English
Related papers

Related papers: Trajectory-wise Control Variates for Variance Redu…

200 papers

In many sequential decision-making problems we may want to manage risk by minimizing some measure of variability in costs in addition to minimizing a standard criterion. Conditional value-at-risk (CVaR) is a relatively new risk measure that…

Artificial Intelligence · Computer Science 2014-07-14 Yinlam Chow , Mohammad Ghavamzadeh

Sequence generation models are commonly refined with reinforcement learning over user-defined metrics. However, high gradient variance hinders the practical use of this method. To stabilize this method, we adapt to contextual generation of…

Machine Learning · Statistics 2020-06-18 Xinjie Fan , Yizhe Zhang , Zhendong Wang , Mingyuan Zhou

We study a variance reduction strategy based on control variables for simulating the averaged macroscopic behavior of a stochastic slow-fast system. We assume that this averaged behavior can be written in terms of a few slow degrees of…

Numerical Analysis · Mathematics 2016-09-16 Ward Melis , Giovanni Samaey

In this work, we tackle the problem of minimising the Conditional-Value-at-Risk (CVaR) of output quantities of complex differential models with random input data, using gradient-based approaches in combination with the Multi-Level Monte…

Numerical Analysis · Mathematics 2023-10-16 Sundar Ganesh , Fabio Nobile

Policy gradient methods have had great success in solving continuous control tasks, yet the stochastic nature of such problems makes deterministic value estimation difficult. We propose an approach which instead estimates a distribution by…

Machine Learning · Computer Science 2017-12-07 Peter Henderson , Thang Doan , Riashat Islam , David Meger

Monte Carlo (MC) sampling algorithms are an extremely widely-used technique to estimate expectations of functions f(x), especially in high dimensions. Control variates are a very powerful technique to reduce the error of such estimates, but…

Machine Learning · Statistics 2016-06-08 Brendan D. Tracey , David H. Wolpert

Sequential decision-making under cost-sensitive tasks is prohibitively daunting, especially for the problem that has a significant impact on people's daily lives, such as malaria control, treatment recommendation. The main challenge faced…

Machine Learning · Computer Science 2021-05-06 Lixin Zou , Long Xia , Linfang Hou , Xiangyu Zhao , Dawei Yin

Multi-step temporal difference (TD) learning is an important approach in reinforcement learning, as it unifies one-step TD learning with Monte Carlo methods in a way where intermediate algorithms can outperform either extreme. They address…

Machine Learning · Computer Science 2018-09-10 Kristopher De Asis , Richard S. Sutton

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

Many popular statistical models for complex phenomena are intractable, in the sense that the likelihood function cannot easily be evaluated. Bayesian estimation in this setting remains challenging, with a lack of computational methodology…

Computation · Statistics 2015-03-31 Nial Friel , Antonietta Mira , Chris. J. Oates

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

Policy evaluation via Monte Carlo (MC) simulation is at the core of many MC Reinforcement Learning (RL) algorithms (e.g., policy gradient methods). In this context, the designer of the learning system specifies an interaction budget that…

Machine Learning · Computer Science 2024-10-18 Riccardo Poiani , Nicole Nobili , Alberto Maria Metelli , Marcello Restelli

In this paper a novel modification of the multilevel Monte Carlo approach, allowing for further significant complexity reduction, is proposed. The idea of the modification is to use the method of control variates to reduce variance at level…

Computational Finance · Quantitative Finance 2017-03-14 Denis Belomestny , Tigran Nagapetyan

Features in machine learning problems are often time-varying and may be related to outputs in an algebraic or dynamical manner. The dynamic nature of these machine learning problems renders current higher order accelerated gradient descent…

Optimization and Control · Mathematics 2019-05-29 Joseph E. Gaudio , Travis E. Gibson , Anuradha M. Annaswamy , Michael A. Bolender

We study risk-sensitive Reinforcement Learning (RL), where we aim to maximize the Conditional Value at Risk (CVaR) with a fixed risk tolerance $\tau$. Prior theoretical work studying risk-sensitive RL focuses on the tabular Markov Decision…

Machine Learning · Computer Science 2023-11-21 Yulai Zhao , Wenhao Zhan , Xiaoyan Hu , Ho-fung Leung , Farzan Farnia , Wen Sun , Jason D. Lee

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

We propose a sampling-based framework for finite-horizon trajectory and policy optimization under differentiable dynamics by casting controller design as inference. Specifically, we minimize a KL-regularized expected trajectory cost, which…

Machine Learning · Computer Science 2026-05-12 Heng Yang

State-of-the-art model-based Reinforcement Learning (RL) approaches either use gradient-free, population-based methods for planning, learned policy networks, or a combination of policy networks and planning. Hybrid approaches that combine…

Machine Learning · Computer Science 2026-05-25 Jonathan Spieler , Sven Behnke

Model Predictive Control (MPC) enables reliable trajectory optimization under dynamics constraints, but often depends on accurate dynamics models and carefully hand-designed cost functions. Recent learning-based MPC methods aim to reduce…

Robotics · Computer Science 2026-03-05 Shizhe Cai , Zeya Yin , Jayadeep Jacob , Fabio Ramos

Cross-validation (CV) is widely used for tuning a model with respect to user-selected parameters and for selecting a "best" model. For example, the method of $k$-nearest neighbors requires the user to choose $k$, the number of neighbors,…

Applications · Statistics 2012-03-01 Hui Shen , William J. Welch , Jacqueline M. Hughes-Oliver