Interactive Thompson sampling for multi-objective multi-armed bandits

DOI10.1007/978-3-319-67504-6_2MaRDI QIDQ1990281zbMATH OpenOpenAlexFDO

Authors Diederik M. Roijers, Luisa M. Zintgraf, Ann Nowé

Publication date 25 October 2018

Full work available at URL https://doi.org/10.1007/978-3-319-67504-6_2

Mathematics Subject Classification ID

Management decision making, including multiple objectives (90B50) Utility theory (91B16) Software, source code, etc. for problems pertaining to operations research and mathematical programming (90-04)

Recommendations

• Hypervolume indicator and dominance reward based multi-objective Monte-Carlo tree search
• Efficient multi-objective reinforcement learning via multiple-gradient descent with iteratively discovered weight-vector sets
• A Survey of Preference-Based Online Learning with Bandit Algorithms
• Multi-objective reinforcement learning using sets of Pareto dominating policies
• scientific article; zbMATH DE number 6276176

Cited in

(1)

• FlexiBO: A Decoupled Cost-Aware Multi-Objective Optimization Approach for Deep Neural Networks

This page was built for publication: Interactive Thompson sampling for multi-objective multi-armed bandits

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q1990281)