English
Related papers

Related papers: GenDICE: Generalized Offline Estimation of Station…

200 papers

This paper introduces a Bayesian framework that combines Markov chain Monte Carlo (MCMC) sampling, dimensionality reduction, and neural density estimation to efficiently handle inverse problems that (i) must be solved multiple times, and…

Computational Engineering, Finance, and Science · Computer Science 2026-02-24 Giacomo Bottacini , Matteo Torzoni , Andrea Manzoni

The identification of distribution network topology and parameters is a critical problem that lays the foundation for improving network efficiency, enhancing reliability, and increasing its capacity to host distributed energy resources.…

Systems and Control · Electrical Eng. & Systems 2023-08-23 Ognjen Stanojev , Lucien Werner , Steven Low , Gabriela Hug

Gradient-based methods for optimisation of objectives in stochastic settings with unknown or intractable dynamics require estimators of derivatives. We derive an objective that, under automatic differentiation, produces low-variance…

Machine Learning · Computer Science 2019-09-25 Gregory Farquhar , Shimon Whiteson , Jakob Foerster

We present a distributional approach to theoretical analyses of reinforcement learning algorithms for constant step-sizes. We demonstrate its effectiveness by presenting simple and unified proofs of convergence for a variety of…

Machine Learning · Computer Science 2020-03-30 Philip Amortila , Doina Precup , Prakash Panangaden , Marc G. Bellemare

Offline reinforcement learning aims to utilize datasets of previously gathered environment-action interaction records to learn a policy without access to the real environment. Recent work has shown that offline reinforcement learning can be…

Machine Learning · Computer Science 2023-08-30 Hanhan Zhou , Tian Lan , Vaneet Aggarwal

In this study, we investigate the DIstribution Correction Estimation (DICE) methods, an important line of work in offline reinforcement learning (RL) and imitation learning (IL). DICE-based methods impose state-action-level behavior…

Machine Learning · Computer Science 2024-02-02 Liyuan Mao , Haoran Xu , Weinan Zhang , Xianyuan Zhan

Gradient estimation -- approximating the gradient of an expectation with respect to the parameters of a distribution -- is central to the solution of many machine learning problems. However, when the distribution is discrete, most common…

Machine Learning · Statistics 2024-04-16 Jiaxin Shi , Yuhao Zhou , Jessica Hwang , Michalis K. Titsias , Lester Mackey

We study offline Reinforcement Learning in large infinite-horizon discounted Markov Decision Processes (MDPs) when the reward and transition models are linearly realizable under a known feature map. Starting from the classic linear-program…

Machine Learning · Computer Science 2024-05-24 Gergely Neu , Nneka Okolo

Offline imitation from observations aims to solve MDPs where only task-specific expert states and task-agnostic non-expert state-action pairs are available. Offline imitation is useful in real-world scenarios where arbitrary interactions…

Machine Learning · Computer Science 2023-11-03 Kai Yan , Alexander G. Schwing , Yu-Xiong Wang

A common tool in the practice of Markov Chain Monte Carlo is to use approximating transition kernels to speed up computation when the desired kernel is slow to evaluate or intractable. A limited set of quantitative tools exist to assess the…

Probability · Mathematics 2026-01-14 Jeffrey Negrea , Jeffrey S. Rosenthal

The recently proposed distribution correction estimation (DICE) family of estimators has advanced the state of the art in off-policy evaluation from behavior-agnostic data. While these estimators all perform some form of stationary…

Machine Learning · Computer Science 2020-07-28 Mengjiao Yang , Ofir Nachum , Bo Dai , Lihong Li , Dale Schuurmans

Ordinary differential equations (ODEs) provide a powerful framework for modeling dynamic systems arising in a wide range of scientific domains. However, most existing ODE methods focus on a single system, and do not adequately address the…

Methodology · Statistics 2026-04-08 Shuoxun Xu , Zijian Guo , Brooke R. Staveland , Robert T. Knight , Lexin Li

Deploying reinforcement learning (RL) in safety-critical settings is constrained by brittleness under distribution shift. We study out-of-distribution (OOD) detection for RL time series and introduce DEEDEE, a two-statistic detector that…

Machine Learning · Computer Science 2025-10-27 Tala Aljaafari , Varun Kanade , Philip Torr , Christian Schroeder de Witt

Off-policy evaluation (OPE) is one of the most fundamental problems in reinforcement learning (RL) to estimate the expected long-term payoff of a given target policy with only experiences from another behavior policy that is potentially…

Machine Learning · Computer Science 2024-10-24 Yang Hu , Tianyi Chen , Na Li , Kai Wang , Bo Dai

Learning a predictive model of the mean return, or value function, plays a critical role in many reinforcement learning algorithms. Distributional reinforcement learning (DRL) has been shown to improve performance by modeling the value…

Machine Learning · Computer Science 2025-07-08 Ju-Seung Byun , Andrew Perrault

Irreversible and rejection-free Monte Carlo methods, recently developed in Physics under the name Event-Chain and known in Statistics as Piecewise Deterministic Monte Carlo (PDMC), have proven to produce clear acceleration over standard…

Computation · Statistics 2020-04-28 Manon Michel , Alain Durmus , Stéphane Sénécal

Sequential Monte Carlo (SMC), or particle filtering, is widely used in nonlinear state-space systems, but its performance often suffers from poorly approximated proposal and state-transition distributions. This work introduces a…

Machine Learning · Computer Science 2026-05-14 Wessel L. van Nierop , Nir Shlezinger , Ruud J. G. van Sloun

We develop a new continuous-time stochastic gradient descent method for optimizing over the stationary distribution of stochastic differential equation (SDE) models. The algorithm continuously updates the SDE model's parameters using an…

Machine Learning · Computer Science 2023-08-29 Ziheng Wang , Justin Sirignano

A novel class of non-reversible Markov chain Monte Carlo schemes relying on continuous-time piecewise-deterministic Markov Processes has recently emerged. In these algorithms, the state of the Markov process evolves according to a…

Methodology · Statistics 2018-05-16 Paul Vanetti , Alexandre Bouchard-Côté , George Deligiannidis , Arnaud Doucet

Many Imitation and Reinforcement Learning approaches rely on the availability of expert-generated demonstrations for learning policies or value functions from data. Obtaining a reliable distribution of trajectories from motion planners is…

Robotics · Computer Science 2021-07-13 Alexander Lambert , Byron Boots