related papers: Tracking Drift: Variation-Aware Entropy Scheduling…

200 papers

Deploying robust machine learning models has to account for concept drifts arising due to the dynamically changing and non-stationary nature of data. Addressing drifts is particularly imperative in the security domain due to the…

Cryptography and Security · Computer Science 2022-06-16 Aditya Kuppa , Nhien-An Le-Khac

This work proposes a unified control architecture that couples a Reinforcement Learning (RL)-driven controller with a disturbance-rejection Extended State Observer (ESO), complemented by an Event-Triggered Mechanism (ETM) to limit…

Optimization and Control · Mathematics 2026-01-01 Ningwei Bai , Chi Pui Chan , Qichen Yin , Tengyang Gong , Yunda Yan , Zezhi Tang

In Continual Learning (CL) contexts, concept drift typically refers to the analysis of changes in data distribution. A drift in the input data can have negative consequences on a learning predictor and the system's stability. The majority…

Machine Learning · Computer Science 2024-10-23 Sebastian Basterrech

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

Machine learning models deployed in nonstationary environments inevitably experience performance degradation due to data drift. While numerous drift detection heuristics exist, most lack a dynamical interpretation and provide limited…

Machine Learning · Computer Science 2026-01-19 Lennon Shikhman

Real-world robots must operate under evolving dynamics caused by changing operating conditions, external disturbances, and unmodeled effects. These may appear as gradual drifts, transient fluctuations, or abrupt shifts, demanding real-time…

Robotics · Computer Science 2025-12-17 Rishabh Dev Yadav , Avirup Das , Hongyu Song , Samuel Kaski , Wei Pan

Data stream classification is an important problem in the field of machine learning. Due to the non-stationary nature of the data where the underlying distribution changes over time (concept drift), the model needs to continuously adapt to…

Machine Learning · Computer Science 2022-09-13 Andrea Castellani , Sebastian Schmitt , Barbara Hammer

What data or environments to use for training to improve downstream performance is a longstanding and very topical question in reinforcement learning. In particular, Unsupervised Environment Design (UED) methods have gained recent attention…

Machine Learning · Computer Science 2024-10-31 Alexander Rutherford , Michael Beukman , Timon Willi , Bruno Lacerda , Nick Hawes , Jakob Foerster

Multimodal reward models are crucial for aligning multimodal large language models with human preferences. Recent works have incorporated reasoning capabilities into these models, achieving promising results. However, training these models…

Artificial Intelligence · Computer Science 2026-02-03 Shidong Yang , Tongwen Huang , Hao Wen , Yong Wang , Li Chen , Xiangxiang Chu

Adversarial training is among the most effective strategies for defending deep neural networks against adversarial examples. A key limitation of existing adversarial training approaches lies in their reliance on a fixed perturbation budget,…

Computer Vision and Pattern Recognition · Computer Science 2025-12-05 Alan Mitkiy , James Smith , Myungseo wong , Hana Satou , Hiroshi Tanaka , Emily Johnson

This paper develops an adaptive observation-based efficient reinforcement learning (RL) approach for systems with uncertain drift dynamics. A novel concurrent learning adaptive extended observer (CL-AEO) is first designed to jointly…

Dynamical Systems · Mathematics 2020-11-25 Maopeng Ran , Lihua Xie

When learning from streaming data, a change in the data distribution, also known as concept drift, can render a previously-learned model inaccurate and require training a new model. We present an adaptive learning algorithm that extends…

Machine Learning · Computer Science 2020-08-04 Ashraf Tahmasbi , Ellango Jothimurugesan , Srikanta Tirthapura , Phillip B. Gibbons

An open challenge in supervised learning is \emph{conceptual drift}: a data point begins as classified according to one label, but over time the notion of that label changes. Beyond linear autoregressive models, transfer and meta learning…

Optimization and Control · Mathematics 2019-09-13 Amrit Singh Bedi , Alec Koppel , Ketan Rajawat , Brian M. Sadler

Prediction models frequently face the challenge of concept drift, in which the underlying data distribution changes over time, weakening performance. Examples can include models which predict loan default, or those used in healthcare…

Machine Learning · Computer Science 2024-12-16 Louis Chislett , Catalina A. Vallejos , Timothy I. Cannings , James Liley

Reasoning ability has become a defining capability of Large Language Models (LLMs), with Reinforcement Learning with Verifiable Rewards (RLVR) emerging as a key paradigm to enhance it. However, RLVR training often suffers from policy…

Machine Learning · Computer Science 2026-04-20 Xiaoyun Zhang , Xiaojian Yuan , Di Huang , Wang You , Chen Hu , Jingqing Ruan , Ai Jian , Kejiang Chen , Xing Hu

Real-world autonomous decision-making systems, from robots to recommendation engines, must operate in environments that change over time. While deep reinforcement learning (RL) has shown an impressive ability to learn optimal policies in…

Machine Learning · Computer Science 2025-05-16 Jonathan Clifford Balloch

Both entropy-minimizing and entropy-maximizing (curiosity) objectives for unsupervised reinforcement learning (RL) have been shown to be effective in different environments, depending on the environment's level of natural entropy. However,…

Machine Learning · Computer Science 2024-08-19 Adriana Hugessen , Roger Creus Castanyer , Faisal Mohamed , Glen Berseth

Evolution strategy (ES) has been shown great promise in many challenging reinforcement learning (RL) tasks, rivaling other state-of-the-art deep RL methods. Yet, there are two limitations in the current ES practice that may hinder its…

Machine Learning · Computer Science 2020-02-24 Jiaxing Zhang , Hoang Tran , Guannan Zhang

Evolution strategies (ES), as a family of black-box optimization algorithms, recently emerge as a scalable alternative to reinforcement learning (RL) approaches such as Q-learning or policy gradient, and are much faster when many central…

Machine Learning · Computer Science 2022-04-01 Zhi Wang , Chunlin Chen , Daoyi Dong

Non-stationary online learning has drawn much attention in recent years. In particular, dynamic regret and adaptive regret are proposed as two principled performance measures for online convex optimization in non-stationary environments. To…

Machine Learning · Computer Science 2025-09-10 Peng Zhao , Yan-Feng Xie , Lijun Zhang , Zhi-Hua Zhou