English
Related papers

Related papers: Coordinate-wise Control Variates for Deep Policy G…

200 papers

Policy gradient methods have demonstrated success in reinforcement learning tasks that have high-dimensional continuous state and action spaces. However, policy gradient methods are also notoriously sample inefficient. This can be…

Machine Learning · Computer Science 2019-08-12 Ching-An Cheng , Xinyan Yan , Byron Boots

Variational inference in Bayesian deep learning often involves computing the gradient of an expectation that lacks a closed-form solution. In these cases, pathwise and score-function gradient estimators are the most common approaches. The…

Machine Learning · Statistics 2024-10-10 Kenyon Ng , Susan Wei

In statistics and machine learning, approximation of an intractable integration is often achieved by using the unbiased Monte Carlo estimator, but the variances of the estimation are generally high in many applications. Control variates…

Machine Learning · Statistics 2019-10-16 Ruosi Wan , Mingjun Zhong , Haoyi Xiong , Zhanxing Zhu

Zero-variance control variates (ZV-CV) are a post-processing method to reduce the variance of Monte Carlo estimators of expectations using the derivatives of the log target. Once the derivatives are available, the only additional…

Computation · Statistics 2022-08-17 Leah F. South , Chris J. Oates , Antonietta Mira , Christopher Drovandi

Policy gradient methods have achieved remarkable successes in solving challenging reinforcement learning problems. However, it still often suffers from the large variance issue on policy gradient estimation, which leads to poor sample…

Machine Learning · Statistics 2018-02-26 Hao Liu , Yihao Feng , Yi Mao , Dengyong Zhou , Jian Peng , Qiang Liu

Control variates are variance reduction tools for Monte Carlo estimators. They can provide significant variance reduction, but usually require a large number of samples, which can be prohibitive when sampling or evaluating the integrand is…

Methodology · Statistics 2023-06-08 Zhuo Sun , Alessandro Barp , François-Xavier Briol

Policy gradient methods have enjoyed great success in deep reinforcement learning but suffer from high variance of gradient estimates. The high variance problem is particularly exasperated in problems with long horizons or high-dimensional…

Machine Learning · Computer Science 2018-03-21 Cathy Wu , Aravind Rajeswaran , Yan Duan , Vikash Kumar , Alexandre M Bayen , Sham Kakade , Igor Mordatch , Pieter Abbeel

Variational inference is increasingly being addressed with stochastic optimization. In this setting, the gradient's variance plays a crucial role in the optimization procedure, since high variance gradients lead to poor convergence. A…

Machine Learning · Computer Science 2020-10-23 Tomas Geffner , Justin Domke

We propose neural control variates (NCV) for unbiased variance reduction in parametric Monte Carlo integration. So far, the core challenge of applying the method of control variates has been finding a good approximation of the integrand…

Machine Learning · Computer Science 2020-09-07 Thomas Müller , Fabrice Rousselle , Jan Novák , Alexander Keller

Policy gradient methods are a widely used class of model-free reinforcement learning algorithms where a state-dependent baseline is used to reduce gradient estimator variance. Several recent papers extend the baseline to depend on both the…

Machine Learning · Computer Science 2018-11-20 George Tucker , Surya Bhupatiraju , Shixiang Gu , Richard E. Turner , Zoubin Ghahramani , Sergey Levine

In this paper, a novel optimal control-based baseline function is presented for the policy gradient method in deep reinforcement learning (RL). The baseline is obtained by computing the value function of an optimal control problem, which is…

Machine Learning · Computer Science 2024-11-07 Xubo Lyu , Site Li , Seth Siriya , Ye Pu , Mo Chen

Neural control variates (NCVs) have emerged as a powerful tool for variance reduction in Monte Carlo (MC) simulations, particularly in high-dimensional problems where traditional control variates are difficult to construct analytically. By…

High Energy Physics - Lattice · Physics 2025-08-22 Hyunwoo Oh

Policy-gradient methods in Reinforcement Learning(RL) are very universal and widely applied in practice but their performance suffers from the high variance of the gradient estimate. Several procedures were proposed to reduce it including…

Machine Learning · Computer Science 2022-06-16 Maxim Kaledin , Alexander Golubev , Denis Belomestny

Control variates are a well-established tool to reduce the variance of Monte Carlo estimators. However, for large-scale problems including high-dimensional and large-sample settings, their advantages can be outweighed by a substantial…

Machine Learning · Statistics 2021-07-22 Shijing Si , Chris. J. Oates , Andrew B. Duncan , Lawrence Carin , François-Xavier Briol

Policy gradient methods in reinforcement learning have become increasingly prevalent for state-of-the-art performance in continuous control tasks. Novel methods typically benchmark against a few key algorithms such as deep deterministic…

Machine Learning · Computer Science 2017-08-15 Riashat Islam , Peter Henderson , Maziar Gomrokchi , Doina Precup

Volt-var control (VVC) is the problem of operating power distribution systems within healthy regimes by controlling actuators in power systems. Existing works have mostly adopted the conventional routine of representing the power systems (a…

Machine Learning · Computer Science 2022-06-22 Xian Yeow Lee , Soumik Sarkar , Yubo Wang

Control variates can be a powerful tool to reduce the variance of Monte Carlo estimators, but constructing effective control variates can be challenging when the number of samples is small. In this paper, we show that when a large number of…

Methodology · Statistics 2023-06-08 Zhuo Sun , Chris J. Oates , François-Xavier Briol

The control variates method is a classical variance reduction technique for Monte Carlo estimators that exploits correlated auxiliary variables without introducing bias. In many applications, the quantity of interest can be expressed as a…

Statistics Theory · Mathematics 2025-11-10 Louison Bocquet-Nouaille , Jérôme Morio , Benjamin Bobbia

Results obtained with stochastic methods have an inherent uncertainty due to the finite number of samples that can be achieved in practice. In lattice QCD this problem is particularly salient in some observables like, for instance,…

High Energy Physics - Lattice · Physics 2025-03-13 Paulo F. Bedaque , Hyunwoo Oh

Gradient-based methods have been widely used for system design and optimization in diverse application domains. Recently, there has been a renewed interest in studying theoretical properties of these methods in the context of control and…

Optimization and Control · Mathematics 2022-10-11 Bin Hu , Kaiqing Zhang , Na Li , Mehran Mesbahi , Maryam Fazel , Tamer Başar
‹ Prev 1 2 3 10 Next ›