相关论文: Policy Consolidation for Continual Reinforcement L…

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…

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…

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…

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,…

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…

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…

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…

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…

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…

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…

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…

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…

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…

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…

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…

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…

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…

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…

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,…

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…