English
Related papers

Related papers: Optimistic Value Iteration

200 papers

We demonstrate a limitation of discounted expected utility, a standard approach for representing the preference to risk when future cost is discounted. Specifically, we provide an example of the preference of a decision maker that appears…

Computer Science and Game Theory · Computer Science 2012-02-20 Takayuki Osogami

Minimizing the empirical risk is a popular training strategy, but for learning tasks where the data may be noisy or heavy-tailed, one may require many observations in order to generalize well. To achieve better performance under less…

Machine Learning · Statistics 2018-10-16 Matthew J. Holland , Kazushi Ikeda

In the design of probabilistic timed systems, bounded requirements concerning behaviour that occurs within a given time, energy, or more generally cost budget are of central importance. Traditionally, such requirements have been…

Logic in Computer Science · Computer Science 2016-05-19 Ernst Moritz Hahn , Arnd Hartmanns

This paper presents a new static analysis for deriving upper bounds on the expected resource consumption of probabilistic programs. The analysis is fully automatic and derives symbolic bounds that are multivariate polynomials of the inputs.…

Programming Languages · Computer Science 2017-11-27 Van Chan Ngo , Quentin Carbonneaux , Jan Hoffmann

Optimization algorithms appear in the core calculations of numerous Artificial Intelligence (AI) and Machine Learning methods, as well as Engineering and Business applications. Following recent works on the theoretical deficiencies of AI, a…

Optimization and Control · Mathematics 2024-10-29 Nikolaos P. Bakas , Vagelis Plevris , Andreas Langousis , Savvas A. Chatzichristofis

The aim of a probabilistic output analysis is to derive a probability distribution of possible output values for a program from a probability distribution of its input. We present a method for performing static output analysis, based on…

Programming Languages · Computer Science 2015-09-30 Mads Rosendahl , Maja H. Kirkeby

This paper discusses algorithms for solving Markov decision processes (MDPs) that have monotone optimal policies. We propose a two-stage alternating convex optimization scheme that can accelerate the search for an optimal policy by…

Systems and Control · Computer Science 2017-04-04 Robert Mattila , Cristian R. Rojas , Vikram Krishnamurthy , Bo Wahlberg

We consider the problem of learning control policies that optimize a reward function while satisfying constraints due to considerations of safety, fairness, or other costs. We propose a new algorithm, Projection-Based Constrained Policy…

Machine Learning · Computer Science 2020-10-08 Tsung-Yen Yang , Justinian Rosca , Karthik Narasimhan , Peter J. Ramadge

We propose a data-driven method to establish probabilistic performance guarantees for parametric optimization problems solved via iterative algorithms. Our approach addresses two key challenges: providing convergence guarantees to…

Optimization and Control · Mathematics 2025-10-31 Jingyi Huang , Paul Goulart , Kostas Margellos

This work focuses on optimal harvesting-renewing for a stochastic population. A mixed regular-singular control formulation with a state constraint and regime-switching is introduced. The decision-makers either harvest or renew with finite…

Optimization and Control · Mathematics 2022-11-07 K. Q. Tran , L. T. N. Bich , George Yin

Multi-turn human-AI collaboration is fundamental to deploying interactive services such as adaptive tutoring, conversational recommendation, and professional consultation. However, optimizing these interactions via reinforcement learning is…

Machine Learning · Computer Science 2026-03-26 Haoyu Wang , Yuxin Chen , Liang Luo , Buyun Zhang , Ellie Dingqiao Wen , Pan Li

We consider Bayesian optimization of an expensive-to-evaluate black-box objective function, where we also have access to cheaper approximations of the objective. In general, such approximations arise in applications such as reinforcement…

Machine Learning · Statistics 2016-11-16 Matthias Poloczek , Jialei Wang , Peter I. Frazier

Policy iteration and value iteration are at the core of many (approximate) dynamic programming methods. For Markov Decision Processes with finite state and action spaces, we show that they are instances of semismooth Newton-type methods to…

Optimization and Control · Mathematics 2022-06-28 Matilde Gargiani , Andrea Zanelli , Dominic Liao-McPherson , Tyler Summers , John Lygeros

A standard objective in partially-observable Markov decision processes (POMDPs) is to find a policy that maximizes the expected discounted-sum payoff. However, such policies may still permit unlikely but highly undesirable outcomes, which…

Artificial Intelligence · Computer Science 2017-01-31 Krishnendu Chatterjee , Petr Novotný , Guillermo A. Pérez , Jean-François Raskin , Đorđe Žikelić

We analyze the generalization and robustness of the batched weighted average algorithm for V-geometrically ergodic Markov data. This algorithm is a good alternative to the empirical risk minimization algorithm when the latter suffers from…

Machine Learning · Statistics 2014-08-13 Nguyen Viet Cuong , Lam Si Tung Ho , Vu Dinh

Iterative numerical algorithms are typically equipped with a stopping criterion, where the iteration process is terminated when some error or misfit measure is deemed to be below a given tolerance. This is a useful setting for comparing…

Numerical Analysis · Computer Science 2014-12-04 Uri Ascher , Farbod Roosta-Khorasani

Simple stochastic games can be solved by value iteration (VI), which yields a sequence of under-approximations of the value of the game. This sequence is guaranteed to converge to the value only in the limit. Since no stopping criterion is…

Logic in Computer Science · Computer Science 2021-02-02 Edon Kelmendi , Julia Krämer , Jan Kretinsky , Maximilian Weininger

Randomized experiments are the gold standard for evaluating the effects of changes to real-world systems. Data in these tests may be difficult to collect and outcomes may have high variance, resulting in potentially large measurement error.…

Machine Learning · Statistics 2018-06-27 Benjamin Letham , Brian Karrer , Guilherme Ottoni , Eytan Bakshy

Real-world recommender systems often need to balance multiple objectives when deciding which recommendations to present to users. These include behavioural signals (e.g. clicks, shares, dwell time), as well as broader objectives (e.g.…

Information Retrieval · Computer Science 2024-09-17 Olivier Jeunen , Jatin Mandav , Ivan Potapov , Nakul Agarwal , Sourabh Vaid , Wenzhe Shi , Aleksei Ustimenko

The choice of the parameter value for regularized inverse problems is critical to the results and remains a topic of interest. This article explores a criterion for selecting a good parameter value by maximizing the probability of the data,…

Numerical Analysis · Mathematics 2020-02-11 Toby Sanders , Rodrigo B. Platte , Robert D. Skeel