English
Related papers

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

200 papers

This paper investigates methods for estimating the optimal stochastic control policy for a Markov Decision Process with unknown transition dynamics and an unknown reward function. This form of model-free reinforcement learning comprises…

Machine Learning · Computer Science 2019-12-06 Brandon Trabucco , Albert Qu , Simon Li , Ganeshkumar Ashokavardhanan

The policy gradient approach is a flexible and powerful reinforcement learning method particularly for problems with continuous actions such as robot control. A common challenge in this scenario is how to reduce the variance of policy…

Machine Learning · Computer Science 2013-01-18 Tingting Zhao , Hirotaka Hachiya , Voot Tangkaratt , Jun Morimoto , Masashi Sugiyama

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

Reinforcement learning constantly deals with hard integrals, for example when computing expectations in policy evaluation and policy iteration. These integrals are rarely analytically solvable and typically estimated with the Monte Carlo…

Machine Learning · Computer Science 2022-02-23 Sebastien M. R. Arnold , Pierre L'Ecuyer , Liyu Chen , Yi-fan Chen , Fei Sha

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

Being able to solve a task in diverse ways makes agents more robust to task variations and less prone to local optima. In this context, constrained diversity optimization has become a useful reinforcement learning (RL) framework for…

Machine Learning · Computer Science 2026-05-13 Cornelius V. Braun , Sayantan Auddy , Marc Toussaint

Reinforcement learning algorithms utilizing policy gradients (PG) to optimize Conditional Value at Risk (CVaR) face significant challenges with sample inefficiency, hindering their practical applications. This inefficiency stems from two…

Machine Learning · Computer Science 2024-07-01 Yudong Luo , Yangchen Pan , Han Wang , Philip Torr , Pascal Poupart

Deep generative models such as conditional variational autoencoders (CVAEs) have shown great promise for predicting trajectories of surrounding agents in autonomous vehicle planning. State-of-the-art models have achieved remarkable accuracy…

Robotics · Computer Science 2025-10-14 Yongxi Cao , Julian F. Schumann , Jens Kober , Joni Pajarinen , Arkady Zgonnikov

Reinforcement learning provides a mathematical framework for learning-based control, whose success largely depends on the amount of data it can utilize. The efficient utilization of historical trajectories obtained from previous policies is…

Machine Learning · Computer Science 2025-03-06 Yifan Lin , Yuhao Wang , Enlu Zhou

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

Variance reduction techniques have been shown by others in the past to be a useful tool to reduce variance in Simulation studies. However, their application and success in the past has been mainly domain specific, with relatively little…

Computational Engineering, Finance, and Science · Computer Science 2013-06-03 Adrian Adewunmi , Uwe Aickelin

Many machine learning problems involve Monte Carlo gradient estimators. As a prominent example, we focus on Monte Carlo variational inference (MCVI) in this paper. The performance of MCVI crucially depends on the variance of its stochastic…

Machine Learning · Statistics 2018-07-05 Alexander Buchholz , Florian Wenzel , Stephan Mandt

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

Monte Carlo (MC) sampling is a popular method for estimating the statistics (e.g. expectation and variance) of a random variable. Its slow convergence has led to the emergence of advanced techniques to reduce the variance of the MC…

Statistics Theory · Mathematics 2024-06-21 Mohamed Reda El Amri , Paul Mycek , Sophie Ricci , Matthias De Lozzo

Policy gradient methods are among the most effective methods for large-scale reinforcement learning, and their empirical success has prompted several works that develop the foundation of their global convergence theory. However, prior works…

Machine Learning · Computer Science 2020-12-25 Junzi Zhang , Jongho Kim , Brendan O'Donoghue , Stephen Boyd

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 describe and analyze a variance reduction approach for Monte Carlo (MC) sampling that accelerates the estimation of statistics of computationally expensive simulation models using an ensemble of models with lower cost. These lower cost…

Computation · Statistics 2021-05-04 Alex A. Gorodetsky , Gianluca Geraci , Mike Eldred , John D. Jakeman

In order to model risk aversion in reinforcement learning, an emerging line of research adapts familiar algorithms to optimize coherent risk functionals, a class that includes conditional value-at-risk (CVaR). Because optimizing the…

Machine Learning · Computer Science 2021-03-09 Audrey Huang , Liu Leqi , Zachary C. Lipton , Kamyar Azizzadenesheli

Monte Carlo estimation in plays a crucial role in stochastic reaction networks. However, reducing the statistical uncertainty of the corresponding estimators requires sampling a large number of trajectories. We propose control variates…

Methodology · Statistics 2021-10-19 Michael Backenköhler , Luca Bortolussi , Verena Wolf

The development of efficient numerical methods for kinetic equations with stochastic parameters is a challenge due to the high dimensionality of the problem. Recently we introduced a multiscale control variate strategy which is capable to…

Numerical Analysis · Mathematics 2018-12-14 Giacomo Dimarco , Lorenzo Pareschi