Analyzing bandit-based adaptive operator selection mechanisms

DOI10.1007/s10472-010-9213-yzbMath1226.68081OpenAlexW1977474365MaRDI QIDQ647443

Álvaro Fialho, Marc Schoenauer, Michèle Sebag, Luis Da Costa

Publication date: 23 November 2011

Published in: Annals of Mathematics and Artificial Intelligence (Search for Journal in Brave)

Full work available at URL: https://doi.org/10.1007/s10472-010-9213-y

zbMATH Keywords

multi-armed banditsparameter controladaptive operator selection

Mathematics Subject Classification ID

Learning and adaptive systems in artificial intelligence (68T05) Problem solving in the context of artificial intelligence (heuristics, search strategies, etc.) (68T20)

Related Items (15)

An adaptive evolutionary approach for real-time vehicle routing and dispatching ⋮ Autonomous operator management for evolutionary algorithms ⋮ A dynamic Thompson sampling hyper-heuristic framework for learning activity planning in personalized learning ⋮ Multi-constructor CMSA for the maximum disjoint dominating sets problem ⋮ Multi-armed bandit-based hyper-heuristics for combinatorial optimization problems ⋮ Hyperparameter autotuning of programs with HybridTuner ⋮ Adaptive operator selection with reinforcement learning ⋮ Differential evolution with adaptive trial vector generation strategy and cluster-replacement-based feasibility rule for constrained optimization ⋮ Adaptive multimeme algorithm for flexible job shop scheduling problem ⋮ Using Automated Algorithm Configuration for Parameter Control ⋮ Analyzing bandit-based adaptive operator selection mechanisms ⋮ Self-adjusting mutation rates with provably optimal success rules ⋮ Latest stored information based adaptive selection strategy for multiobjective evolutionary algorithm ⋮ A methodology for determining an effective subset of heuristics in selection hyper-heuristics ⋮ Gorthaur-EXP3: bandit-based selection from a portfolio of recommendation algorithms balancing the accuracy-diversity dilemma

Uses Software

• Genocop

Cites Work

• Unnamed Item
• Algorithm portfolio selection as a bandit problem with unbounded losses
• Autonomous operator management for evolutionary algorithms
• Analyzing bandit-based adaptive operator selection mechanisms
• Parameter setting in evolutionary algorithms.
• Asymptotically efficient adaptive allocation rules
• Evolutionary computation in practice
• The Sequential Parameter Optimization Toolbox
• Inference about the change-point from cumulative sum tests
• Artificial Evolution
• Introduction to evolutionary computing
• Finite-time analysis of the multiarmed bandit problem

This page was built for publication: Analyzing bandit-based adaptive operator selection mechanisms