English
Related papers

Related papers: Efficient Learning for Entropy-Regularized Markov …

200 papers

We consider large-scale Markov decision processes (MDPs) with parameter uncertainty, under the robust MDP paradigm. Previous studies showed that robust MDPs, based on a minimax approach to handle uncertainty, can be solved using dynamic…

Machine Learning · Computer Science 2013-06-27 Aviv Tamar , Huan Xu , Shie Mannor

This article reviews the application of advanced Monte Carlo techniques in the context of Multilevel Monte Carlo (MLMC). MLMC is a strategy employed to compute expectations which can be biased in some sense, for instance, by using the…

Computation · Statistics 2017-04-25 Ajay Jasra , Kody Law , Carina Suciu

We address the approximation of functionals depending on a system of particles, described by stochastic differential equations (SDEs), in the mean-field limit when the number of particles approaches infinity. This problem is equivalent to…

Numerical Analysis · Mathematics 2017-05-02 Abdul-Lateef Haji-Ali , Raul Tempone

Markov Chain Monte Carlo (MCMC) algorithms are often used for approximate inference inside learning, but their slow mixing can be difficult to diagnose and the approximations can seriously degrade learning. To alleviate these issues, we…

Machine Learning · Computer Science 2015-02-25 Jacob Steinhardt , Percy Liang

In supervised learning, we fit a single statistical model to a given data set, assuming that the data is associated with a singular task, which yields well-tuned models for specific use, but does not adapt well to new contexts. By contrast,…

Machine Learning · Computer Science 2020-09-11 Bingjia Wang , Alec Koppel , Vikram Krishnamurthy

We present a hierarchical reinforcement learning framework that formulates each task in the hierarchy as a special type of Markov decision process for which the Bellman equation is linear and has analytical solution. Problems of this type,…

Artificial Intelligence · Computer Science 2016-03-11 Anders Jonsson , Vicenç Gómez

Markov Decision Processes (MDPs) offer a fairly generic and powerful framework to discuss the notion of optimal policies for dynamic systems, in particular when the dynamics are stochastic. However, computing the optimal policy of an MDP…

Systems and Control · Electrical Eng. & Systems 2024-07-24 Dirk Reinhardt , Akhil S. Anand , Shambhuraj Sawant , Sebastien Gros

Fairness plays a crucial role in various multi-agent systems (e.g., communication networks, financial markets, etc.). Many multi-agent dynamical interactions can be cast as Markov Decision Processes (MDPs). While existing research has…

Machine Learning · Computer Science 2023-06-02 Peizhong Ju , Arnob Ghosh , Ness B. Shroff

We propose a novel Continuation Multi Level Monte Carlo (CMLMC) algorithm for weak approximation of stochastic models. The CMLMC algorithm solves the given approximation problem for a sequence of decreasing tolerances, ending when the…

Numerical Analysis · Mathematics 2015-05-22 Nathan Collier , Abdul-Lateef Haji-Ali , Fabio Nobile , Erik von Schwerin , Raul Tempone

As the size of engineered systems grows, problems in reliability theory can become computationally challenging, often due to the combinatorial growth in the cut sets. In this paper we demonstrate how Multilevel Monte Carlo (MLMC) - a…

Computation · Statistics 2017-03-14 Louis J. M. Aslett , Tigran Nagapetyan , Sebastian J. Vollmer

We propose empirical dynamic programming algorithms for Markov decision processes (MDPs). In these algorithms, the exact expectation in the Bellman operator in classical value iteration is replaced by an empirical estimate to get `empirical…

Optimization and Control · Mathematics 2013-11-26 William B. Haskell , Rahul Jain , Dileep Kalathil

This paper considers a new approach to using Markov chain Monte Carlo (MCMC) in contexts where one may adopt multilevel (ML) Monte Carlo. The underlying problem is to approximate expectations w.r.t. an underlying probability measure that is…

Numerical Analysis · Mathematics 2018-06-27 Ajay Jasra , Kody Law , Yaxian Xu

Markov Chain Monte Carlo (MCMC) methods sample from unnormalized probability distributions and offer guarantees of exact sampling. However, in the continuous case, unfavorable geometry of the target distribution can greatly limit the…

Machine Learning · Statistics 2020-10-09 Zengyi Li , Yubei Chen , Friedrich T. Sommer

In this paper we develop a very efficient approach to the Monte Carlo estimation of the expected value of partial perfect information (EVPPI) that measures the average benefit of knowing the value of a subset of uncertain parameters…

Numerical Analysis · Mathematics 2019-12-09 Michael B. Giles , Takashi Goda

We extend the Longstaff-Schwartz algorithm for approximately solving optimal stopping problems on high-dimensional state spaces. We reformulate the optimal stopping problem for Markov processes in discrete time as a generalized statistical…

Probability · Mathematics 2007-05-23 Daniel Egloff

In this work, we present, analyze, and implement a class of Multi-Level Markov chain Monte Carlo (ML-MCMC) algorithms based on independent Metropolis-Hastings proposals for Bayesian inverse problems. In this context, the likelihood function…

Numerical Analysis · Mathematics 2021-05-06 Juan Pablo Madrigal-Cianci , Fabio Nobile , Raul Tempone

Discrete time stochastic optimal control problems and Markov decision processes (MDPs) are fundamental models for sequential decision-making under uncertainty and as such provide the mathematical framework underlying reinforcement learning…

Optimization and Control · Mathematics 2025-07-01 Arnulf Jentzen , Konrad Kleinberg , Thomas Kruse

Markov decision processes (MDPs) are formal models commonly used in sequential decision-making. MDPs capture the stochasticity that may arise, for instance, from imprecise actuators via probabilities in the transition function. However, in…

Artificial Intelligence · Computer Science 2023-06-21 Marnix Suilen , Thiago D. Simão , David Parker , Nils Jansen

In this article we consider computing expectations w.r.t.~probability laws associated to a certain class of stochastic systems. In order to achieve such a task, one must not only resort to numerical approximation of the expectation, but…

Computation · Statistics 2017-10-30 Ajay Jasra , Kengo Kamatani , Kody Law , Yan Zhou

General purpose intelligent learning agents cycle through (complex,non-MDP) sequences of observations, actions, and rewards. On the other hand, reinforcement learning is well-developed for small finite state Markov Decision Processes…

Artificial Intelligence · Computer Science 2009-12-30 Marcus Hutter