English
Related papers

Related papers: Memory-Efficient Episodic Control Reinforcement Le…

200 papers

We are interested in learning models of non-stationary environments, which can be framed as a multi-task learning problem. Model-free reinforcement learning algorithms can achieve good asymptotic performance in multi-task learning at a cost…

Machine Learning · Computer Science 2020-11-24 Elahe Aghapour , Nora Ayanian

The two main challenges faced by continual learning approaches are catastrophic forgetting and memory limitations on the storage of data. To cope with these challenges, we propose a novel, cognitively-inspired approach which trains…

Computer Vision and Pattern Recognition · Computer Science 2020-07-15 Ali Ayub , Alan R. Wagner

Generalising the idea of the classical EM algorithm that is widely used for computing maximum likelihood estimates, we propose an EM-Control (EM-C) algorithm for solving multi-period finite time horizon stochastic control problems. The new…

Economics · Quantitative Finance 2016-11-08 Steven Kou , Xianhua Peng , Xingbo Xu

Recent breakthroughs in Go play and strategic games have witnessed the great potential of reinforcement learning in intelligently scheduling in uncertain environment, but some bottlenecks are also encountered when we generalize this…

Machine Learning · Computer Science 2018-12-27 Xingxing Liang , Qi Wang , Yanghe Feng , Zhong Liu , Jincai Huang

Event detection (ED), a sub-task of event extraction, involves identifying triggers and categorizing event mentions. Existing methods primarily rely upon supervised learning and require large-scale labeled event datasets which are…

Computation and Language · Computer Science 2023-02-03 Shumin Deng , Ningyu Zhang , Jiaojian Kang , Yichi Zhang , Wei Zhang , Huajun Chen

Many DNN-enabled vision applications constantly operate under severe energy constraints such as unmanned aerial vehicles, Augmented Reality headsets, and smartphones. Designing DNNs that can meet a stringent energy budget is becoming…

Machine Learning · Computer Science 2019-04-09 Haichuan Yang , Yuhao Zhu , Ji Liu

The evolution of Large Language Model (LLM) agents towards System~2 reasoning, characterized by deliberative, high-precision problem-solving, requires maintaining rigorous logical integrity over extended horizons. However, prevalent memory…

Artificial Intelligence · Computer Science 2026-05-15 Kaixiang Wang , Yidan Lin , Jiong Lou , Zhaojiacheng Zhou , Bunyod Suvonov , Jie Li

Bayesian meta-learning enables robust and fast adaptation to new tasks with uncertainty assessment. The key idea behind Bayesian meta-learning is empirical Bayes inference of hierarchical model. In this work, we extend this framework to…

Machine Learning · Computer Science 2020-11-19 Yayi Zou , Xiaoqi Lu

We introduce a lifelong language learning setup where a model needs to learn from a stream of text examples without any dataset identifier. We propose an episodic memory model that performs sparse experience replay and local adaptation to…

Machine Learning · Computer Science 2019-11-27 Cyprien de Masson d'Autume , Sebastian Ruder , Lingpeng Kong , Dani Yogatama

Current generation of memory-augmented neural networks has limited scalability as they cannot efficiently process data that are too large to fit in the external memory storage. One example of this is lifelong learning scenario where the…

Machine Learning · Computer Science 2018-12-12 Hyunwoo Jung , Moonsu Han , Minki Kang , Sungju Hwang

Class-Incremental Learning (CIL) [40] trains classifiers under a strict memory budget: in each incremental phase, learning is done for new data, most of which is abandoned to free space for the next phase. The preserved data are exemplars…

Computer Vision and Pattern Recognition · Computer Science 2023-01-18 Yaoyao Liu , Bernt Schiele , Qianru Sun

Efficient energy management is essential for reliable and sustainable microgrid operation amid increasing renewable integration. In this paper, an imitation learning-based framework to approximate mixed-integer Economic Model Predictive…

Systems and Control · Electrical Eng. & Systems 2026-04-29 Changrui Liu , Shengling Shi , Anil Alan , Ganesh Kumar Venayagamoorthy , Bart De Schutter

Performance metrics-driven context caching has a profound impact on throughput and response time in distributed context management systems for real-time context queries. This paper proposes a reinforcement learning based approach to…

Systems and Control · Electrical Eng. & Systems 2023-02-10 Shakthi Weerasinghe , Arkady Zaslavsky , Seng W. Loke , Amin Abken , Alireza Hassani

Modern deep-learning training is not memoryless. Updates depend on optimizer moments and averaging, data-order policies (random reshuffling vs with-replacement, staged augmentations and replay), the nonconvex path, and auxiliary state…

Machine Learning · Computer Science 2026-01-30 Vasileios Sevetlidis , George Pavlidis

In this paper, we propose an adaptive event-triggered reinforcement learning control for continuous-time nonlinear systems, subject to bounded uncertainties, characterized by complex interactions. Specifically, the proposed method is…

Machine Learning · Computer Science 2024-10-01 Umer Siddique , Abhinav Sinha , Yongcan Cao

Model-based reinforcement learning has shown promise for improving sample efficiency and decision-making in complex environments. However, existing methods face challenges in training stability, robustness to noise, and computational…

Machine Learning · Computer Science 2024-10-08 Yutaka Shimizu , Masayoshi Tomizuka

Ensemble learning is a meta-learning approach that combines the predictions of multiple learners, demonstrating improved accuracy and robustness. Nevertheless, ensembling models like Convolutional Neural Networks (CNNs) result in high…

Distributed, Parallel, and Cluster Computing · Computer Science 2024-09-16 Le Zhang , Onat Gungor , Flavio Ponzina , Tajana Rosing

A properly designed controller can help improve the quality of experimental measurements or force a dynamical system to follow a completely new time-evolution path. Recent developments in deep reinforcement learning have made steep advances…

Statistical Mechanics · Physics 2025-02-26 Ruslan Mukhamadiarov

Model-based strategies for control are critical to obtain sample efficient learning. Dyna is a planning paradigm that naturally interleaves learning and planning, by simulating one-step experience to update the action-value function. This…

Artificial Intelligence · Computer Science 2018-06-13 Yangchen Pan , Muhammad Zaheer , Adam White , Andrew Patterson , Martha White

We present a theoretical study of continual and experiential learning in large language model agents that combine episodic memory with reinforcement learning. We argue that the key mechanism for continual adaptation, without updating model…

Artificial Intelligence · Computer Science 2026-01-30 Jun Wang