English
Related papers

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

200 papers

Policy gradient methods are powerful reinforcement learning algorithms and have been demonstrated to solve many complex tasks. However, these methods are also data-inefficient, afflicted with high variance gradient estimates, and frequently…

Machine Learning · Computer Science 2019-05-15 Andreas Doerr , Michael Volpp , Marc Toussaint , Sebastian Trimpe , Christian Daniel

In this work, we develop a reduced-basis approach for the efficient computation of parametrized expected values, for a large number of parameter values, using the control variate method to reduce the variance. Two algorithms are proposed to…

Numerical Analysis · Mathematics 2009-09-30 Sebastien Boyaval , Tony Lelievre

Stochastic gradient-based optimisation for discrete latent variable models is challenging due to the high variance of gradients. We introduce a variance reduction technique for score function estimators that makes use of double control…

Machine Learning · Statistics 2022-06-07 Michalis K. Titsias , Jiaxin Shi

Control variates are variance reduction techniques for Monte Carlo estimators. They play a critical role in improving Monte Carlo estimators in scientific and machine learning applications that involve computationally expensive integrals.…

Methodology · Statistics 2026-02-27 Kaiyu Li , Yiming Yang , Xiaoyuan Cheng , Yi He , Zhuo Sun

The concept of the value-gradient is introduced and developed in the context of reinforcement learning. It is shown that by learning the value-gradients exploration or stochastic behaviour is no longer needed to find locally optimal…

Neural and Evolutionary Computing · Computer Science 2008-03-26 Michael Fairbank

Offline reinforcement learning provides a viable approach to obtain advanced control strategies for dynamical systems, in particular when direct interaction with the environment is not available. In this paper, we introduce a conceptual…

Machine Learning · Computer Science 2024-01-04 Marc Weber , Phillip Swazinna , Daniel Hein , Steffen Udluft , Volkmar Sterzing

Policy gradient methods can solve complex tasks but often fail when the dimensionality of the action-space or objective multiplicity grow very large. This occurs, in part, because the variance on score-based gradient estimators scales…

Machine Learning · Computer Science 2021-11-24 Thomas Spooner , Nelson Vadori , Sumitra Ganesh

Gradient-based optimization methods are commonly used to identify local optima in high-dimensional spaces. When derivatives cannot be evaluated directly, stochastic estimators can provide approximate gradients. However, these estimators'…

Machine Learning · Computer Science 2026-02-03 Philipp Andelfinger , Wentong Cai

Policy gradient methods are very attractive in reinforcement learning due to their model-free nature and convergence guarantees. These methods, however, suffer from high variance in gradient estimation, resulting in poor sample efficiency.…

Machine Learning · Computer Science 2018-11-16 Sergey Pankov

The quantile varying coefficient (VC) model can flexibly capture dynamical patterns of regression coefficients. In addition, due to the quantile check loss function, it is robust against outliers and heavy-tailed distributions of the…

Methodology · Statistics 2023-07-11 Fei Zhou , Jie Ren , Shuangge Ma , Cen Wu

We propose a method for designing policies for convex stochastic control problems characterized by random linear dynamics and convex stage cost. We consider policies that employ quadratic approximate value functions as a substitute for the…

Optimization and Control · Mathematics 2023-11-10 Alan Yang , Stephen Boyd

Multivariate functions encountered in high-dimensional uncertainty quantification problems often vary most strongly along a few dominant directions in the input parameter space. We propose a gradient-based method for detecting these…

Analysis of PDEs · Mathematics 2019-11-11 Olivier Zahm , Paul Constantine , Clémentine Prieur , Youssef Marzouk

We introduce a novel policy learning method that integrates analytical gradients from differentiable environments with the Proximal Policy Optimization (PPO) algorithm. To incorporate analytical gradients into the PPO framework, we…

Machine Learning · Computer Science 2023-12-15 Sanghyun Son , Laura Yu Zheng , Ryan Sullivan , Yi-Ling Qiao , Ming C. Lin

Several authors have recently developed risk-sensitive policy gradient methods that augment the standard expected cost minimization problem with a measure of variability in cost. These studies have focused on specific risk-measures, such as…

Artificial Intelligence · Computer Science 2015-06-09 Aviv Tamar , Yinlam Chow , Mohammad Ghavamzadeh , Shie Mannor

We introduce a variational algorithm to estimate the likelihood of a rare event within a nonequilibrium molecular dynamics simulation through the evaluation of an optimal control force. Optimization of a control force within a chosen basis…

Statistical Mechanics · Physics 2021-01-14 Avishek Das , David T. Limmer

Modern language models often need to optimize a primary accuracy objective while also accommodating secondary behavioral preferences, such as verbosity, agreeableness, or the level of technical expertise in its response. In practice, a base…

Machine Learning · Computer Science 2026-05-18 Xuechen Zhang , Zijian Huang , Kai Yang , Weijia Zhang , Jiasi Chen , Samet Oymak

The task of estimating the gradient of a function in the presence of noise is central to several forms of reinforcement learning, including policy search methods. We present two techniques for reducing gradient estimation errors in the…

Machine Learning · Computer Science 2012-12-12 Gregory Lawrence , Noah Cowan , Stuart Russell

Black-box variational inference performance is sometimes hindered by the use of gradient estimators with high variance. This variance comes from two sources of randomness: Data subsampling and Monte Carlo sampling. While existing control…

Machine Learning · Computer Science 2024-03-11 Xi Wang , Tomas Geffner , Justin Domke

Variational Quantum Circuits are being used as versatile Quantum Machine Learning models. Some empirical results exhibit an advantage in supervised and generative learning tasks. However, when applied to Reinforcement Learning, less is…

Quantum Physics · Physics 2023-01-18 André Sequeira , Luis Paulo Santos , Luís Soares Barbosa

Approximate inference in complex probabilistic models such as deep Gaussian processes requires the optimisation of doubly stochastic objective functions. These objectives incorporate randomness both from mini-batch subsampling of the data…

Machine Learning · Statistics 2020-03-26 Ayman Boustati , Sattar Vakili , James Hensman , ST John