English
Related papers

Related papers: Beyond Distributions: Geometric Action Control for…

200 papers

Offline reinforcement learning learns from a static dataset without interacting with environments, which ensures security and thus owns a good application prospect. However, directly applying naive reinforcement learning algorithm usually…

Machine Learning · Computer Science 2024-11-08 Yi Shen , Hanyan Huang

Generative adversarial nets (GANs) have become a preferred tool for tasks involving complicated distributions. To stabilise the training and reduce the mode collapse of GANs, one of their main variants employs the integral probability…

Machine Learning · Computer Science 2020-10-27 Shengxi Li , Zeyang Yu , Min Xiang , Danilo Mandic

3D Gaussian Splatting (3DGS) has become one of the most influential works in the past year. Due to its efficient and high-quality novel view synthesis capabilities, it has been widely adopted in many research fields and applications.…

Computer Vision and Pattern Recognition · Computer Science 2025-03-19 Glenn Grubert , Florian Barthel , Anna Hilsmann , Peter Eisert

Training generative adversarial networks (GANs) is known to be difficult, especially for financial time series. This paper first analyzes the well-posedness problem in GANs minimax games and the convexity issue in GANs objective functions.…

Machine Learning · Statistics 2021-12-28 Othmane Mounjid , Xin Guo

Decentralized training is often regarded as inferior to centralized training because the consensus errors between workers are thought to undermine convergence and generalization, even with homogeneous data distributions. This work…

Machine Learning · Computer Science 2026-02-04 Zesen Wang , Mikael Johansson

Deep Reinforcement Learning (DRL) methods have performed well in an increasing numbering of high-dimensional visual decision making domains. Among all such visual decision making problems, those with discrete action spaces often tend to…

Machine Learning · Computer Science 2017-05-23 Sahil Sharma , Aravind Suresh , Rahul Ramesh , Balaraman Ravindran

Many commodity sensors that measure the robot and dynamic obstacle's state have non-Gaussian noise characteristics. Yet, many current approaches treat the underlying-uncertainty in motion and perception as Gaussian, primarily to ensure…

Robotics · Computer Science 2022-09-23 Anish Gupta , Arun Kumar Singh , K. Madhava Krishna

We introduce a novel reinforcement learning (RL) framework that treats parameterized action distributions as actions, redefining the boundary between agent and environment. This reparameterization makes the new action space continuous,…

Machine Learning · Computer Science 2026-05-15 Jiamin He , A. Rupam Mahmood , Martha White

Recent reinforcement learning approaches have shown surprisingly strong capabilities of bang-bang policies for solving continuous control benchmarks. The underlying coarse action space discretizations often yield favourable exploration…

Machine Learning · Computer Science 2024-04-08 Tim Seyde , Peter Werner , Wilko Schwarting , Markus Wulfmeier , Daniela Rus

Optimization is crucial for MEC networks to function efficiently and reliably, most of which are NP-hard and lack efficient approximation algorithms. This leads to a paucity of optimal solution, constraining the effectiveness of…

Networking and Internet Architecture · Computer Science 2025-05-06 Ruihuai Liang , Bo Yang , Pengyu Chen , Xuelin Cao , Zhiwen Yu , Mérouane Debbah , Dusit Niyato , H. Vincent Poor , Chau Yuen

Generative adversarial networks (GANs) aim to generate realistic data from some prior distribution (e.g., Gaussian noises). However, such prior distribution is often independent of real data and thus may lose semantic information (e.g.,…

Computer Vision and Pattern Recognition · Computer Science 2018-06-15 Jiezhang Cao , Yong Guo , Qingyao Wu , Chunhua Shen , Junzhou Huang , Mingkui Tan

Realistic human geometry generation is an important yet challenging task, requiring both the preservation of fine clothing details and the accurate modeling of clothing-body interactions. To tackle this challenge, we build upon Geometry…

Computer Vision and Pattern Recognition · Computer Science 2026-05-01 Xiangjun Tang , Biao Zhang , Peter Wonka

Robust federated learning aims to maintain reliable performance despite the presence of adversarial or misbehaving workers. While state-of-the-art (SOTA) robust distributed gradient descent (Robust-DGD) methods were proven theoretically…

Machine Learning · Computer Science 2025-05-12 Youssef Allouah , Rachid Guerraoui , Nirupam Gupta , Ahmed Jellouli , Geovani Rizk , John Stephan

Generative adversarial networks (GANs) are effective in generating realistic images but the training is often unstable. There are existing efforts that model the training dynamics of GANs in the parameter space but the analysis cannot…

Machine Learning · Computer Science 2020-07-09 Kun Xu , Chongxuan Li , Jun Zhu , Bo Zhang

Many deep generative models are defined as a push-forward of a Gaussian measure by a continuous generator, such as Generative Adversarial Networks (GANs) or Variational Auto-Encoders (VAEs). This work explores the latent space of such deep…

Machine Learning · Computer Science 2023-05-16 Thibaut Issenhuth , Ugo Tanielian , Jérémie Mary , David Picard

Learning from human feedback is a viable alternative to control design that does not require modelling or control expertise. Particularly, learning from corrective advice garners advantages over evaluative feedback as it is a more intuitive…

Machine Learning · Computer Science 2019-03-14 Daan Wout , Jan Scholten , Carlos Celemin , Jens Kober

Generative adversarial networks (GANs) while being very versatile in realistic image synthesis, still are sensitive to the input distribution. Given a set of data that has an imbalance in the distribution, the networks are susceptible to…

Computer Vision and Pattern Recognition · Computer Science 2018-02-05 Shashank Sharma , Vinay P. Namboodiri

Reinforcement learning for control over continuous spaces typically uses high-entropy stochastic policies, such as Gaussian distributions, for local exploration and estimating policy gradient to optimize performance. Many robotic control…

Machine Learning · Computer Science 2024-04-03 Ya-Chien Chang , Sicun Gao

Soft Actor-Critic algorithm is widely recognized for its robust performance across a range of deep reinforcement learning tasks, where it leverages the tanh transformation to constrain actions within bounded limits. However, this…

Machine Learning · Computer Science 2025-04-23 Yanjun Chen , Xinming Zhang , Xianghui Wang , Zhiqiang Xu , Xiaoyu Shen , Wei Zhang

Existing 4D Gaussian Splatting methods rely on per-Gaussian deformation from a canonical space to target frames, which overlooks redundancy among adjacent Gaussian primitives and results in suboptimal performance. To address this…

Computer Vision and Pattern Recognition · Computer Science 2025-05-14 He Huang , Qi Yang , Mufan Liu , Yiling Xu , Zhu Li