English
Related papers

Related papers: Generalized Emphatic Temporal Difference Learning:…

200 papers

We consider off-policy policy evaluation with function approximation (FA) in average-reward MDPs, where the goal is to estimate both the reward rate and the differential value function. For this problem, bootstrapping is necessary and,…

Machine Learning · Computer Science 2022-10-19 Shangtong Zhang , Yi Wan , Richard S. Sutton , Shimon Whiteson

This paper deals with the asymptotic behavior and FEM error analysis of a class of strongly damped wave equations using a semidiscrete finite element method in spatial directions combined with a finite difference scheme in the time…

Numerical Analysis · Mathematics 2025-11-03 Krishan Kumar , P. Danumjaya , Anil Kumar , Amiya K. Pani

We study the generalization performance of online learning algorithms trained on samples coming from a dependent source of data. We show that the generalization error of any stable online algorithm concentrates around its regret--an easily…

Machine Learning · Statistics 2012-06-08 Alekh Agarwal , John C. Duchi

The policy gradient theorem (Sutton et al., 2000) prescribes the usage of a cumulative discounted state distribution under the target policy to approximate the gradient. Most algorithms based on this theorem, in practice, break this…

Machine Learning · Computer Science 2022-07-08 Samuele Tosatto , Andrew Patterson , Martha White , A. Rupam Mahmood

The goal of this paper is to investigate distributed temporal difference (TD) learning for a networked multi-agent Markov decision process. The proposed approach is based on distributed optimization algorithms, which can be interpreted as…

Machine Learning · Computer Science 2025-05-14 Han-Dong Lim , Donghwan Lee

Differential temporal difference (TD) methods are value-based reinforcement learning algorithms that have been proposed for infinite-horizon problems. They rely on reward centering, where each reward is centered by the average reward. This…

Machine Learning · Computer Science 2026-05-07 Kris De Asis , Mohamed Elsayed , Jiamin He

Timed automata are the formal model for real-time systems. Extensions with discrete probabilistic branching have been considered in the literature and successfully applied. Probabilistic timed automata (PTA) do require all branching…

Logic in Computer Science · Computer Science 2024-03-05 Darion Haase , Joost-Pieter Katoen

Gradient temporal difference (Gradient TD) algorithms are a popular class of stochastic approximation (SA) algorithms used for policy evaluation in reinforcement learning. Here, we consider Gradient TD algorithms with an additional heavy…

Machine Learning · Computer Science 2021-11-23 Rohan Deb , Shalabh Bhatnagar

We study off-policy evaluation and learning from sequential data in a structured class of Markov decision processes that arise from repeated interactions with an exogenous sequence of arrivals with contexts, which generate unknown…

Machine Learning · Computer Science 2021-10-20 Nathan Kallus , Angela Zhou

We consider off-policy evaluation of dynamic treatment rules under sequential ignorability, given an assumption that the underlying system can be modeled as a partially observed Markov decision process (POMDP). We propose an estimator,…

Machine Learning · Computer Science 2023-05-10 Yuchen Hu , Stefan Wager

This paper introduces a novel family of generalized exponentiated gradient (EG) updates derived from an Alpha-Beta divergence regularization function. Collectively referred to as EGAB, the proposed updates belong to the category of…

Machine Learning · Computer Science 2024-12-30 Andrzej Cichocki , Sergio Cruces , Auxiliadora Sarmiento , Toshihisa Tanaka

Recently, Sidford, Wang, Wu and Ye (2018) developed an algorithm combining variance reduction techniques with value iteration to solve discounted Markov decision processes. This algorithm has a sublinear complexity when the discount factor…

Optimization and Control · Mathematics 2019-09-16 Marianne Akian , Stéphane Gaubert , Zheng Qu , Omar Saadi

The problem of topic modeling can be seen as a generalization of the clustering problem, in that it posits that observations are generated due to multiple latent factors (e.g., the words in each document are generated as a mixture of…

Machine Learning · Computer Science 2013-01-21 Animashree Anandkumar , Dean P. Foster , Daniel Hsu , Sham M. Kakade , Yi-Kai Liu

Entropic tilting (ET) is a Bayesian decision-analytic method for constraining distributions to satisfy defined targets or bounds for sets of expectations. This report recapitulates the foundations and basic theory of ET for conditioning…

Methodology · Statistics 2022-08-16 Emily Tallman , Mike West

We develop a generic data-driven method for estimator selection in off-policy policy evaluation settings. We establish a strong performance guarantee for the method, showing that it is competitive with the oracle estimator, up to a constant…

Machine Learning · Computer Science 2020-08-25 Yi Su , Pavithra Srinath , Akshay Krishnamurthy

In multivariable time series (MTS) forecasting, existing state-of-the-art deep learning approaches tend to focus on autoregressive formulations and often overlook the potential of using exogenous variables in enhancing the prediction of the…

Machine Learning · Computer Science 2025-04-03 Yuxuan Shu , Vasileios Lampos

We present an approach for penalized tensor decomposition (PTD) that estimates smoothly varying latent factors in multi-way data. This generalizes existing work on sparse tensor decomposition and penalized matrix decompositions, in a manner…

Methodology · Statistics 2016-05-16 Oscar Hernan Madrid Padilla , James G. Scott

Estimation of Distribution Algorithms (EDAs) are stochastic heuristics that search for optimal solutions by learning and sampling from probabilistic models. Despite their popularity in real-world applications, there is little rigorous…

Neural and Evolutionary Computing · Computer Science 2018-07-27 Duc-Cuong Dang , Per Kristian Lehre , Phan Trung Hai Nguyen

Two-timescale stochastic approximation (TTSA) is among the most general frameworks for iterative stochastic algorithms. This includes well-known stochastic optimization methods such as SGD variants and those designed for bilevel or minimax…

Machine Learning · Statistics 2024-02-15 Jie Hu , Vishwaraj Doshi , Do Young Eun

Understanding the confidence with which a machine learning model classifies an input datum is an important, and perhaps under-investigated, concept. In this paper, we propose a new calibration metric, the Entropic Calibration Difference…

Machine Learning · Computer Science 2025-02-21 Daniel James Sumler , Lee Devlin , Simon Maskell , Richard O. Lane