English
Related papers

Related papers: Cluster-based Sampling in Hindsight Experience Rep…

200 papers

Efficiently allocating incoming jobs to nodes in large-scale clusters can lead to substantial improvements in both cluster utilization and job performance. In order to allocate incoming jobs, cluster schedulers usually rely on a set of…

Machine Learning · Computer Science 2026-03-12 Martin Asenov , Qiwen Deng , Gingfung Yeung , Adam Barker

Experience replay is widely used to improve learning efficiency in reinforcement learning by leveraging past experiences. However, existing experience replay methods, whether based on uniform or prioritized sampling, often suffer from low…

Machine Learning · Computer Science 2025-05-20 Kaiyan Zhao , Yiming Wang , Yuyang Chen , Yan Li , Leong Hou U , Xiaoguang Niu

Reinforcement Learning (RL) algorithms can suffer from poor sample efficiency when rewards are delayed and sparse. We introduce a solution that enables agents to learn temporally extended actions at multiple levels of abstraction in a…

Machine Learning · Computer Science 2019-03-11 Andrew Levy , Robert Platt , Kate Saenko

Ensemble clustering integrates a set of base clustering results to generate a stronger one. Existing methods usually rely on a co-association (CA) matrix that measures how many times two samples are grouped into the same cluster according…

Machine Learning · Computer Science 2023-02-24 Yuheng Jia , Sirui Tao , Ran Wang , Yongheng Wang

Even though reinforcement-learning-based algorithms achieved superhuman performance in many domains, the field of robotics poses significant challenges as the state and action spaces are continuous, and the reward function is predominantly…

In reinforcement learning (RL), experience replay-based sampling techniques play a crucial role in promoting convergence by eliminating spurious correlations. However, widely used methods such as uniform experience replay (UER) and…

Machine Learning · Computer Science 2023-02-07 Ramnath Kumar , Dheeraj Nagaraj

Improving sample efficiency is central to Reinforcement Learning (RL), especially in environments where the rewards are sparse. Some recent approaches have proposed to specify reward functions as manually designed or learned reward…

Machine Learning · Computer Science 2024-01-26 Shuai Han , Mehdi Dastani , Shihan Wang

Robotic manipulation and control has increased in importance in recent years. However, state of the art techniques still have limitations when required to operate in real world applications. This paper explores Hindsight Experience Replay…

Robotics · Computer Science 2022-09-27 Francisco Roldan Sanchez , Stephen Redmond , Kevin McGuinness , Noel O'Connor

Few-shot learning has been extensively explored to address problems where the amount of labeled samples is very limited for some classes. In the semi-supervised few-shot learning setting, substantial quantities of unlabeled samples are…

Computer Vision and Pattern Recognition · Computer Science 2025-12-16 Souvik Maji , Rhythm Baghel , Pratik Mazumder

There has been much recent research on human activity re\-cog\-ni\-tion (HAR), due to the proliferation of wearable sensors in watches and phones, and the advances of deep learning methods, which avoid the need to manually extract features…

Machine Learning · Computer Science 2022-09-20 Louis Mahon , Thomas Lukasiewicz

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

Several algorithms have been proposed to sample non-uniformly the replay buffer of deep Reinforcement Learning (RL) agents to speed-up learning, but very few theoretical foundations of these sampling schemes have been provided. Among…

Machine Learning · Computer Science 2022-06-15 Thibault Lahire , Matthieu Geist , Emmanuel Rachelson

Complex sequential tasks in continuous-control settings often require agents to successfully traverse a set of "narrow passages" in their state space. Solving such tasks with a sparse reward in a sample-efficient manner poses a challenge to…

Experience replay \citep{lin1993reinforcement, mnih2015human} is a widely used technique to achieve efficient use of data and improved performance in RL algorithms. In experience replay, past transitions are stored in a memory buffer and…

Machine Learning · Computer Science 2021-12-09 Liran Szlak , Ohad Shamir

Exploration strategy design is one of the challenging problems in reinforcement learning~(RL), especially when the environment contains a large state space or sparse rewards. During exploration, the agent tries to discover novel areas or…

Machine Learning · Computer Science 2019-06-07 Xiao Ma , Shen-Yi Zhao , Wu-Jun Li

Replay in neural networks involves training on sequential data with memorized samples, which counteracts forgetting of previous behavior caused by non-stationarity. We present a method where these auxiliary samples are generated on the fly,…

Machine Learning · Computer Science 2020-12-15 Xu Ji , Joao Henriques , Tinne Tuytelaars , Andrea Vedaldi

In order to learn quickly with few samples, meta-learning utilizes prior knowledge learned from previous tasks. However, a critical challenge in meta-learning is task uncertainty and heterogeneity, which can not be handled via globally…

Machine Learning · Computer Science 2019-11-19 Huaxiu Yao , Ying Wei , Junzhou Huang , Zhenhui Li

In general class-incremental learning, researchers typically use sample sets as a tool to avoid catastrophic forgetting during continuous learning. At the same time, researchers have also noted the differences between class-incremental…

Machine Learning · Computer Science 2024-08-16 Weimin Yin , Bin Chen adn Chunzhao Xie , Zhenhao Tan

Adapting machine learning algorithms to better handle the presence of clusters or batch effects within training datasets is important across a wide variety of biological applications. This article considers the effect of ensembling Random…

Machine Learning · Statistics 2025-04-01 Maya Ramchandran , Rajarshi Mukherjee , Giovanni Parmigiani

Traditional machine learning approaches assume that data comes from a single generating mechanism, which may not hold for most real life data. In these cases, the single mechanism assumption can result in suboptimal performance. We…

Machine Learning · Computer Science 2025-01-31 Mehmet Efe Lorasdagi , Ahmet Berker Koc , Ali Taha Koc , Suleyman Serdar Kozat