English
Related papers

Related papers: Policy Consolidation for Continual Reinforcement L…

200 papers

The utility of learning a dynamics/world model of the environment in reinforcement learning has been shown in a many ways. When using neural networks, however, these models suffer catastrophic forgetting when learned in a lifelong or…

Machine Learning · Computer Science 2019-06-12 Nicholas Ketz , Soheil Kolouri , Praveen Pilly

While recent progress has spawned very powerful machine learning systems, those agents remain extremely specialized and fail to transfer the knowledge they gain to similar yet unseen tasks. In this paper, we study a simple reinforcement…

Machine Learning · Computer Science 2020-12-15 Remi Tachet , Philip Bachman , Harm van Seijen

It has been observed that neural networks perform poorly when the data or tasks are presented sequentially. Unlike humans, neural networks suffer greatly from catastrophic forgetting, making it impossible to perform life-long learning. To…

Machine Learning · Computer Science 2023-01-31 Longhui Yu , Tianyang Hu , Lanqing Hong , Zhen Liu , Adrian Weller , Weiyang Liu

Developments in deep generative models have allowed for tractable learning of high-dimensional data distributions. While the employed learning procedures typically assume that training data is drawn i.i.d. from the distribution of interest,…

Machine Learning · Computer Science 2017-05-24 Ari Seff , Alex Beatson , Daniel Suo , Han Liu

In the present era of deep learning, continual learning research is mainly focused on mitigating forgetting when training a neural network with stochastic gradient descent on a non-stationary stream of data. On the other hand, in the more…

Machine Learning · Computer Science 2024-05-30 Soochan Lee , Hyeonseong Jeon , Jaehyeon Son , Gunhee Kim

Modern neural network based speech recognition models are required to continually absorb new data without re-training the whole system, especially in downstream applications using foundation models, having no access to the original training…

Computation and Language · Computer Science 2025-06-23 Enes Yavuz Ugan , Ngoc-Quan Pham , Alexander Waibel

Policy gradient methods have shown success in learning control policies for high-dimensional dynamical systems. Their biggest downside is the amount of exploration they require before yielding high-performing policies. In a lifelong…

Machine Learning · Computer Science 2020-10-23 Jorge A. Mendez , Boyu Wang , Eric Eaton

In reinforcement learning, an agent interacts sequentially with an environment to maximize a reward, receiving only partial, probabilistic feedback. This creates a fundamental exploration-exploitation trade-off: the agent must explore to…

Quantum Physics · Physics 2026-03-27 Josep Lumbreras , Ruo Cheng Huang , Yanglin Hu , Marco Fanizza , Mile Gu

Lifelong learning is a very important step toward realizing robust autonomous artificial agents. Neural networks are the main engine of deep learning, which is the current state-of-the-art technique in formulating adaptive artificial…

Machine Learning · Computer Science 2019-12-11 Mohammed Amer , Tomás Maul

Deep reinforcement learning has made significant progress in the field of continuous control, such as physical control and autonomous driving. However, it is challenging for a reinforcement model to learn a policy for each task sequentially…

Machine Learning · Computer Science 2019-06-24 Fengda Zhu , Xiaojun Chang , Runhao Zeng , Mingkui Tan

Continual Learning (CL) considers the problem of training an agent sequentially on a set of tasks while seeking to retain performance on all previous tasks. A key challenge in CL is catastrophic forgetting, which arises when performance on…

Machine Learning · Computer Science 2022-03-16 Samuel Kessler , Jack Parker-Holder , Philip Ball , Stefan Zohren , Stephen J. Roberts

Continual learning, involving sequential training on diverse tasks, often faces catastrophic forgetting. While knowledge distillation-based approaches exhibit notable success in preventing forgetting, we pinpoint a limitation in their…

Machine Learning · Computer Science 2024-05-17 Zenglin Shi , Pei Liu , Tong Su , Yunpeng Wu , Kuien Liu , Yu Song , Meng Wang

Rather than learning new control policies for each new task, it is possible, when tasks share some structure, to compose a "meta-policy" from previously learned policies. This paper reports results from experiments using Deep Reinforcement…

Artificial Intelligence · Computer Science 2017-11-07 Richard Liaw , Sanjay Krishnan , Animesh Garg , Daniel Crankshaw , Joseph E. Gonzalez , Ken Goldberg

Future deep learning models will be distinguished by systems that perpetually learn through interaction, imagination, and cooperation, blurring the line between training and inference. This makes continual learning a critical challenge, as…

Machine Learning · Computer Science 2025-05-20 Truman Hickok

We study the problem of learning a good set of policies, so that when combined together, they can solve a wide variety of unseen reinforcement learning tasks with no or very little new data. Specifically, we consider the framework of…

Machine Learning · Computer Science 2022-03-16 Safa Alver , Doina Precup

Catastrophic forgetting poses a substantial challenge for managing intelligent agents controlled by a large model, causing performance degradation when these agents face new tasks. In our work, we propose a novel solution - the Progressive…

Machine Learning · Computer Science 2025-09-04 Zhiyuan Wang , Xiaoyang Qu , Jing Xiao , Bokui Chen , Jianzong Wang

Scarcity of data and incremental learning of new tasks pose two major bottlenecks for many modern computer vision algorithms. The phenomenon of catastrophic forgetting, i.e., the model's inability to classify previously learned data after…

Computer Vision and Pattern Recognition · Computer Science 2023-09-06 Sanchar Palit , Biplab Banerjee , Subhasis Chaudhuri

Catastrophic forgetting is a critical challenge in training deep neural networks. Although continual learning has been investigated as a countermeasure to the problem, it often suffers from the requirements of additional network components…

Machine Learning · Computer Science 2019-10-23 Dongmin Park , Seokil Hong , Bohyung Han , Kyoung Mu Lee

One of the objectives of continual learning is to prevent catastrophic forgetting in learning multiple tasks sequentially, and the existing solutions have been driven by the conceptualization of the plasticity-stability dilemma. However,…

Machine Learning · Computer Science 2024-04-16 Seungyub Han , Yeongmo Kim , Taehyun Cho , Jungwoo Lee

Linear dynamical systems that obey stochastic differential equations are canonical models. While optimal control of known systems has a rich literature, the problem is technically hard under model uncertainty and there are hardly any…

Systems and Control · Electrical Eng. & Systems 2023-06-09 Mohamad Kazem Shirani Faradonbeh , Mohamad Sadegh Shirani Faradonbeh