paper-with-me

Papers

Closed-loop Control for Online Continual Learning

2021-09-29 · Yaqian Zhang, Eibe Frank, Bernhard Pfahringer, Albert Bifet, Nick Jin Sean Lim, Alvin Jia

Online class-incremental continual learning (CL) deals with the sequential task learning problem in a realistic non-stationary setting with a single-pass through of data. Replay-based CL methods have shown promising results in several online class-incremental continual learning benchmarks. However, these replay methods typically assume pre-defined and fixed replay dynamics, which is suboptimal. This paper introduces a closed-loop continual learning framework, which obtains a real-time feedback learning signal via an additional test memory and then adapts the replay dynamics accordingly. More specifically, we propose a reinforcement learning-based method to dynamically adjust replay hyperparameters online to balance the stability and plasticity trade-off in continual learning. To address the non-stationarity in the continual learning environment, we employ a Q function with task-specific and task-shared components to support fast adaptation. The proposed method is applied to improve state-of-the-art replay-based methods and achieves superior performance on popular benchmarks.

📄 PDF Abstract BibTeX

Code (0)

등록된 구현이 없습니다.

Tasks

Continual Learning

Methods 이 논문이 사용한 방법론

Test 설명 없음

Similar Papers 제목 키워드 기반

Non-Conservative Data-driven Safe Control Design for Nonlinear Systems with Polyhedral Safe Sets

2025-05-12 · Amir Modares, Bosen Lian, Hamidreza Modares

This paper presents a data-driven nonlinear safe control design approach for discrete-time systems under parametric uncertainties and additive disturbances. We first characterize a new control structure from which a data…

Computational Efficiency

Stability-Preserving Online Adaptation of Neural Closed-loop Maps

2026-03-23 · Danilo Saccani, Luca Furieri, Giancarlo Ferrari-Trecate arxiv

The growing complexity of modern control tasks calls for controllers that can react online as objectives and disturbances change, while preserving closed-loop stability. Recent approaches for improving the performance of…

Data-Driven Robust Stabilization with RobustDomain of Attraction Estimate for Nonlinear Discrete-Time Systems

2019-12-26

Nonlinear robust control is pursued by overcoming the drawback of linear robust control that it ignores available information about existing nonlinearities and the resulting controllers may be too conservative, especiall…

High-Precision and High-Efficiency Trajectory Tracking for Excavators Based on Closed-Loop Dynamics

2025-09-22 · Ziqing Zou, Cong Wang, Yue Hu, Xiao Liu 외 arxiv

The complex nonlinear dynamics of hydraulic excavators, such as time delays and control coupling, pose significant challenges to achieving high-precision trajectory tracking. Traditional control methods often fall short …

Continual Learning

On the Design of Safe Continual RL Methods for Control of Nonlinear Systems

2025-02-21 · Austin Coursey, Marcos Quinones-Grueiro, Gautam Biswas

Reinforcement learning (RL) algorithms have been successfully applied to control tasks associated with unmanned aerial vehicles and robotics. In recent years, safe RL has been proposed to allow the safe execution of RL a…

Continual LearningMuJoCoReinforcement Learning (RL)