English
Related papers

Related papers: Continual Task Learning through Adaptive Policy Se…

200 papers

Adapting Automatic Speech Recognition (ASR) models to new domains results in a deterioration of performance on the original domain(s), a phenomenon called Catastrophic Forgetting (CF). Even monolingual ASR models cannot be extended to new…

Audio and Speech Processing · Electrical Eng. & Systems 2026-01-22 Steven Vander Eeckt , Hugo Van hamme

To cope with real-world dynamics, an intelligent system needs to incrementally acquire, update, accumulate, and exploit knowledge throughout its lifetime. This ability, known as continual learning, provides a foundation for AI systems to…

Machine Learning · Computer Science 2024-02-07 Liyuan Wang , Xingxing Zhang , Hang Su , Jun Zhu

Compositional reinforcement learning is a promising approach for training policies to perform complex long-horizon tasks. Typically, a high-level task is decomposed into a sequence of subtasks and a separate policy is trained to perform…

Machine Learning · Computer Science 2023-06-09 Kishor Jothimurugan , Steve Hsu , Osbert Bastani , Rajeev Alur

Reinforcement learning has been applied to a wide variety of robotics problems, but most of such applications involve collecting data from scratch for each new task. Since the amount of robot data we can collect for any single task is…

Machine Learning · Computer Science 2020-10-28 Avi Singh , Albert Yu , Jonathan Yang , Jesse Zhang , Aviral Kumar , 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

Continual learning (CL) is a major challenge of machine learning (ML) and describes the ability to learn several tasks sequentially without catastrophic forgetting (CF). Recent works indicate that CL is a complex topic, even more so when…

Machine Learning · Computer Science 2022-06-09 Benedikt Bagus , Alexander Gepperth

Despite remarkable successes achieved by modern neural networks in a wide range of applications, these networks perform best in domain-specific stationary environments where they are trained only once on large-scale controlled data…

Neural and Evolutionary Computing · Computer Science 2019-04-23 Pouya Bashivan , Martin Schrimpf , Robert Ajemian , Irina Rish , Matthew Riemer , Yuhai Tu

Offline Reinforcement Learning (RL), which operates solely on static datasets without further interactions with the environment, provides an appealing alternative to learning a safe and promising control policy. The prevailing methods…

Machine Learning · Computer Science 2025-03-18 Kun Wu , Yinuo Zhao , Zhiyuan Xu , Zhengping Che , Chengxiang Yin , Chi Harold Liu , Feiferi Feng , Jian Tang

Despite the remarkable success of large language models (LLMs), they still face bottlenecks while deploying in dynamic, real-world settings with primary challenges being concept drift and the high cost of gradient-based adaptation.…

Artificial Intelligence · Computer Science 2026-05-21 Nitin Vetcha , Dianbo Liu

Incorporating pre-collected offline data can substantially improve the sample efficiency of reinforcement learning (RL), but its benefits can break down when the transition dynamics in the offline dataset differ from those encountered…

Machine Learning · Computer Science 2026-01-22 Lingkai Kong , Haichuan Wang , Tonghan Wang , Guojun Xiong , Milind Tambe

A fundamental challenge in Continual Learning (CL) is catastrophic forgetting, where adapting to new tasks degrades the performance on previous ones. While the field has evolved with diverse methods, this rapid surge in diverse…

Machine Learning · Computer Science 2025-12-29 Wenbin Li , Shangge Liu , Borui Kang , Yiyang Chen , KaXuan Lew , Yang Chen , Yinghuan Shi , Lei Wang , Yang Gao , Jiebo Luo

Lifelong reinforcement learning provides a promising framework for developing versatile agents that can accumulate knowledge over a lifetime of experience and rapidly learn new tasks by building upon prior knowledge. However, current…

Machine Learning · Computer Science 2015-05-22 Haitham Bou Ammar , Rasul Tutunov , Eric Eaton

Continual learning (CL) for Foundation Models (FMs) is an essential yet underexplored challenge, especially in Federated Continual Learning (FCL), where each client learns from a private, evolving task stream under strict data and…

Machine Learning · Computer Science 2025-08-14 Hao Yu , Xin Yang , Boyang Fan , Xuemei Cao , Hanlin Gu , Lixin Fan , Qiang Yang

Continual instruction tuning enables large language models (LLMs) to learn incrementally while retaining past knowledge, whereas existing methods primarily focus on how to retain old knowledge rather than on selecting which new knowledge to…

Computation and Language · Computer Science 2025-03-21 Peiyi Lin , Fukai Zhang , Kai Niu , Hao Fu

General-purpose learning systems should improve themselves in open-ended fashion in ever-changing environments. Conventional learning algorithms for neural networks, however, suffer from catastrophic forgetting (CF), i.e., previously…

Machine Learning · Computer Science 2025-02-18 Kazuki Irie , Róbert Csordás , Jürgen Schmidhuber

Online matching problems arise in many complex systems, from cloud services and online marketplaces to organ exchange networks, where timely, principled decisions are critical for maintaining high system performance. Traditional heuristics…

Machine Learning · Statistics 2025-10-09 Chiara Mignacco , Matthieu Jonckheere , Gilles Stoltz

Continual learning requires incremental compatibility with a sequence of tasks. However, the design of model architecture remains an open question: In general, learning all tasks with a shared set of parameters suffers from severe…

Machine Learning · Computer Science 2022-07-15 Liyuan Wang , Xingxing Zhang , Qian Li , Jun Zhu , Yi Zhong

Continual Learning (CL) aims at incrementally learning new tasks without forgetting the knowledge acquired from old ones. Experience Replay (ER) is a simple and effective rehearsal-based strategy, which optimizes the model with current…

Computer Vision and Pattern Recognition · Computer Science 2023-12-05 Tao Zhuo , Zhiyong Cheng , Zan Gao , Hehe Fan , Mohan Kankanhalli

Predicting the future behavior of agents is a fundamental task in autonomous vehicle domains. Accurate prediction relies on comprehending the surrounding map, which significantly regularizes agent behaviors. However, existing methods have…

Computer Vision and Pattern Recognition · Computer Science 2024-01-19 Chen Feng , Hangning Zhou , Huadong Lin , Zhigang Zhang , Ziyao Xu , Chi Zhang , Boyu Zhou , Shaojie Shen

Path planning in dynamic environments is a fundamental challenge in intelligent transportation and robotics, where obstacles and conditions change over time, introducing uncertainty and requiring continuous adaptation. While existing…

Robotics · Computer Science 2025-11-20 Jonas De Maeyer , Hossein Yarahmadi , Moharram Challenger