English
Related papers

Related papers: TSN-Affinity: Similarity-Driven Parameter Reuse fo…

200 papers

Offline reinforcement learning (RL) tasks require the agent to learn from a pre-collected dataset with no further interactions with the environment. Despite the potential to surpass the behavioral policies, RL-based methods are generally…

Machine Learning · Computer Science 2022-01-13 Minghuan Liu , Hanye Zhao , Zhengyu Yang , Jian Shen , Weinan Zhang , Li Zhao , Tie-Yan Liu

Online continual learning (OCL) aims to train neural networks incrementally from a non-stationary data stream with a single pass through data. Rehearsal-based methods attempt to approximate the observed input distributions over time with a…

Machine Learning · Computer Science 2022-11-15 Yaqian Zhang , Bernhard Pfahringer , Eibe Frank , Albert Bifet , Nick Jin Sean Lim , Yunzhe Jia

Despite the evolution of Convolutional Neural Networks (CNNs), their performance is surprisingly dependent on the choice of hyperparameters. However, it remains challenging to efficiently explore large hyperparameter search space due to the…

Computer Vision and Pattern Recognition · Computer Science 2022-09-27 HyunJae Lee , Gihyeon Lee , Junhwan Kim , Sungjun Cho , Dohyun Kim , Donggeun Yoo

Continual learning on graphs tackles the problem of training a graph neural network (GNN) where graph data arrive in a streaming fashion and the model tends to forget knowledge from previous tasks when updating with new data. Traditional…

Machine Learning · Computer Science 2024-01-09 Xiaoxue Han , Zhuo Feng , Yue Ning

Continual self-supervised learning (CSSL) methods have gained increasing attention in remote sensing (RS) due to their capability to learn new tasks sequentially from continuous streams of unlabeled data. Existing CSSL methods, while…

Computer Vision and Pattern Recognition · Computer Science 2025-05-19 Lars Möllenbrok , Behnood Rasti , Begüm Demir

Reinforcement Learning (RL) is a method for learning decision-making tasks that could enable robots to learn and adapt to their situation on-line. For an RL algorithm to be practical for robotic control tasks, it must learn in very few…

Artificial Intelligence · Computer Science 2015-03-19 Todd Hester , Michael Quinlan , Peter Stone

Continuous-time reinforcement learning (CTRL) provides a principled framework for sequential decision-making in environments where interactions evolve continuously over time. Despite its empirical success, the theoretical understanding of…

Machine Learning · Computer Science 2025-05-22 Runze Zhao , Yue Yu , Adams Yiyue Zhu , Chen Yang , Dongruo Zhou

Class-Incremental Learning (CIL) aims to learn new classes sequentially while retaining the knowledge of previously learned classes. Recently, pre-trained models (PTMs) combined with parameter-efficient fine-tuning (PEFT) have shown…

Computer Vision and Pattern Recognition · Computer Science 2025-06-02 Jiangpeng He , Zhihao Duan , Fengqing Zhu

Biological brains have the capability to adaptively coordinate relevant neuronal populations based on the task context to learn continuously changing tasks in real-world environments. However, existing spiking neural network-based continual…

Neural and Evolutionary Computing · Computer Science 2024-11-12 Bing Han , Feifei Zhao , Yang Li , Qingqun Kong , Xianqi Li , Yi Zeng

Meta-reinforcement learning (RL) methods can meta-train policies that adapt to new tasks with orders of magnitude less data than standard RL, but meta-training itself is costly and time-consuming. If we can meta-train on offline data, then…

Machine Learning · Computer Science 2022-07-08 Vitchyr H. Pong , Ashvin Nair , Laura Smith , Catherine Huang , Sergey Levine

Many value-based deep reinforcement learning algorithms rely on target networks - lagged copies of the online network - to stabilize training. While effective, this mechanism introduces a fundamental stability-recency tradeoff: slower…

Machine Learning · Computer Science 2026-05-20 Leonard S. Pleiss , James Harrison , Maximilian Schiffer

Graph neural networks (GNNs) have been widely applied to numerous fields. A recent work which combines layered structure and residual connection proposes an improved deep architecture to extend CAmouflage-REsistant GNN (CARE-GNN) to deep…

Machine Learning · Computer Science 2022-02-15 Yufan Zeng , Jiashan Tang

The performance of a reinforcement learning (RL) system depends on the computational architecture used to approximate a value function. Deep learning methods provide both optimization techniques and architectures for approximating nonlinear…

Machine Learning · Computer Science 2021-06-21 John D. Martin , Joseph Modayil

The potential of offline reinforcement learning (RL) is that high-capacity models trained on large, heterogeneous datasets can lead to agents that generalize broadly, analogously to similar advances in vision and NLP. However, recent works…

Machine Learning · Computer Science 2023-04-19 Aviral Kumar , Rishabh Agarwal , Xinyang Geng , George Tucker , Sergey Levine

In the past, continual learning (CL) was mostly concerned with the problem of catastrophic forgetting in neural networks, that arises when incrementally learning a sequence of tasks. Current CL methods function within the confines of…

Machine Learning · Computer Science 2025-07-29 Shishir Muralidhara , Didier Stricker , René Schuster

Using Reinforcement Learning (RL) to learn new robotic tasks from scratch is often inefficient. Leveraging prior knowledge has the potential to significantly enhance learning efficiency, which, however, raises two critical challenges: how…

Robotics · Computer Science 2025-06-10 Zechen Hu , Tong Xu , Xuesu Xiao , Xuan Wang

Despite recent advances in improving the sample-efficiency of reinforcement learning (RL) algorithms, designing an RL algorithm that can be practically deployed in real-world environments remains a challenge. In this paper, we present…

Robotics · Computer Science 2024-07-11 Younggyo Seo , Jafar Uruç , Stephen James

Reinforcement learning (RL) is a framework to optimize a control policy using rewards that are revealed by the system as a response to a control action. In its standard form, RL involves a single agent that uses its policy to accomplish a…

Systems and Control · Electrical Eng. & Systems 2021-11-24 Juan Cervino , Juan Andres Bazerque , Miguel Calvo-Fullana , Alejandro Ribeiro

Improving sample efficiency is a key research problem in reinforcement learning (RL), and CURL, which uses contrastive learning to extract high-level features from raw pixels of individual video frames, is an efficient…

Machine Learning · Computer Science 2020-10-16 Jinhua Zhu , Yingce Xia , Lijun Wu , Jiajun Deng , Wengang Zhou , Tao Qin , Houqiang Li

The goal of Continual Learning (CL) task is to continuously learn multiple new tasks sequentially while achieving a balance between the plasticity and stability of new and old knowledge. This paper analyzes that this insufficiency arises…

Machine Learning · Computer Science 2024-05-28 Hanxi Xiao , Fan Lyu