English
Related papers

Related papers: An Investigation of Batch Normalization in Off-Pol…

200 papers

Meta-learning is a branch of machine learning which trains neural network models to synthesize a wide variety of data in order to rapidly solve new problems. In process control, many systems have similar and well-understood dynamics, which…

Systems and Control · Electrical Eng. & Systems 2022-09-20 Daniel G. McClement , Nathan P. Lawrence , Johan U. Backstrom , Philip D. Loewen , Michael G. Forbes , R. Bhushan Gopaluni

Deep neural networks have a clear degradation when applying to the unseen environment due to the covariate shift. Conventional approaches like domain adaptation requires the pre-collected target data for iterative training, which is…

Computer Vision and Pattern Recognition · Computer Science 2021-10-11 Fuming You , Jingjing Li , Zhou Zhao

Most prior approaches to offline reinforcement learning (RL) utilize \textit{behavior regularization}, typically augmenting existing off-policy actor critic algorithms with a penalty measuring divergence between the policy and the offline…

Machine Learning · Computer Science 2021-10-15 Haoran Xu , Xianyuan Zhan , Jianxiong Li , Honglei Yin

Batch Normalization (BN) is widely used to stabilize the optimization process and improve the test performance of deep neural networks. The regularization effect of BN depends on the batch size and explicitly using smaller batch sizes with…

Machine Learning · Computer Science 2023-12-20 Atli Kosson , Dongyang Fan , Martin Jaggi

Adversarial attacks and robustness in Deep Reinforcement Learning (DRL) have been widely studied in various threat models; however, few consider environmental state perturbations, which are natural in embodied scenarios. To improve the…

Machine Learning · Computer Science 2025-06-11 Chenxu Wang , Huaping Liu

We consider off-dynamics reinforcement learning (RL) where one needs to transfer policies across different domains with dynamics mismatch. Despite the focus on developing dynamics-aware algorithms, this field is hindered due to the lack of…

Machine Learning · Computer Science 2024-10-29 Jiafei Lyu , Kang Xu , Jiacheng Xu , Mengbei Yan , Jingwen Yang , Zongzhang Zhang , Chenjia Bai , Zongqing Lu , Xiu Li

Batch normalization (BN) is a ubiquitous operation in deep neural networks, primarily used to improve stability and regularization during training. BN centers and scales feature maps using sample means and variances, which are naturally…

Machine Learning · Statistics 2026-02-04 Sofia Ivolgina , P. Thomas Fletcher , Baba C. Vemuri

Off-policy reinforcement learning algorithms promise to be applicable in settings where only a fixed data-set (batch) of environment interactions is available and no new experience can be acquired. This property makes these algorithms…

Actor-critic deep reinforcement learning (DRL) algorithms have recently achieved prominent success in tackling various challenging reinforcement learning (RL) problems, particularly complex control tasks with high-dimensional continuous…

Machine Learning · Computer Science 2023-05-04 Gang Chen , Victoria Huang

Sampling from unnormalized probability densities is a central challenge in computational science. Boltzmann generators are generative models that enable independent sampling from the Boltzmann distribution of physical systems at a given…

Machine Learning · Computer Science 2026-02-04 Henrik Schopmans , Christopher von Klitzing , Pascal Friederich

Deep neural networks (DNNs) are the workhorses of deep learning, which constitutes the state of the art in numerous application domains. However, DNN-based decision rules are notoriously prone to poor generalization, i.e., may prove…

Machine Learning · Computer Science 2023-05-11 Guy Amir , Osher Maayan , Tom Zelazny , Guy Katz , Michael Schapira

Learning a predictive model of the mean return, or value function, plays a critical role in many reinforcement learning algorithms. Distributional reinforcement learning (DRL) has been shown to improve performance by modeling the value…

Machine Learning · Computer Science 2025-07-08 Ju-Seung Byun , Andrew Perrault

In this work, we describe a new approach that uses deep neural networks (DNN) to obtain regularization parameters for solving inverse problems. We consider a supervised learning approach, where a network is trained to approximate the…

Numerical Analysis · Mathematics 2021-04-15 Babak Maboudi Afkham , Julianne Chung , Matthias Chung

Batch reinforcement learning (RL) is important to apply RL algorithms to many high stakes tasks. Doing batch RL in a way that yields a reliable new policy in large domains is challenging: a new decision policy may visit states and actions…

Machine Learning · Computer Science 2020-07-23 Yao Liu , Adith Swaminathan , Alekh Agarwal , Emma Brunskill

Normalization techniques play an important role in supporting efficient and often more effective training of deep neural networks. While conventional methods explicitly normalize the activations, we suggest to add a loss term instead. This…

Machine Learning · Computer Science 2018-11-22 Etai Littwin , Lior Wolf

Reinforcement learning (RL) algorithms have been around for decades and employed to solve various sequential decision-making problems. These algorithms however have faced great challenges when dealing with high-dimensional environments. The…

Machine Learning · Computer Science 2020-04-01 Thanh Thi Nguyen , Ngoc Duy Nguyen , Saeid Nahavandi

Many reinforcement learning algorithms, particularly those that rely on return estimates for policy improvement, can suffer from poor sample efficiency and training instability due to high-variance return estimates. In this paper we…

Machine Learning · Computer Science 2026-01-06 Alexander W. Goodall , Edwin Hamel-De le Court , Francesco Belardinelli

Extensive utilization of deep reinforcement learning (DRL) policy networks in diverse continuous control tasks has raised questions regarding performance degradation in expansive state spaces where the input state norm is larger than that…

Machine Learning · Computer Science 2024-01-02 Ruining Zhang , Haoran Han , Maolong Lv , Qisong Yang , Jian Cheng

In the Bayesian reinforcement learning (RL) setting, a prior distribution over the unknown problem parameters -- the rewards and transitions -- is assumed, and a policy that optimizes the (posterior) expected return is sought. A common…

Machine Learning · Computer Science 2021-09-27 Aviv Tamar , Daniel Soudry , Ev Zisselman

The widespread use of Batch Normalization has enabled training deeper neural networks with more stable and faster results. However, the Batch Normalization works best using large batch size during training and as the state-of-the-art…

Computer Vision and Pattern Recognition · Computer Science 2020-11-24 Martin Kolarik , Radim Burget , Kamil Riha