English
Related papers

Related papers: Mitigating Plasticity Loss in Continual Reinforcem…

200 papers

Continual learning aims to empower artificial intelligence (AI) with strong adaptability to the real world. For this purpose, a desirable solution should properly balance memory stability with learning plasticity, and acquire sufficient…

Machine Learning · Computer Science 2023-11-10 Liyuan Wang , Xingxing Zhang , Qian Li , Mingtian Zhang , Hang Su , Jun Zhu , Yi Zhong

Reinforcement learning (RL) post-training is a critical stage in modern language model development, playing a key role in improving alignment and reasoning ability. However, several phenomena remain poorly understood, including the…

Machine Learning · Computer Science 2026-01-09 Akiyoshi Tomihari

Continual Pre-Training (CPT) has become a popular and effective method to apply strong foundation models to specific downstream tasks. In this work, we explore the learning dynamics throughout the CPT process for large language models. We…

Computation and Language · Computer Science 2025-06-23 Xingjin Wang , Howe Tissue , Lu Wang , Linjing Li , Daniel Dajun Zeng

A common challenge in continual learning (CL) is catastrophic forgetting, where the performance on old tasks drops after new, additional tasks are learned. In this paper, we propose a novel framework called ReCL to slow down forgetting in…

Machine Learning · Computer Science 2025-03-04 Pascal Janetzky , Tobias Schlagenhauf , Stefan Feuerriegel

Regularization is commonly used for alleviating overfitting in machine learning. For convolutional neural networks (CNNs), regularization methods, such as DropBlock and Shake-Shake, have illustrated the improvement in the generalization…

Computer Vision and Pattern Recognition · Computer Science 2021-01-01 Yi Wang , Zhen-Peng Bian , Junhui Hou , Lap-Pui Chau

Continual learning of partially similar tasks poses a challenge for artificial neural networks, as task similarity presents both an opportunity for knowledge transfer and a risk of interference and catastrophic forgetting. However, it…

Machine Learning · Statistics 2024-05-31 Naoki Hiratani

Robust training methods typically defend against specific attack types, such as Lp attacks with fixed budgets, and rarely account for the fact that defenders may encounter new attacks over time. A natural solution is to adapt the defended…

Machine Learning · Computer Science 2025-02-07 Sihui Dai , Christian Cianfarani , Arjun Bhagoji , Vikash Sehwag , Prateek Mittal

Adversarial robustness is essential for security and reliability of machine learning systems. However, adversarial robustness enhanced by defense algorithms is easily erased as the neural network's weights update to learn new tasks. To…

Machine Learning · Computer Science 2024-08-14 Xiaolei Ru , Xiaowei Cao , Zijia Liu , Jack Murdoch Moore , Xin-Ya Zhang , Xia Zhu , Wenjia Wei , Gang Yan

Continual learning aims to improve the ability of modern learning systems to deal with non-stationary distributions, typically by attempting to learn a series of tasks sequentially. Prior art in the field has largely considered supervised…

Machine Learning · Computer Science 2019-11-01 Dushyant Rao , Francesco Visin , Andrei A. Rusu , Yee Whye Teh , Razvan Pascanu , Raia Hadsell

In Continual Learning, a Neural Network is trained on a stream of data whose distribution shifts over time. Under these assumptions, it is especially challenging to improve on classes appearing later in the stream while remaining accurate…

Machine Learning · Computer Science 2020-10-13 Pietro Buzzega , Matteo Boschini , Angelo Porrello , Simone Calderara

To meet the demands of applications like robotics and autonomous driving that require real-time responses to dynamic environments, efficient continual learning methods suitable for edge devices have attracted increasing attention. In this…

Computer Vision and Pattern Recognition · Computer Science 2025-09-22 Runjie Shao , Boyu Diao , Zijia An , Ruiqi Liu , Yongjun Xu

Time-dependent data-generating distributions have proven to be difficult for gradient-based training of neural networks, as the greedy updates result in catastrophic forgetting of previously learned knowledge. Despite the progress in the…

Machine Learning · Computer Science 2023-04-03 Matthias De Lange , Gido van de Ven , Tinne Tuytelaars

How can we build agents that keep learning from experience, quickly and efficiently, after their initial training? Here we take inspiration from the main mechanism of learning in biological brains: synaptic plasticity, carefully tuned by…

Neural and Evolutionary Computing · Computer Science 2018-08-01 Thomas Miconi , Jeff Clune , Kenneth O. Stanley

Class-Incremental Learning (CIL) is a critical capability for real-world applications, enabling learning systems to adapt to new tasks while retaining knowledge from previous ones. Recent advancements in pre-trained models (PTMs) have…

Machine Learning · Computer Science 2025-04-28 Kun He , Zijian Song , Shuoxi Zhang , John E. Hopcroft

Reinforcement learning is applied to the development of control strategies in order to reduce skin friction drag in a fully developed turbulent channel flow at a low Reynolds number. Motivated by the so-called opposition control (Choi et…

Fluid Dynamics · Physics 2023-04-26 Takahiro Sonoda , Zhuchen Liu , Toshitaka Itoh , Yosuke Hasegawa

An extendable, efficient and explainable Machine Learning approach is proposed to represent cyclic plasticity and replace conventional material models based on the Radial Return Mapping algorithm. High accuracy and stability by means of a…

Materials Science · Physics 2025-08-11 Stefan Hildebrand , Sandra Klinge

The diversity of tasks and dynamic nature of reinforcement learning (RL) require RL agents to be able to learn sequentially and continuously, a learning paradigm known as continuous reinforcement learning. This survey reviews how continual…

Machine Learning · Computer Science 2025-06-30 Amara Zuffer , Michael Burke , Mehrtash Harandi

In contrast to the human ability to continuously acquire knowledge, agents struggle with the stability-plasticity dilemma in deep reinforcement learning (DRL), which refers to the trade-off between retaining existing skills (stability) and…

Artificial Intelligence · Computer Science 2025-04-14 Jiahua Lan , Sen Zhang , Haixia Pan , Ruijun Liu , Li Shen , Dacheng Tao

Continual learning (CL) is a branch of machine learning that aims to enable agents to adapt and generalise previously learned abilities so that these can be reapplied to new tasks or environments. This is particularly useful in multi-task…

Machine Learning · Computer Science 2025-11-20 Kim N. Nolle , Ivana Dusparic , Rhodri Cusack , Vinny Cahill

Continual learning entails learning a sequence of tasks and balancing their knowledge appropriately. With limited access to old training samples, much of the current work in deep neural networks has focused on overcoming catastrophic…

Machine Learning · Computer Science 2023-10-16 Yilin Lyu , Liyuan Wang , Xingxing Zhang , Zicheng Sun , Hang Su , Jun Zhu , Liping Jing