Hypervolume indicator and dominance reward based multi-objective Monte-Carlo tree search

DOI10.1007/S10994-013-5369-0MaRDI QIDQ374142zbMATH OpenOpenAlexFDO

Authors Michèle Sebag, Weijia Wang

Publication date 22 October 2013

Published in Machine Learning (Search for Journal in Brave)

Full work available at URL https://doi.org/10.1007/s10994-013-5369-0

zbMATH Keywords

multi-objective optimizationsequential decision makingMonte-Carlo tree searchreinforcement learning

Mathematics Subject Classification ID

Monte Carlo methods (65C05) Learning and adaptive systems in artificial intelligence (68T05) Multi-objective and goal programming (90C29)

Recommendations

• Hypervolume-based multiobjective optimization: theoretical foundations and practical implications
• Many-objective optimization and hypervolume based search.
• Improving multivariate Horner schemes with Monte Carlo tree search
• A comparison of Monte Carlo tree search and rolling horizon optimization for large-scale dynamic resource allocation problems
• A new hypervolume-based differential evolution algorithm for many-objective optimization

Cites work

• scientific article; zbMATH DE number 5957207 (Why is no real title available?)
• scientific article; zbMATH DE number 1975103 (Why is no real title available?)
• scientific article; zbMATH DE number 6276214 (Why is no real title available?)
• Algorithms for reinforcement learning.
• Finite-time analysis of the multiarmed bandit problem
• Markov Decision Processes with Multiple Long-Run Average Objectives
• Multi-objective optimization using evolutionary algorithms
• NP-complete scheduling problems
• SMS-EMOA: multiobjective selection based on dominated hypervolume
• Theory of the hypervolume indicator: optimal \(\mu\)-distributions and the choice of the reference point
• Workflow Scheduling Algorithms for Grid Computing

Cited in

(3)

• Interactive Thompson sampling for multi-objective multi-armed bandits
• Automated streamliner portfolios for constraint satisfaction problems
• Multi-objective reinforcement learning using sets of Pareto dominating policies

Describes a project that uses

Uses Software

• SMS-EMOA
• CMA-ES

This page was built for publication: Hypervolume indicator and dominance reward based multi-objective Monte-Carlo tree search

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q374142)