English
Related papers

Related papers: Integrating Episodic Memory into a Reinforcement L…

200 papers

Unlike humans, who are capable of continual learning over their lifetimes, artificial neural networks have long been known to suffer from a phenomenon known as catastrophic forgetting, whereby new learning can lead to abrupt erasure of…

Artificial Intelligence · Computer Science 2018-06-20 Christos Kaplanis , Murray Shanahan , Claudia Clopath

Lifelong learning is a long-standing aim for artificial agents that act in dynamic environments, in which an agent needs to accumulate knowledge incrementally without forgetting previously learned representations. We investigate methods for…

Machine Learning · Computer Science 2021-11-17 Vadym Gryshchuk , Cornelius Weber , Chu Kiong Loo , Stefan Wermter

Reservoir Computing is a type of recursive neural network commonly used for recognizing and predicting spatio-temporal events relying on a complex hierarchy of nested feedback loops to generate a memory functionality. The Reservoir…

Mesoscale and Nanoscale Physics · Physics 2018-02-05 George Bourianoff , Daniele Pinna , Matthias Sitte , Karin Everschor-Sitte

Existing reasoning tasks often have an important assumption that the input contents can be always accessed while reasoning, requiring unlimited storage resources and suffering from severe time delay on long sequences. To achieve efficient…

Machine Learning · Computer Science 2021-06-03 Zhu Zhang , Chang Zhou , Jianxin Ma , Zhijie Lin , Jingren Zhou , Hongxia Yang , Zhou Zhao

Incremental learning is a form of online learning. Incremental learning can modify the parameters and structure of the deep learning model so that the model does not forget the old knowledge while learning new knowledge. Preventing…

Computer Vision and Pattern Recognition · Computer Science 2020-10-12 Sheng Ren , Yan He , Neal N. Xiong , Kehua Guo

An associative memory (AM) enables cue-response recall, and associative memorization has recently been noted to underlie the operation of modern neural architectures such as Transformers. This work addresses a distributed setting where…

Machine Learning · Computer Science 2026-04-24 Bowen Wang , Matteo Zecchin , Osvaldo Simeone

In online continual learning, a neural network incrementally learns from a non-i.i.d. data stream. Nearly all online continual learning methods employ experience replay to simultaneously prevent catastrophic forgetting and underfitting on…

Machine Learning · Computer Science 2024-07-22 Jason Yoo , Yunpeng Liu , Frank Wood , Geoff Pleiss

In many sequential tasks, a model needs to remember relevant events from the distant past to make correct predictions. Unfortunately, a straightforward application of gradient based training requires intermediate computations to be stored…

Machine Learning · Computer Science 2023-08-14 Artyom Sorokin , Nazar Buzun , Leonid Pugachev , Mikhail Burtsev

Under a unified operational definition, we define LLM memory as a persistent state written during pretraining, finetuning, or inference that can later be addressed and that stably influences outputs. We propose a four-part taxonomy…

Artificial Intelligence · Computer Science 2025-09-24 Dianxing Zhang , Wendong Li , Kani Song , Jiaye Lu , Gang Li , Liuchun Yang , Sheng Li

The ability to learn continually without forgetting the past tasks is a desired attribute for artificial learning systems. Existing approaches to enable such learning in artificial neural networks usually rely on network growth, importance…

Machine Learning · Computer Science 2021-03-18 Gobinda Saha , Isha Garg , Kaushik Roy

In this paper, we introduce variational semantic memory into meta-learning to acquire long-term knowledge for few-shot learning. The variational semantic memory accrues and stores semantic information for the probabilistic inference of…

Machine Learning · Computer Science 2021-07-16 Xiantong Zhen , Yingjun Du , Huan Xiong , Qiang Qiu , Cees G. M. Snoek , Ling Shao

In model-based learning, an agent's model is commonly defined over transitions between consecutive states of an environment even though planning often requires reasoning over multi-step timescales, with intermediate states either…

Machine Learning · Computer Science 2020-10-06 Alexey Zakharov , Matthew Crosby , Zafeirios Fountas

Recommender systems have become an integral part of online platforms. Every day the volume of training data is expanding and the number of user interactions is constantly increasing. The exploration of larger and more expressive models has…

Information Retrieval · Computer Science 2025-02-13 Antonios Valkanas , Yuening Wang , Yingxue Zhang , Mark Coates

Sequential memory, the ability to form and accurately recall a sequence of events or stimuli in the correct order, is a fundamental prerequisite for biological and artificial intelligence as it underpins numerous cognitive functions (e.g.,…

Artificial Intelligence · Computer Science 2024-10-04 Ramy Mounir , Sudeep Sarkar

Online learning holds the promise of enabling efficient long-term credit assignment in recurrent neural networks. However, current algorithms fall short of offline backpropagation by either not being scalable or failing to learn long-range…

Machine Learning · Computer Science 2023-11-08 Nicolas Zucchet , Robert Meier , Simon Schug , Asier Mujika , João Sacramento

Imitation learning algorithms learn a policy from demonstrations of expert behavior. We show that, for deterministic experts, imitation learning can be done by reduction to reinforcement learning with a stationary reward. Our theoretical…

Machine Learning · Statistics 2022-03-16 Kamil Ciosek

Continual learning is a promising machine learning paradigm to learn new tasks while retaining previously learned knowledge over streaming training data. Till now, rehearsal-based methods, keeping a small part of data from old tasks as a…

Machine Learning · Computer Science 2023-08-04 Quanziang Wang , Renzhen Wang , Yuexiang Li , Dong Wei , Kai Ma , Yefeng Zheng , Deyu Meng

Deep reinforcement learning has enabled robots to learn motor skills from environmental interactions with minimal to no prior knowledge. However, existing reinforcement learning algorithms assume an episodic setting, in which the agent…

Machine Learning · Computer Science 2022-05-27 Jigang Kim , J. hyeon Park , Daesol Cho , H. Jin Kim

In sparse reward scenarios of reinforcement learning (RL), the memory mechanism provides promising shortcuts to policy optimization by reflecting on past experiences like humans. However, current memory-based RL methods simply store and…

Machine Learning · Computer Science 2026-05-28 Renye Yan , Yaozhong Gan , You Wu , Junliang Xing , Ling Liangn , Yeshang Zhu , Yimao Cai

Experience replay (ER) is a fundamental component of off-policy deep reinforcement learning (RL). ER recalls experiences from past iterations to compute gradient estimates for the current policy, increasing data-efficiency. However, the…

Machine Learning · Computer Science 2019-05-21 Guido Novati , Petros Koumoutsakos