English
Related papers

Related papers: Finite-Sample Analysis of the Monte Carlo Explorin…

200 papers

Sequential decision problems are often approximately solvable by simulating possible future action sequences. {\em Metalevel} decision procedures have been developed for selecting {\em which} action sequences to simulate, based on…

Artificial Intelligence · Computer Science 2012-07-26 Nicholas Hay , Stuart Russell , David Tolpin , Solomon Eyal Shimony

Quantiles and expected shortfalls are usually used to measure risks of stochastic systems, which are often estimated by Monte Carlo methods. This paper focuses on the use of quasi-Monte Carlo (QMC) method, whose convergence rate is…

Numerical Analysis · Mathematics 2020-05-07 Zhijian He , Xiaoqun Wang

To plan safely in uncertain environments, agents must balance utility with safety constraints. Safe planning problems can be modeled as a chance-constrained partially observable Markov decision process (CC-POMDP) and solutions often use…

Artificial Intelligence · Computer Science 2024-05-02 Robert J. Moss , Arec Jamgochian , Johannes Fischer , Anthony Corso , Mykel J. Kochenderfer

We study risk-sensitive RL where the goal is learn a history-dependent policy that optimizes some risk measure of cumulative rewards. We consider a family of risks called the optimized certainty equivalents (OCE), which captures important…

Machine Learning · Computer Science 2025-03-03 Kaiwen Wang , Dawen Liang , Nathan Kallus , Wen Sun

We study the policy evaluation problem in an online multi-reward multi-policy discounted setting, where multiple reward functions must be evaluated simultaneously for different policies. We adopt an $(\epsilon,\delta)$-PAC perspective to…

Machine Learning · Computer Science 2025-08-19 Alessio Russo , Aldo Pacchiano

This paper studies the use of a machine learning-based estimator as a control variate for mitigating the variance of Monte Carlo sampling. Specifically, we seek to uncover the key factors that influence the efficiency of control variates in…

Statistics Theory · Mathematics 2023-05-29 Jose Blanchet , Haoxuan Chen , Yiping Lu , Lexing Ying

We consider the problem of reinforcement learning when provided with (1) a baseline control policy and (2) a set of constraints that the learner must satisfy. The baseline policy can arise from demonstration data or a teacher agent and may…

Machine Learning · Computer Science 2021-07-13 Tsung-Yen Yang , Justinian Rosca , Karthik Narasimhan , Peter J. Ramadge

This paper concerns the approximation of smooth, high-dimensional functions from limited samples using polynomials. This task lies at the heart of many applications in computational science and engineering - notably, some of those arising…

Numerical Analysis · Mathematics 2023-11-07 Ben Adcock , Simone Brugiapaglia

Most provably-efficient learning algorithms introduce optimism about poorly-understood states and actions to encourage exploration. We study an alternative approach for efficient exploration, posterior sampling for reinforcement learning…

Machine Learning · Statistics 2013-12-30 Ian Osband , Daniel Russo , Benjamin Van Roy

The optimal stopping problem is a category of decision problems with a specific constrained configuration. It is relevant to various real-world applications such as finance and management. To solve the optimal stopping problem,…

Computational Finance · Quantitative Finance 2022-08-02 Leonardo Kanashiro Felizardo , Elia Matsumoto , Emilio Del-Moral-Hernandez

It is often necessary to make sampling-based statistical inference about many probability distributions in parallel. Given a finite computational resource, this article addresses how to optimally divide sampling effort between the samplers…

Methodology · Statistics 2015-02-18 Nicholas Heard , Melissa Turcotte

Bayesian optimization is a popular framework for efficiently tackling black-box search problems. As a rule, these algorithms operate by iteratively choosing what to evaluate next until some predefined budget has been exhausted. We…

Machine Learning · Statistics 2024-12-12 James T. Wilson

In the Monte Carlo (MC) method statistical noise is usually present. Statistical noise may become dominant in the calculation of a distribution, usually by iteration, but is less Important in calculating integrals. The subject of the…

Computational Physics · Physics 2013-11-08 Mihály Makai , Zoltán Szatmáry

We investigate the exploration of an unknown environment when no reward function is provided. Building on the incremental exploration setting introduced by Lim and Auer [1], we define the objective of learning the set of $\epsilon$-optimal…

Machine Learning · Computer Science 2021-01-01 Jean Tarbouriech , Matteo Pirotta , Michal Valko , Alessandro Lazaric

Purpose: In recent years Monte-Carlo sampling methods, such as Monte Carlo tree search, have achieved tremendous success in model free reinforcement learning. A combination of the so called upper confidence bounds policy to preserve the…

Artificial Intelligence · Computer Science 2011-10-24 Boris Mitavskiy , Jonathan Rowe , Chris Cannings

In many problems, complex non-Gaussian and/or nonlinear models are required to accurately describe a physical system of interest. In such cases, Monte Carlo algorithms are remarkably flexible and extremely powerful approaches to solve such…

Computation · Statistics 2015-04-23 Thi Le Thu Nguyen , Francois Septier , Gareth W. Peters , Yves Delignon

Random sampling of graph partitions under constraints has become a popular tool for evaluating legislative redistricting plans. Analysts detect partisan gerrymandering by comparing a proposed redistricting plan with an ensemble of sampled…

Applications · Statistics 2023-11-09 Cory McCartan , Kosuke Imai

Reinforcement Learning has drawn huge interest as a tool for solving optimal control problems. Solving a given problem (task or environment) involves converging towards an optimal policy. However, there might exist multiple optimal policies…

Machine Learning · Computer Science 2023-02-16 Simo Alami. C , Fernando Llorente , Rim Kaddah , Luca Martino , Jesse Read

The class of deep deterministic off-policy algorithms is effectively applied to solve challenging continuous control problems. Current approaches commonly utilize random noise as an exploration method, which has several drawbacks, including…

Machine Learning · Computer Science 2024-05-07 Igor Kuznetsov

In this paper, we present the Monte-Carlo Compressive Optimization algorithm, a new method to solve a combinatorial optimization problem that is assumed compressible. The method relies on random queries to the objective function in order to…

Optimization and Control · Mathematics 2025-10-30 Baptiste Chevalier , Shimpei Yamaguchi , Wojciech Roga , Masahiro Takeoka