English
Related papers

Related papers: Scaling Off-Policy Reinforcement Learning with Bat…

200 papers

Normalization layers have recently experienced a renaissance in the deep reinforcement learning and continual learning literature, with several works highlighting diverse benefits such as improving loss landscape conditioning and combatting…

Machine Learning · Computer Science 2024-07-03 Clare Lyle , Zeyu Zheng , Khimya Khetarpal , James Martens , Hado van Hasselt , Razvan Pascanu , Will Dabney

Existing neural networks are memory-consuming and computationally intensive, making deploying them challenging in resource-constrained environments. However, there are various methods to improve their efficiency. Two such methods are…

Machine Learning · Computer Science 2023-11-10 Anastasiia Prutianova , Alexey Zaytsev , Chung-Kuei Lee , Fengyu Sun , Ivan Koryakovskiy

While robot learning has demonstrated promising results for enabling robots to automatically acquire new skills, a critical challenge in deploying learning-based systems is scale: acquiring enough data for the robot to effectively…

Many failures in deep continual and reinforcement learning are associated with increasing magnitudes of the weights, making them hard to change and potentially causing overfitting. While many methods address these learning failures, they…

Machine Learning · Computer Science 2024-07-03 Mohamed Elsayed , Qingfeng Lan , Clare Lyle , A. Rupam Mahmood

Diffusion models have achieved remarkable success in image generation but come with significant computational costs, posing challenges for deployment in resource-constrained environments. Recent post-training quantization (PTQ) methods have…

Computer Vision and Pattern Recognition · Computer Science 2025-07-18 Dongyeun Lee , Jiwan Hur , Hyounguk Shon , Jae Young Lee , Junmo Kim

Batch Normalization is a commonly used trick to improve the training of deep neural networks. These neural networks use L2 regularization, also called weight decay, ostensibly to prevent overfitting. However, we show that L2 regularization…

Machine Learning · Computer Science 2017-06-19 Twan van Laarhoven

Robust real-world learning should benefit from both demonstrations and interactions with the environment. Current approaches to learning from demonstration and reward perform supervised learning on expert demonstration data and use…

Artificial Intelligence · Computer Science 2019-05-31 Yang Gao , Huazhe Xu , Ji Lin , Fisher Yu , Sergey Levine , Trevor Darrell

Deep Reinforcement Learning (RL) methods rely on experience replay to approximate the minibatched supervised learning setting; however, unlike supervised learning where access to lots of training data is crucial to generalization,…

Machine Learning · Computer Science 2021-02-24 Brett Daley , Cameron Hickert , Christopher Amato

Quantum computers have rapidly improved in scale and fidelity, yet access to large systems remains limited for most researchers. This makes accurate and scalable noisy quantum simulation essential. While density matrix simulation provides…

Quantum Physics · Physics 2026-05-19 Siddharth Dangwal , Tina Oberoi , Ajay Sailopal , Dhirpal Shah , Frederic T. Chong

Post-training quantization (PTQ) reduces a model's memory footprint by mapping full precision weights into low bit weights without costly retraining, but can degrade its downstream performance especially in low 2- to 3-bit settings. We…

Machine Learning · Computer Science 2025-07-18 Hanqi Xiao , Yi-Lin Sung , Elias Stengel-Eskin , Mohit Bansal

While agents trained by Reinforcement Learning (RL) can solve increasingly challenging tasks directly from visual observations, generalizing learned skills to novel environments remains very challenging. Extensive use of data augmentation…

Machine Learning · Computer Science 2021-12-10 Nicklas Hansen , Hao Su , Xiaolong Wang

Reinforcement learning provides a framework for learning to control which actions to take towards completing a task through trial-and-error. In many applications observing interactions is costly, necessitating sample-efficient learning. In…

Machine Learning · Statistics 2020-11-04 Charles Gadd , Markus Heinonen , Harri Lähdesmäki , Samuel Kaski

Conventional wisdom holds that large-batch training is fundamentally incompatible with Reinforcement Learning (RL) - beyond a modest threshold, increasing batch sizes typically yields diminishing returns or performance degradation due to…

Machine Learning · Statistics 2026-05-22 Jongchan Park

3D policy learning promises superior generalization and cross-embodiment transfer, but progress has been hindered by training instabilities and severe overfitting, precluding the adoption of powerful 3D perception models. In this work, we…

Computer Vision and Pattern Recognition · Computer Science 2026-04-17 Zhengdong Hong , Shenrui Wu , Haozhe Cui , Boyi Zhao , Ran Ji , Yiyang He , Hangxing Zhang , Zundong Ke , Jun Wang , Guofeng Zhang , Jiayuan Gu

Performing unsupervised domain adaptation on resource-constrained edge devices is challenging. Existing research typically adopts architecture optimization (e.g., designing slimmable networks) but requires expensive training costs.…

Computer Vision and Pattern Recognition · Computer Science 2024-09-16 Nanyang Du , Chen Tang , Yuxiao Jiang , Yuan Meng , Zhi Wang

Unsupervised reinforcement learning (URL) poses a promising paradigm to learn useful behaviors in a task-agnostic environment without the guidance of extrinsic rewards to facilitate the fast adaptation of various downstream tasks. Previous…

Machine Learning · Computer Science 2023-02-23 Yifu Yuan , Jianye Hao , Fei Ni , Yao Mu , Yan Zheng , Yujing Hu , Jinyi Liu , Yingfeng Chen , Changjie Fan

We study offline multitask reinforcement learning in settings where multiple tasks share a low-rank representation of their action-value functions. In this regime, a learner is provided with fixed datasets collected from several related…

Machine Learning · Computer Science 2026-04-28 Kausthubh Manda , Raghuram Bharadwaj Diddigi

The realization of scalable fault-tolerant quantum computing is expected to hinge on quantum error-correcting codes. In the quest for more efficient quantum fault tolerance, a critical code parameter is the weight of measurements that…

Quantum Physics · Physics 2025-02-21 Austin Yubo He , Zi-Wen Liu

Unloading containers in the courier, express and parcel industry is a physically demanding and labor-intensive work. Automatizing this process is an important step towards increasing the efficiency of parcel-handling systems. This work…

Systems and Control · Electrical Eng. & Systems 2026-05-27 Jan Rüdiger , Max Schenke , Daniel Weber

Modern machine learning models are becoming increasingly expensive to train for real-world image and text classification tasks, where massive web-scale data is collected in a streaming fashion. To reduce the training cost, online batch…

Machine Learning · Computer Science 2024-11-26 William Bankes , George Hughes , Ilija Bogunovic , Zi Wang