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

DOI10.1007/s10994-013-5369-0zbMath1273.68308OpenAlexW1974819972MaRDI QIDQ374142

Michèle Sebag, Wei-Jia 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 optimizationreinforcement learningsequential decision makingMonte-Carlo tree search

Mathematics Subject Classification ID

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

Related Items (1)

Automated streamliner portfolios for constraint satisfaction problems

Uses Software

• CMA-ES
• SMS-EMOA

Cites Work

• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item
• SMS-EMOA: multiobjective selection based on dominated hypervolume
• NP-complete scheduling problems
• Algorithms for Reinforcement Learning
• Workflow Scheduling Algorithms for Grid Computing
• Theory of the hypervolume indicator
• Markov Decision Processes with Multiple Long-Run Average Objectives
• Finite-time analysis of the multiarmed bandit problem

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