English
Related papers

Related papers: Pessimistic Off-Policy Multi-Objective Optimizatio…

200 papers

Reinforcement Learning (RL) has been shown effective in domains where the agent can learn policies by actively interacting with its operating environment. However, if we change the RL scheme to offline setting where the agent can only…

Machine Learning · Computer Science 2021-11-11 Jinning Li , Chen Tang , Masayoshi Tomizuka , Wei Zhan

To date, the multi-objective optimization literature has mainly focused on conflicting objectives, studying the Pareto front, or requiring users to balance tradeoffs. Yet, in machine learning practice, there are many scenarios where such…

Machine Learning · Computer Science 2025-03-05 Yonathan Efroni , Ben Kretzu , Daniel Jiang , Jalaj Bhandari , Zheqing , Zhu , Karen Ullrich

Some real problems require the evaluation of expensive and noisy objective functions. Moreover, the analytical expression of these objective functions may be unknown. These functions are known as black-boxes, for example, estimating the…

Machine Learning · Statistics 2021-07-12 Lucia Asencio Martín , Eduardo C. Garrido-Merchán

In this work, a new multiobjective optimization algorithm called multiobjective learner performance-based behavior algorithm is proposed. The proposed algorithm is based on the process of transferring students from high school to college.…

Neural and Evolutionary Computing · Computer Science 2022-01-31 Chnoor M. Rahman , Tarik A. Rashid , Aram Mahmood Ahmed , Seyedali Mirjalili

The optimal allocation of assets has been widely discussed with the theoretical analysis of risk measures, and pessimism is one of the most attractive approaches beyond the conventional optimal portfolio model. The $\alpha$-risk plays a…

Portfolio Management · Quantitative Finance 2024-05-20 Sungchul Hong , Jong-June Jeon

Offline reinforcement learning (RL), where the agent aims to learn the optimal policy based on the data collected by a behavior policy, has attracted increasing attention in recent years. While offline RL with linear function approximation…

Machine Learning · Computer Science 2024-10-10 Qiwei Di , Heyang Zhao , Jiafan He , Quanquan Gu

Searching the space of policies directly for the optimal policy has been one popular method for solving partially observable reinforcement learning problems. Typically, with each change of the target policy, its value is estimated from the…

Artificial Intelligence · Computer Science 2007-05-23 Leonid Peshkin , Christian R. Shelton

Real-world problems typically require the simultaneous optimization of several, often conflicting objectives. Many of these multi-objective optimization problems are characterized by wide ranges of uncertainties in their decision variables…

Neural and Evolutionary Computing · Computer Science 2019-10-21 Faramarz Khosravi , Alexander Raß , Jürgen Teich

The goal of multi-objective optimisation is to identify a collection of points which describe the best possible trade-offs between the multiple objectives. In order to solve this vector-valued optimisation problem, practitioners often…

Optimization and Control · Mathematics 2025-05-09 Ben Tu , Nikolas Kantas , Robert M. Lee , Behrang Shafei

This study concentrates on clustering problems and aims to find compact clusters that are informative regarding the outcome variable. The main goal is partitioning data points so that observations in each cluster are similar and the outcome…

Neural and Evolutionary Computing · Computer Science 2022-01-27 Zahra Ghasemi , Hadi Akbarzadeh Khorshidi , Uwe Aickelin

Multi-objective optimisation problems involve finding solutions with varying trade-offs between multiple and often conflicting objectives. Ising machines are physical devices that aim to find the absolute or approximate ground states of an…

Artificial Intelligence · Computer Science 2023-05-22 Mayowa Ayodele , Richard Allmendinger , Manuel López-Ibáñez , Arnaud Liefooghe , Matthieu Parizy

Reinforcement Learning, a machine learning framework for training an autonomous agent based on rewards, has shown outstanding results in various domains. However, it is known that learning a good policy is difficult in a domain where…

Machine Learning · Computer Science 2019-06-27 Takahisa Imagawa , Takuya Hiraoka , Yoshimasa Tsuruoka

Policy optimization is an effective reinforcement learning approach to solve continuous control tasks. Recent achievements have shown that alternating online and offline optimization is a successful choice for efficient trajectory reuse.…

Machine Learning · Computer Science 2018-11-01 Alberto Maria Metelli , Matteo Papini , Francesco Faccio , Marcello Restelli

We study Off-Policy Evaluation (OPE) in contextual bandit settings with large action spaces. The benchmark estimators suffer from severe bias and variance tradeoffs. Parametric approaches suffer from bias due to difficulty specifying the…

Machine Learning · Statistics 2023-12-15 Tatsuhiro Shimizu , Laura Forastiere

This paper proposes a new family of algorithms for the online optimisation of composite objectives. The algorithms can be interpreted as the combination of the exponentiated gradient and $p$-norm algorithm. Combined with algorithmic ideas…

Optimization and Control · Mathematics 2022-08-09 Weijia Shao , Fikret Sivrikaya , Sahin Albayrak

We present a novel, input-output data-driven approach to uncertainty model identification. As the true bounds and distributions of system uncertainties ultimately remain unknown, we depart from the goal of identifying the uncertainty model…

Systems and Control · Electrical Eng. & Systems 2025-08-29 Jannes Hühnerbein , Jad Wehbeh , Eric C. Kerrigan

This paper is concerned with constructing a confidence interval for a target policy's value offline based on a pre-collected observational data in infinite horizon settings. Most of the existing works assume no unmeasured variables exist…

Machine Learning · Statistics 2022-11-07 Chengchun Shi , Jin Zhu , Ye Shen , Shikai Luo , Hongtu Zhu , Rui Song

In many real world problems, optimization decisions have to be made with limited information. The decision maker may have no a priori or posteriori data about the often nonconvex objective function except from on a limited number of points…

Optimization and Control · Mathematics 2011-11-10 Tansu Alpcan

Inverse optimization describes a process that is the "reverse" of traditional mathematical optimization. Unlike traditional optimization, which seeks to compute optimal decisions given an objective and constraints, inverse optimization…

Optimization and Control · Mathematics 2022-07-28 Timothy C. Y. Chan , Rafid Mahmood , Ian Yihang Zhu

In this paper we propose a general framework to characterize and solve the stochastic optimization problems with multiple objectives underlying many real world learning applications. We first propose a projection based algorithm which…

Machine Learning · Computer Science 2013-07-16 Mehrdad Mahdavi , Tianbao Yang , Rong Jin