English
Related papers

Related papers: Why Should I Trust You, Bellman? The Bellman Error…

200 papers

Calibration, the practice of choosing the parameters of a structural model to match certain empirical moments, can be viewed as minimum distance estimation. Existing standard error formulas for such estimators require a consistent estimate…

Econometrics · Economics 2024-06-19 Matthew D. Cocci , Mikkel Plagborg-Møller

Mermin states in a recent paper that his nontechnical version of Bell's theorem stands and is not invalidated by time and setting dependent instrument parameters as claimed in one of our previous papers. We identify a number of…

Quantum Physics · Physics 2007-05-23 Karl Hess , Walter Philipp

Estimating the value function for a fixed policy is a fundamental problem in reinforcement learning. Policy evaluation algorithms---to estimate value functions---continue to be developed, to improve convergence rates, improve stability and…

Machine Learning · Statistics 2018-08-29 Touqir Sajed , Wesley Chung , Martha White

We study the convergence of $Q$-learning with linear function approximation. Our key contribution is the introduction of a novel multi-Bellman operator that extends the traditional Bellman operator. By exploring the properties of this…

Machine Learning · Computer Science 2023-10-02 Diogo S. Carvalho , Pedro A. Santos , Francisco S. Melo

The empirical proof of Bell inequality violations was a landmark moment for research into quantum foundations. It commits us to a universe without strict relativistic locality or requires that we escape through a potential loophole like…

Quantum Physics · Physics 2026-05-29 Geoff Beck

Every prediction is ultimately used in a downstream task. Consequently, evaluating prediction quality is more meaningful when considered in the context of its downstream use. Metrics based solely on predictive performance often diverge from…

Machine Learning · Computer Science 2025-08-26 Novin Shahroudi , Viacheslav Komisarenko , Meelis Kull

Evaluation of the Bellman functions is a difficult task. The exact Bellman functions of the dyadic Carleson Embedding Theorem 1.1 and the dyadic maximal operators are obtained in [3] and [4]. Actually, the same Bellman functions also work…

Classical Analysis and ODEs · Mathematics 2015-02-12 Jingguo Lai

Decision makers often need to rely on imperfect probabilistic forecasts. While average performance metrics are typically available, it is difficult to assess the quality of individual forecasts and the corresponding utilities. To convey…

Machine Learning · Statistics 2021-03-03 Shengjia Zhao , Stefano Ermon

Motion planning under uncertainty for an autonomous system can be formulated as a Markov Decision Process with a continuous state space. In this paper, we propose a novel solution to this decision-theoretic planning problem that directly…

Robotics · Computer Science 2020-07-02 Junhong Xu , Kai Yin , Lantao Liu

In 2008 I thought I found a proof of the Riemann Hypothesis, but there was an error. In the Spring 2020 I believed to have fixed the error, but it cannot be fixed. I describe here where the error was. It took me several days to find the…

General Mathematics · Mathematics 2021-01-19 Jorma Jormakka

Often in real-world datasets, especially in high dimensional data, some feature values are missing. Since most data analysis and statistical methods do not handle gracefully missing values, the first step in the analysis requires the…

Machine Learning · Statistics 2016-12-08 Yehezkel S. Resheff , Daphna Weinshall

A class of distortions termed functional Bregman divergences is defined, which includes squared error and relative entropy. A functional Bregman divergence acts on functions or distributions, and generalizes the standard Bregman divergence…

Information Theory · Computer Science 2007-07-13 B. A. Frigyik , S. Srivastava , M. R. Gupta

In this work, we show that Bell's inequality violation of arise from the fact that the condition imposed upon the development of inequality is not respected when it is applied in the idealized experiment. Such a condition is that the…

Quantum Physics · Physics 2020-06-16 Felipe Andrade Velozo , José A. C. Nogales

The value function formulation captures the hierarchical nature of bilevel optimization through the optimal value function of the lower level problem, yet its implicit and nonsmooth characteristics pose significant analytical and…

Optimization and Control · Mathematics 2025-10-21 Mengwei Xu , Yu-Hong Dai , Xin-Wei Liu , Meiqi Ma

Bregman divergences are a class of distance-like comparison functions which play fundamental roles in optimization, statistics, and information theory. One important property of Bregman divergences is that they cause two useful formulations…

Information Theory · Computer Science 2025-01-07 Philip S. Chodrow

A method for calculating multi-portfolio time consistent multivariate risk measures in discrete time is presented. Market models for $d$ assets with transaction costs or illiquidity and possible trading constraints are considered on a…

Risk Management · Quantitative Finance 2017-01-27 Zachary Feinstein , Birgit Rudloff

This paper presents a new filter for state-space models based on Bellman's dynamic-programming principle, allowing for nonlinearity, non-Gaussianity and degeneracy in the observation and/or state-transition equations. The resulting Bellman…

Methodology · Statistics 2025-02-18 Rutger-Jan Lange

The paper deals with a risk averse dynamic programming problem with infinite horizon. First, the required assumptions are formulated to have the problem well defined. Then the Bellman equation is derived, which may be also seen as a…

Optimization and Control · Mathematics 2022-08-04 Martin Šmíd , Miloš Kopa

A primary requirement for any reinforcement learning method is that it should produce policies that improve upon the initial guess. In this work, we show that the widely used Deep Q-Network (DQN) fails to satisfy this minimal criterion --…

Machine Learning · Computer Science 2025-06-18 Aditya Gopalan , Gugan Thoppe

Approximate value iteration (AVI) is a family of algorithms for reinforcement learning (RL) that aims to obtain an approximation of the optimal value function. Generally, AVI algorithms implement an iterated procedure where each step…

Machine Learning · Computer Science 2024-03-07 Théo Vincent , Alberto Maria Metelli , Boris Belousov , Jan Peters , Marcello Restelli , Carlo D'Eramo