English
Related papers

Related papers: Fisher-Guided Selective Forgetting: Mitigating The…

200 papers

Deep reinforcement learning for continuous control has recently achieved impressive progress. However, existing methods often suffer from primacy bias, a tendency to overfit early experiences stored in the replay buffer, which limits an RL…

Machine Learning · Computer Science 2025-07-04 Zilin Kang , Chenyuan Hu , Yu Luo , Zhecheng Yuan , Ruijie Zheng , Huazhe Xu

This work identifies a common flaw of deep reinforcement learning (RL) algorithms: a tendency to rely on early interactions and ignore useful evidence encountered later. Because of training on progressively growing datasets, deep RL agents…

Machine Learning · Computer Science 2022-05-17 Evgenii Nikishin , Max Schwarzer , Pierluca D'Oro , Pierre-Luc Bacon , Aaron Courville

The early phase of training a deep neural network has a dramatic effect on the local curvature of the loss function. For instance, using a small learning rate does not guarantee stable optimization because the optimization trajectory has a…

Preference-based reinforcement learning (PbRL) has emerged as a promising paradigm for teaching robots complex behaviors without reward engineering. However, its effectiveness is often limited by two critical challenges: the reliance on…

Robotics · Computer Science 2025-12-02 Ruiqi Wang , Dezhong Zhao , Ziqin Yuan , Tianyu Shao , Guohua Chen , Dominic Kao , Sungeun Hong , Byung-Cheol Min

Machine learning models trained on sensitive or private data can inadvertently memorize and leak that information. Machine unlearning seeks to retroactively remove such details from model weights to protect privacy. We contribute a…

Machine Learning · Computer Science 2024-04-29 Jiaeli Shi , Najah Ghalyan , Kostis Gourgoulias , John Buford , Sean Moran

Classical federated learning (FL) enables training machine learning models without sharing data for privacy preservation, but heterogeneous data characteristic degrades the performance of the localized model. Personalized FL (PFL) addresses…

Machine Learning · Computer Science 2023-11-13 Mingjia Shi , Yuhao Zhou , Kai Wang , Huaizheng Zhang , Shudong Huang , Qing Ye , Jiangcheng Lv

We present Preference Flow Matching (PFM), a new framework for preference-based reinforcement learning (PbRL) that streamlines the integration of preferences into an arbitrary class of pre-trained models. Existing PbRL methods require…

Machine Learning · Computer Science 2024-10-29 Minu Kim , Yongsik Lee , Sehyeok Kang , Jihwan Oh , Song Chong , Se-Young Yun

Catastrophic forgetting impairs the continuous learning of large language models. We propose Fisher-Guided Gradient Masking (FGGM), a framework that mitigates this by strategically selecting parameters for updates using diagonal Fisher…

Machine Learning · Computer Science 2026-01-27 Chao-Hong Tan , Qian Chen , Wen Wang , Yukun Ma , Chong Zhang , Chong Deng , Qinglin Zhang , Xiangang Li , Jieping Ye

As machine learning has moved towards leveraging large models as priors for downstream tasks, the community has debated the right form of prior for solving reinforcement learning (RL) problems. If one were to try to prefetch as much…

Machine Learning · Computer Science 2026-02-13 Chongyi Zheng , Royina Karegoudra Jayanth , Benjamin Eysenbach

Motivated by the growing interest in quantum machine learning, in particular quantum neural networks (QNNs), we study how recently introduced evaluation metrics based on the Fisher information matrix (FIM) are effective for predicting their…

Machine Learning · Computer Science 2025-10-09 Lorenzo Pastori , Veronika Eyring , Mierk Schwabe

Reinforcement learning (RL) is a branch of machine learning which is employed to solve various sequential decision making problems without proper supervision. Due to the recent advancement of deep learning, the newly proposed Deep-RL…

Artificial Intelligence · Computer Science 2019-04-17 Dhruv Ramani

The primacy bias in model-free reinforcement learning (MFRL), which refers to the agent's tendency to overfit early data and lose the ability to learn from new data, can significantly decrease the performance of MFRL algorithms. Previous…

Machine Learning · Computer Science 2024-08-20 Zhongjian Qiao , Jiafei Lyu , Xiu Li

We show that deep reinforcement learning algorithms can retain their ability to learn without resetting network parameters in settings where the number of gradient updates greatly exceeds the number of environment samples by combatting…

Machine Learning · Computer Science 2024-08-06 Marcel Hussing , Claas Voelcker , Igor Gilitschenski , Amir-massoud Farahmand , Eric Eaton

Deep neural networks (DNNs) have recently achieved a great success in computer vision and several related fields. Despite such progress, current neural architectures still suffer from catastrophic interference (a.k.a. forgetting) which…

Computer Vision and Pattern Recognition · Computer Science 2021-11-23 Hichem Sahbi , Haoming Zhan

Reinforcement Learning (RL) algorithms allow artificial agents to improve their action selections so as to increase rewarding experiences in their environments. Deep Reinforcement Learning algorithms require solving a nonconvex and…

Machine Learning · Computer Science 2019-04-18 Jacob Rafati , Roummel F. Marcia

Preference-based Reinforcement Learning (PbRL) provides a way to learn high-performance policies in environments where the reward signal is hard to specify, avoiding heuristic and time-consuming reward design. However, PbRL can suffer from…

Machine Learning · Computer Science 2025-07-02 Chenyang Cao , Miguel Rogel-García , Mohamed Nabail , Xueqian Wang , Nicholas Rhinehart

The framework of deep reinforcement learning (DRL) provides a powerful and widely applicable mathematical formalization for sequential decision-making. This paper present a novel DRL framework, termed \emph{$f$-Divergence Reinforcement…

Machine Learning · Computer Science 2021-12-15 Chen Gong , Qiang He , Yunpeng Bai , Zhou Yang , Xiaoyu Chen , Xinwen Hou , Xianjie Zhang , Yu Liu , Guoliang Fan

Reinforcement learning (RL) in episodic, factored Markov decision processes (FMDPs) is studied. We propose an algorithm called FMDP-BF, which leverages the factorization structure of FMDP. The regret of FMDP-BF is shown to be exponentially…

Machine Learning · Computer Science 2021-03-11 Xiaoyu Chen , Jiachen Hu , Lihong Li , Liwei Wang

Deep neural networks are known to suffer the catastrophic forgetting problem, where they tend to forget the knowledge from the previous tasks when sequentially learning new tasks. Such failure hinders the application of deep learning based…

Machine Learning · Computer Science 2018-12-04 Junfeng Wen , Yanshuai Cao , Ruitong Huang

The backpropagation networks are notably susceptible to catastrophic forgetting, where networks tend to forget previously learned skills upon learning new ones. To address such the 'sensitivity-stability' dilemma, most previous efforts have…

Machine Learning · Computer Science 2021-10-12 Danruo Deng , Guangyong Chen , Jianye Hao , Qiong Wang , Pheng-Ann Heng
‹ Prev 1 2 3 10 Next ›