Multi-objective dynamic programming with limited precision

DOI10.1007/S10898-021-01096-XMaRDI QIDQ2114599zbMATHOpenAlexFDO

Authors Yanyan Li

Publication date 15 March 2022

Published in Journal of Global Optimization (Search for Journal in Brave)

Copyright license Creative Commons Attribution 4.0 International

Full work available at URL https://arxiv.org/abs/2009.08198

zbMATH Keywords

dynamic programmingMarkov decision processesmulti-objectivereinforcement learning

Mathematics Subject Classification ID

Multi-objective and goal programming (90C29) Dynamic programming (90C39) Markov and semi-Markov decision processes (90C40)

Abstract: This paper addresses the problem of approximating the set of all solutions for Multi-objective Markov Decision Processes. We show that in the vast majority of interesting cases, the number of solutions is exponential or even infinite. In order to overcome this difficulty we propose to approximate the set of all solutions by means of a limited precision approach based on White's multi-objective value-iteration dynamic programming algorithm. We prove that the number of calculated solutions is tractable and show experimentally that the solutions obtained are a good approximation of the true Pareto front.

Recommendations

• Solution procedures for multi-objective markov decision processes
• Markov Decision Processes with Multiple Objectives
• Publication:3486378
• A discrete dynamic programming approximation to the multiobjective deterministic finite horizon optimal control problem
• Approximating multi-objective scheduling problems

Cites work

• scientific article; zbMATH DE number 3694968 (Why is no real title available?)
• scientific article; zbMATH DE number 700091 (Why is no real title available?)
• A survey of multi-objective sequential decision-making
• Multi-Objective Decision Making
• Multi-Objective Model Checking of Markov Decision Processes
• Multi-objective infinite-horizon discounted Markov decision processes
• Multi-objective reinforcement learning using sets of Pareto dominating policies
• Note on Multiple Objective Dynamic Programming
• Preface on the special issue global optimization with multiple criteria: theory, methods and applications
• Quantitative multi-objective verification for probabilistic systems
• Reinforcement learning. An introduction

Cited in

(3)

• scientific article; zbMATH DE number 4158413 (Why is no real title available?)
• Efficient multiobjective optimization employing Gaussian processes, spectral sampling and a genetic algorithm
• Multiple objective dynamic programming with forward filtering

This page was built for publication: Multi-objective dynamic programming with limited precision

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q2114599)