English
Related papers

Related papers: Generalized Advantage Estimation for Distributiona…

200 papers

We study a reinforcement learning setting, where the state transition function is a convex combination of a stochastic continuous function and a deterministic function. Such a setting generalizes the widely-studied stochastic state…

Machine Learning · Computer Science 2018-10-03 Qingpeng Cai , Ling Pan , Pingzhong Tang

This paper considers policy search in continuous state-action reinforcement learning problems. Typically, one computes search directions using a classic expression for the policy gradient called the Policy Gradient Theorem, which decomposes…

Machine Learning · Computer Science 2020-04-13 Sujay Bhatt , Alec Koppel , Vikram Krishnamurthy

Distributional reinforcement learning (DRL) is a recent reinforcement learning framework whose success has been supported by various empirical studies. It relies on the key idea of replacing the expected return with the return distribution,…

Machine Learning · Computer Science 2020-01-09 Rahul Singh , Keuntaek Lee , Yongxin Chen

While reinforcement learning methods such as Group Relative Preference Optimization (GRPO) have significantly enhanced Large Language Models, adapting them to diffusion models remains challenging. In particular, GRPO demands a stochastic…

Machine Learning · Computer Science 2025-10-10 Yihong Luo , Tianyang Hu , Jing Tang

Gradient compression has surfaced as a key technique to address the challenge of communication efficiency in distributed learning. In distributed deep learning, however, it is observed that gradient distributions are heavy-tailed, with…

Machine Learning · Computer Science 2024-02-07 Guangfeng Yan , Tan Li , Yuanzhang Xiao , Hanxu Hou , Linqi Song

Generative adversarial imitation learning (GAIL) is a popular inverse reinforcement learning approach for jointly optimizing policy and reward from expert trajectories. A primary question about GAIL is whether applying a certain policy…

Machine Learning · Computer Science 2020-06-26 Ziwei Guan , Tengyu Xu , Yingbin Liang

Excessive computational cost for learning large data and streaming data can be alleviated by using stochastic algorithms, such as stochastic gradient descent and its variants. Recent advances improve stochastic algorithms on convergence…

Machine Learning · Statistics 2019-09-24 Shih-Kang Chao , Guang Cheng

In this paper, we propose a novel normalization method called gradient normalization (GN) to tackle the training instability of Generative Adversarial Networks (GANs) caused by the sharp gradient space. Unlike existing work such as gradient…

Machine Learning · Computer Science 2021-10-12 Yi-Lun Wu , Hong-Han Shuai , Zhi-Rui Tam , Hong-Yu Chiu

Modeling correlated or highly stratified multiple-response data becomes a common data analysis task due to modern data monitoring facilities and methods. Generalized estimating equations (GEE) is one of the popular statistical methods for…

Methodology · Statistics 2019-03-05 Zimu Chen , Zhanfeng Wang , Yuan-chin Ivan Chang

A new Wasserstein multi-element polynomial chaos expansion (WPCE) is proposed, which is inspired by recent advances in computational optimal transport for estimating Wasserstein distances. The developed method combines unsupervised learning…

Numerical Analysis · Mathematics 2024-10-17 Robert Gruhlke , Martin Eigel

In modern GANs, maintaining an Exponential Moving Average (EMA) of the generator's weights is a standard practice, as such an averaged model consistently outperforms the actively trained generator. However, the EMA generator is used for…

Computer Vision and Pattern Recognition · Computer Science 2026-05-12 Antoni Nowinowski , Krzysztof Krawiec

In Generalized Linear Estimation (GLE) problems, we seek to estimate a signal that is observed through a linear transform followed by a component-wise, possibly nonlinear and noisy, channel. In the Bayesian optimal setting, Generalized…

Disordered Systems and Neural Networks · Physics 2021-02-03 Luca Saglietti , Yue M. Lu , Carlo Lucibello

Wasserstein Generative Adversarial Networks (WGANs) provide a versatile class of models, which have attracted great attention in various applications. However, this framework has two main drawbacks: (i) Wasserstein-1 (or Earth-Mover)…

Machine Learning · Statistics 2021-07-20 Xin Guo , Johnny Hong , Tianyi Lin , Nan Yang

We introduce a novel and scalable Bayesian framework for multivariate-density-density regression (DDR), designed to model relationships between multivariate distributions. Our approach addresses the critical issue of distributions residing…

Methodology · Statistics 2025-09-24 Khai Nguyen , Yang Ni , Peter Mueller

Policy gradient methods are reinforcement learning algorithms that adapt a parameterized policy by following a performance gradient estimate. Conventional policy gradient methods use Monte-Carlo techniques to estimate the gradient, which…

Machine Learning · Computer Science 2026-05-01 Mohammad Ghavamzadeh , Yaakov Engel , Michal Valko

Differential Networks (DNs), tools that encapsulate interactions within intricate systems, are brought under the Bayesian lens in this research. A novel na{\i}ve Bayesian adaptive graphical elastic net (BAE) prior is introduced to estimate…

Methodology · Statistics 2023-06-27 J. Smith , A. Bekker , M. Arashi

Generative Adversarial Networks (GANs) are one of the most popular tools for learning complex high dimensional distributions. However, generalization properties of GANs have not been well understood. In this paper, we analyze the…

Machine Learning · Computer Science 2019-02-12 Hoang Thanh-Tung , Truyen Tran , Svetha Venkatesh

In contrast to classical reinforcement learning (RL), distributional RL algorithms aim to learn the distribution of returns rather than their expected value. Since the nature of the return distribution is generally unknown a priori or…

Machine Learning · Computer Science 2025-03-17 Moritz A. Zanger , Wendelin Böhmer , Matthijs T. J. Spaan

Bayesian optimization has been successful at global optimization of expensive-to-evaluate multimodal objective functions. However, unlike most optimization methods, Bayesian optimization typically does not use derivative information. In…

Machine Learning · Statistics 2018-02-08 Jian Wu , Matthias Poloczek , Andrew Gordon Wilson , Peter I. Frazier

Reinforcement learning algorithms rely on exploration to discover new behaviors, which is typically achieved by following a stochastic policy. In continuous control tasks, policies with a Gaussian distribution have been widely adopted.…

Machine Learning · Computer Science 2019-03-28 Dmytro Korenkevych , A. Rupam Mahmood , Gautham Vasan , James Bergstra